SIMON Master Console Rebuild
True command center for SIMON + WEB360
This rebuild gives you a cleaner production spine: interactive tree, live viewer, guarded editor, dynamic graphics, architecture map, and note storage. It is designed to sit beside your existing
console.php
and become the stronger replacement path.
Dashboard
Tree
Viewer
System Map
File Registry
Notes
Files
15,551
Folders
418
Scanned Size
3.85 GB
PHP Files
915
Editable Text Files
12,812
File viewer
guarded to /htdocs
/live/cache/arxiv_ai_96f295cc4b4d.json
{ "ok": true, "items": [ { "id": "f016fcd0610a8874cb62ac122ebc7eb4f39f290f", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "OriginBlame: Record- and Token-Level Data Provenance for AI Training Datasets", "summary": "arXiv:2607.13037v1 Announce Type: new Abstract: When a data contributor requests removal, model trainers face a practical gap: unlearning algorithms require a forget set, yet no tool can locate which training records belong to a given author. Existing provenance systems operate at file or dataset level, forcing catastrophic over-deletion. We present ob, a record- and token-level data provenance system that propagates author identity through data processing pipelines and resolves revocation requests into precise forget sets via deterministic queries. Evaluation on 219,555 Wikipedia pages demonstrates that record-level provenance eliminates dataset-level over-deletion (from 101x to 1.3x), while integration adds 1.3-4.0% throughput overhead (HuggingFace) and 2.1-19.0% (Datatrove) on wiki data. On a 1.7B model, provenance-based forget sets improve unlearning by 42% over random baselines.", "url": "https://arxiv.org/abs/2607.13037", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "OriginBlame: Record- and Token-Level Data Provenance for AI Training Datasets", "summary": "arXiv:2607.13037v1 Announce Type: new \nAbstract: When a data contributor requests removal, model trainers face a practical gap: unlearning algorithms require a forget set, yet no tool can locate which training records belong to a given author. Existing provenance systems operate at file or dataset level, forcing catastrophic over-deletion. We present ob, a record- and token-level data provenance system that propagates author identity through data processing pipelines and resolves revocation requests into precise forget sets via deterministic queries. Evaluation on 219,555 Wikipedia pages demonstrates that record-level provenance eliminates dataset-level over-deletion (from 101x to 1.3x), while integration adds 1.3-4.0% throughput overhead (HuggingFace) and 2.1-19.0% (Datatrove) on wiki data. On a 1.7B model, provenance-based forget sets improve unlearning by 42% over random baselines.", "url": "https://arxiv.org/abs/2607.13037", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "2036255f9888e53bb9c80ee07e650ee632b3b36c", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "SPINE: Bridging the Cyber-Physical Gap with Agentic AI", "summary": "arXiv:2607.13049v1 Announce Type: new Abstract: Foundation models have given robots a sophisticated brain for complex decision-making, yet deploying that intelligence into a physical platform still demands tedious, expert-driven calibration. This deployment gap, the robot's spinal cord, remains a primary bottleneck to scalable Embodied AI. Hence, we propose SPINE (Scalable Physical Integration with ageNtic Expertise): an agentic framework for systematically debugging and deploying bimanual robots with minimal robotics expertise. SPINE's harness comprises two orchestrated multi-agent workflows: a profile builder that creates robot-specific context, and a debugger that cycles through diagnosis, repair, and validation until teleoperation works. Across seven DOBOT X-Trainer debugging scenarios, a robotics novice using SPINE outperformed human operators using Claude Code with the same refere…", "url": "https://arxiv.org/abs/2607.13049", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "SPINE: Bridging the Cyber-Physical Gap with Agentic AI", "summary": "arXiv:2607.13049v1 Announce Type: new \nAbstract: Foundation models have given robots a sophisticated brain for complex decision-making, yet deploying that intelligence into a physical platform still demands tedious, expert-driven calibration. This deployment gap, the robot's spinal cord, remains a primary bottleneck to scalable Embodied AI. Hence, we propose SPINE (Scalable Physical Integration with ageNtic Expertise): an agentic framework for systematically debugging and deploying bimanual robots with minimal robotics expertise. SPINE's harness comprises two orchestrated multi-agent workflows: a profile builder that creates robot-specific context, and a debugger that cycles through diagnosis, repair, and validation until teleoperation works. Across seven DOBOT X-Trainer debugging scenarios, a robotics novice using SPINE outperformed human operators using Claude Code with the same reference materials, but without SPINE's structured workflow, improving operationalization success from 75% to 100% and reducing mean time-to-teleoperation from 16 min 45 s to 13 min 47 s. On AgileX PiPER, a distinct ROS/CAN bimanual arm, SPINE resolved all 10 implanted bugs, versus 9 out of 10 for the expert baseline, in nearly the same amount of time. Together, these results show that SPINE can transfer across bimanual platforms, reduce dependence on expert calibration, and move embodied AI closer to scalable real-world deployment.", "url": "https://arxiv.org/abs/2607.13049", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "f7fc91c6e9afb6a3255a3bfa1f9f3fbbbc7d521c", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution", "summary": "arXiv:2607.13069v1 Announce Type: new Abstract: Large language models produce chain-of-thought (CoT) reasoning that appears logically sound yet may not genuinely depend on its stated premises. We introduce interventional grounding audits, a black-box, step-level test of premise dependency: we intervene on a single premise by substituting its target predicate with a fresh symbol, re-run the model, and check whether each reasoning step's normalized conclusion (canonical predicate form) changes. We evaluate on ProntoQA, a synthetic multi-hop deductive reasoning benchmark with gold proof trees, where step-level premise dependencies are known. Applied to 50 ProntoQA problems with GPT-4o, our method achieves F1 = 0.806 on detecting proof-tree dependencies (F1 = 0.885 on predicate-determining dependencies; Recall = 100%), significantly outperforming a self-consistency baseline (F1 = 0.343; 95%…", "url": "https://arxiv.org/abs/2607.13069", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution", "summary": "arXiv:2607.13069v1 Announce Type: new \nAbstract: Large language models produce chain-of-thought (CoT) reasoning that appears logically sound yet may not genuinely depend on its stated premises. We introduce interventional grounding audits, a black-box, step-level test of premise dependency: we intervene on a single premise by substituting its target predicate with a fresh symbol, re-run the model, and check whether each reasoning step's normalized conclusion (canonical predicate form) changes. We evaluate on ProntoQA, a synthetic multi-hop deductive reasoning benchmark with gold proof trees, where step-level premise dependencies are known. Applied to 50 ProntoQA problems with GPT-4o, our method achieves F1 = 0.806 on detecting proof-tree dependencies (F1 = 0.885 on predicate-determining dependencies; Recall = 100%), significantly outperforming a self-consistency baseline (F1 = 0.343; 95% bootstrap CIs non-overlapping). We further identify that 66% of correctly-solved problems contain at least one aligned step insensitive to a direct proof-tree dependency under consistent substitution -- all involving entity-introduction premises, a documented blind spot of the consistent-substitution evaluator -- a \"right answer, wrong reasoning\" signal invisible to passive methods. All audit certificates, raw outputs, and reproduction scripts are available in a public GitHub repository, and we discuss scope limits beyond formal, parsable benchmarks.", "url": "https://arxiv.org/abs/2607.13069", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "b5237b24a49187a355e242e8b60dcbaea8b08849", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "Probabilistic Extension of Neuro-Symbolic AGI Robots based on Belnap's Typed Intensional FOL", "summary": "arXiv:2607.13073v1 Announce Type: new Abstract: Neuro-symbolic AI based on $IFOL_B$ is a way to combine neural learning and symbolic reasoning to overcome limitations of purely neural systems (like lack of interpretability and logical structure) with formal logical machinery for self-reference. In this paper we expand the cognitive power of $IFOL_B$ by using the probability computation for the currently unknown sentences, based on Nilsson's probability structure for the $IFOL_B$. We introduce the global symmetry transformation that preserves the current knowledge database and logical deduction, and the local one used for real-time decisions about concrete (sub)problems that involve only a very strict subset of $IFOL_B$ predicates. The computation of probability density function $KI$ in both cases, based on the Shannon's maximum information entropy, is provided by neural networks of this…", "url": "https://arxiv.org/abs/2607.13073", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "Probabilistic Extension of Neuro-Symbolic AGI Robots based on Belnap's Typed Intensional FOL", "summary": "arXiv:2607.13073v1 Announce Type: new \nAbstract: Neuro-symbolic AI based on $IFOL_B$ is a way to combine neural learning and symbolic reasoning to overcome limitations of purely neural systems (like lack of interpretability and logical structure) with formal logical machinery for self-reference. In this paper we expand the cognitive power of $IFOL_B$ by using the probability computation for the currently unknown sentences, based on Nilsson's probability structure for the $IFOL_B$. We introduce the global symmetry transformation that preserves the current knowledge database and logical deduction, and the local one used for real-time decisions about concrete (sub)problems that involve only a very strict subset of $IFOL_B$ predicates. The computation of probability density function $KI$ in both cases, based on the Shannon's maximum information entropy, is provided by neural networks of this probabilistic neuro-symbolic AGI.", "url": "https://arxiv.org/abs/2607.13073", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "f421d5f3714105537e19b02effdad69eabdddbc9", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "Self-Improvements in Modern Agentic Systems: A Survey", "summary": "arXiv:2607.13104v1 Announce Type: new Abstract: Self-improving autonomous agents are moving from research prototypes to deployed systems. The primary goal is controllable evolution, or adaptation, from experience with minimal or even no human input. This survey frames modern self-improving agents as adaptive systems that convert experience into accumulated capability gains. We offer a system-level framework that represents a modern agent as a configuration coupling a foundation model with an operational scaffold of prompts, memory, tools, and control logic. Within this framework, self-improvement is formalized as a self-induced update operator that obtains and commits updates to model parameters or scaffold components. We organize prior work by update target and by the signals that drive change, then review applications and discuss evaluation, before closing with open problems and futur…", "url": "https://arxiv.org/abs/2607.13104", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "Self-Improvements in Modern Agentic Systems: A Survey", "summary": "arXiv:2607.13104v1 Announce Type: new \nAbstract: Self-improving autonomous agents are moving from research prototypes to deployed systems. The primary goal is controllable evolution, or adaptation, from experience with minimal or even no human input. This survey frames modern self-improving agents as adaptive systems that convert experience into accumulated capability gains. We offer a system-level framework that represents a modern agent as a configuration coupling a foundation model with an operational scaffold of prompts, memory, tools, and control logic. Within this framework, self-improvement is formalized as a self-induced update operator that obtains and commits updates to model parameters or scaffold components. We organize prior work by update target and by the signals that drive change, then review applications and discuss evaluation, before closing with open problems and future directions. For convenience, we track technical updates on https://github.com/selfimproving-agent/awesome-Self-Improving-Agents.", "url": "https://arxiv.org/abs/2607.13104", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "9c92a91ca27a06748a83e61542514554ac467327", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "Improving Molecular Property Prediction in Small Language Models Using Graph-based Tools", "summary": "arXiv:2607.13115v1 Announce Type: new Abstract: Small language models (SLMs) have shown promise for zero-shot molecular property prediction from SMILES strings, yet they often suffer from structural blindness because sequence representations under-specify key graph-topological cues. We propose a modular Context-Augmented Prompting framework that enables agentic tool use at inference time: a trained GNN expert model provides a predictive hint with confidence, and a GNN extracts an instance-specific explanatory subgraph (e.g., a subgraph SMILES and an accompanying explanatory paragraph). We evaluate three commonly used SLMs on MUTAG and Tox21 under five prompting configurations ranging from SMILES-only to using all available tools at hand. Across two datasets, enriching prompts with graph-derived context yields substantial accuracy gains, often exceeding 25% relative improvement and up to…", "url": "https://arxiv.org/abs/2607.13115", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "Improving Molecular Property Prediction in Small Language Models Using Graph-based Tools", "summary": "arXiv:2607.13115v1 Announce Type: new \nAbstract: Small language models (SLMs) have shown promise for zero-shot molecular property prediction from SMILES strings, yet they often suffer from structural blindness because sequence representations under-specify key graph-topological cues. We propose a modular Context-Augmented Prompting framework that enables agentic tool use at inference time: a trained GNN expert model provides a predictive hint with confidence, and a GNN extracts an instance-specific explanatory subgraph (e.g., a subgraph SMILES and an accompanying explanatory paragraph). We evaluate three commonly used SLMs on MUTAG and Tox21 under five prompting configurations ranging from SMILES-only to using all available tools at hand. Across two datasets, enriching prompts with graph-derived context yields substantial accuracy gains, often exceeding 25% relative improvement and up to 74% on Tox21. We further validate the functional relevance of the extracted motifs via a necessity-based edge-drop intervention. Despite the observed gains, a persistent gap remains to specialized GNN models, highlighting both the value and limits of text-conditioned reasoning for molecular structure.", "url": "https://arxiv.org/abs/2607.13115", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "2d5d12388faae9009cfd666f6d38dbce340876e6", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "Oracle Agent Memory as an Enterprise Memory Substrate for Long-Horizon AI Agents", "summary": "arXiv:2607.13157v1 Announce Type: new Abstract: Agent memory is a systems problem for long-horizon agents. Practical deployments require retention of task state across extended conversations, recovery of user-specific facts and preferences across sessions, and accumulation of procedural knowledge from prior outcomes. These requirements extend beyond document retrieval: a memory layer must determine which interactions become durable state, how that state is scoped, how it is retrieved under latency constraints, and how it is revised or removed over time. This report studies Oracle Agent Memory as a database-native memory substrate built on Oracle Database. Three themes organize the discussion: memory as a lifecycle spanning ingestion, extraction, consolidation, retrieval, summarization, and revision or removal; a layered architecture that separates an active memory core from a passive me…", "url": "https://arxiv.org/abs/2607.13157", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "Oracle Agent Memory as an Enterprise Memory Substrate for Long-Horizon AI Agents", "summary": "arXiv:2607.13157v1 Announce Type: new \nAbstract: Agent memory is a systems problem for long-horizon agents. Practical deployments require retention of task state across extended conversations, recovery of user-specific facts and preferences across sessions, and accumulation of procedural knowledge from prior outcomes. These requirements extend beyond document retrieval: a memory layer must determine which interactions become durable state, how that state is scoped, how it is retrieved under latency constraints, and how it is revised or removed over time. This report studies Oracle Agent Memory as a database-native memory substrate built on Oracle Database. Three themes organize the discussion: memory as a lifecycle spanning ingestion, extraction, consolidation, retrieval, summarization, and revision or removal; a layered architecture that separates an active memory core from a passive memory-store interface with explicit scope control across users, agents, and threads; and evaluation methodology in which downstream task accuracy is complemented by memory-centric measures such as evidence retrieval, recall, latency, and estimated token use. The report summarizes LongMemEval results, reaching 93.8% accuracy, compares Oracle Agent Memory against flat-history baselines, using about 10.7x fewer tokens, and published or reported external baselines where available, and closes with implementation-oriented appendix material covering setup, thread lifecycle, and search semantics.", "url": "https://arxiv.org/abs/2607.13157", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "b5ebfe7fcacb9fc413fe3fb399f6c1d66318e17c", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models", "summary": "arXiv:2607.13172v1 Announce Type: new Abstract: We address the problem of safely training an agent policy and deploying a good and safe policy, in settings where the environment dynamics are unknown and no suitable reward function is available. In the context of safety-critical environments, we consider traditional reinforcement learning impractical and resort to the resource of human input. We introduce DROPJ, a human-centred method for both safe training and deployment. We first learn a world model (a learned simulator) from a dataset of prior real-world trajectories. A human then plays the game in this learned simulator to extract several informative simulated trajectories. From these, we sample pairs of simulated trajectory segments and elicit from a human their preference over these segments, as well as a reason (justification) for their choice. We then train a reward model from th…", "url": "https://arxiv.org/abs/2607.13172", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models", "summary": "arXiv:2607.13172v1 Announce Type: new \nAbstract: We address the problem of safely training an agent policy and deploying a good and safe policy, in settings where the environment dynamics are unknown and no suitable reward function is available. In the context of safety-critical environments, we consider traditional reinforcement learning impractical and resort to the resource of human input. We introduce DROPJ, a human-centred method for both safe training and deployment. We first learn a world model (a learned simulator) from a dataset of prior real-world trajectories. A human then plays the game in this learned simulator to extract several informative simulated trajectories. From these, we sample pairs of simulated trajectory segments and elicit from a human their preference over these segments, as well as a reason (justification) for their choice. We then train a reward model from these justified preferences and use it, together with the world model, to directly deploy the agent using model predictive control. Running real-user experiments, we find that generating informative simulated trajectories from a user significantly reduces the computational cost during training compared to other strategies, and can also improve the performance during deployment. In the context of training within a learned simulator, we show that the use of preferences rather than other types of feedback substantially improves the performance during deployment. We further demonstrate that safety justifications accompanying preferences can significantly enhance safety or prioritise user-prescribed aspects of safety associated with them during deployment.", "url": "https://arxiv.org/abs/2607.13172", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "4c005c06e47a208f3caf5075a0a6a91b6186d6c0", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "CayleyR: Solving the TopSpin puzzle via cycle intersection", "summary": "arXiv:2607.13219v1 Announce Type: new Abstract: We present cayleyR, an R package for solving permutation puzzles by detecting cycle intersections in Cayley graphs. The core algorithm performs an iterative bidirectional search: from both the initial and target permutation states, random operation sequences generate cycles in the Cayley graph of the symmetric group Sn; their intersection yields a connecting path. When no direct intersection is found, a distance-guided bridge selection narrows the gap, and the process repeats. The package targets the TopSpin(n,k) puzzle, whose state space is a Cayley graph of Sn generated by a cyclic shift and a prefix reversal. We describe the mathematical framework, the algorithm, and its implementation, which combines a C++ hash-indexed state store with optional Vulkan GPU acceleration. The software is publicly available on CRAN.", "url": "https://arxiv.org/abs/2607.13219", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "CayleyR: Solving the TopSpin puzzle via cycle intersection", "summary": "arXiv:2607.13219v1 Announce Type: new \nAbstract: We present cayleyR, an R package for solving permutation puzzles by detecting cycle intersections in Cayley graphs. The core algorithm performs an iterative bidirectional search: from both the initial and target permutation states, random operation sequences generate cycles in the Cayley graph of the symmetric group Sn; their intersection yields a connecting path. When no direct intersection is found, a distance-guided bridge selection narrows the gap, and the process repeats. The package targets the TopSpin(n,k) puzzle, whose state space is a Cayley graph of Sn generated by a cyclic shift and a prefix reversal. We describe the mathematical framework, the algorithm, and its implementation, which combines a C++ hash-indexed state store with optional Vulkan GPU acceleration. The software is publicly available on CRAN.", "url": "https://arxiv.org/abs/2607.13219", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "b9b482c93c1a22a7c9e5d9d9230db8fb4953113e", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "Networked Intelligence: Active Shared Context Graphs for Human-AI Team Science", "summary": "arXiv:2607.13220v1 Announce Type: new Abstract: Most AI-for-science systems focus on scaling a single reasoning process through better models, larger context windows, long-horizon agentic execution, or digital co-scientists working with one principal user. However, challenging scientific problems are rarely solved by one reasoner alone. They are solved by teams whose members bring different priors, experimental backgrounds, tacit knowledge, and domain-trained intuitions. The open problem is therefore not only how to scale models, but how to cultivate networked intelligence: scaling the connections between humans and AI systems so that a result or hypothesis produced in one context reaches another person, agent, instrument, or robot that can act on it. We introduce Mycelium, an active shared workspace that automatically connects researchers and AI agents as a multi-user co-scientist. As …", "url": "https://arxiv.org/abs/2607.13220", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "Networked Intelligence: Active Shared Context Graphs for Human-AI Team Science", "summary": "arXiv:2607.13220v1 Announce Type: new \nAbstract: Most AI-for-science systems focus on scaling a single reasoning process through better models, larger context windows, long-horizon agentic execution, or digital co-scientists working with one principal user. However, challenging scientific problems are rarely solved by one reasoner alone. They are solved by teams whose members bring different priors, experimental backgrounds, tacit knowledge, and domain-trained intuitions. The open problem is therefore not only how to scale models, but how to cultivate networked intelligence: scaling the connections between humans and AI systems so that a result or hypothesis produced in one context reaches another person, agent, instrument, or robot that can act on it. We introduce Mycelium, an active shared workspace that automatically connects researchers and AI agents as a multi-user co-scientist. As human users and agents work, the system captures important observations and hypotheses, tracks how they relate to the team's evolving model, and routes them to the person or agent whose next decision they can inform. We evaluate Mycelium in its first empirical test, a biological multi-omics campaign in which routed shared context turned a local analytical finding into a cross-expert mechanistic constraint and ultimately into an experimental design. We also give networked intelligence a computational account as sparse conditional computation over distributed scientific contexts. This account distinguishes when a scaled standalone agent can match the network from when independent expertise and non-mergeable contexts make the network irreducible.", "url": "https://arxiv.org/abs/2607.13220", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "47a61470697146e456c6dd52180417684f3a4934", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "AI-Native Insurance for Agentic AI: Pricing, Underwriting, and End-to-End Automation", "summary": "arXiv:2607.13230v1 Announce Type: new Abstract: Agentic AI introduces new insurance challenges because autonomous AI systems can make decisions, invoke tools, modify external environments, and interact with third-party services. This paper develops an AI-native mathematical framework for underwriting, pricing, and contract design for agentic AI deployments. A deployment is represented by a risk state that captures autonomy level, operational authority, permission exposure, governance maturity, and dependency concentration. The framework maps the risk state to event probabilities, loss severities, governance costs, premiums, deductibles, coverage allocation, and policy covenants, and formulates an optimization problem for insurance contract design under participation, profitability, and incentive compatibility constraints. The paper establishes structural properties of insurability, incl…", "url": "https://arxiv.org/abs/2607.13230", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "AI-Native Insurance for Agentic AI: Pricing, Underwriting, and End-to-End Automation", "summary": "arXiv:2607.13230v1 Announce Type: new \nAbstract: Agentic AI introduces new insurance challenges because autonomous AI systems can make decisions, invoke tools, modify external environments, and interact with third-party services. This paper develops an AI-native mathematical framework for underwriting, pricing, and contract design for agentic AI deployments. A deployment is represented by a risk state that captures autonomy level, operational authority, permission exposure, governance maturity, and dependency concentration. The framework maps the risk state to event probabilities, loss severities, governance costs, premiums, deductibles, coverage allocation, and policy covenants, and formulates an optimization problem for insurance contract design under participation, profitability, and incentive compatibility constraints. The paper establishes structural properties of insurability, including characterization of an insurability region, monotone deterioration of feasibility with increasing exposure, and governance certification thresholds. Insurance is further interpreted as both an operational cost and a regulatory mechanism for AI deployment. A healthcare case study illustrates contract optimization, sensitivity analysis, and automated claims processing for agentic AI systems.", "url": "https://arxiv.org/abs/2607.13230", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "d54a596bbf6306d8e35951276f3fd96fe48579c2", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "Cost-Optimal Foundation Model Deployment Portfolio for Transportation Management", "summary": "arXiv:2607.13239v1 Announce Type: new Abstract: Foundation models, including large language models (LLMs) and vision-language models (VLMs), are increasingly used for transportation management center (TMC) tasks such as anomaly detection, incident reporting, and traveler information. Deploying multiple such models across TMC functions raises a portfolio question: which model should serve each function, in which deployment mode, and under what shared hardware budget? We formulate this as the Foundation Model Deployment Portfolio (FMDP) problem, a mixed-integer program minimizing total cost of ownership (TCO) subject to per-function quality, latency, and safety constraints over shared GPU capacity. We prove the problem NP-hard by reduction from the 0-1 knapsack problem and propose a polynomial-time greedy heuristic. In an illustrative case study with five TMC functions and 19 candidate (m…", "url": "https://arxiv.org/abs/2607.13239", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "Cost-Optimal Foundation Model Deployment Portfolio for Transportation Management", "summary": "arXiv:2607.13239v1 Announce Type: new \nAbstract: Foundation models, including large language models (LLMs) and vision-language models (VLMs), are increasingly used for transportation management center (TMC) tasks such as anomaly detection, incident reporting, and traveler information. Deploying multiple such models across TMC functions raises a portfolio question: which model should serve each function, in which deployment mode, and under what shared hardware budget? We formulate this as the Foundation Model Deployment Portfolio (FMDP) problem, a mixed-integer program minimizing total cost of ownership (TCO) subject to per-function quality, latency, and safety constraints over shared GPU capacity. We prove the problem NP-hard by reduction from the 0-1 knapsack problem and propose a polynomial-time greedy heuristic. In an illustrative case study with five TMC functions and 19 candidate (model, mode) pairs, FMDP identifies a mixed portfolio costing $34/mo (97% below the cheapest feasible all-closed-API baseline) by routing four functions to open-source APIs and the one function whose quality floor no open-source model meets to a closed API. Break-even analysis shows that on-premise GPU investment becomes reasonable only above approximately 309 vision queries/hour or if API prices double.", "url": "https://arxiv.org/abs/2607.13239", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "4e64e11616063db4cc55bab81c4127a8394b317d", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable", "summary": "arXiv:2607.13285v1 Announce Type: new Abstract: The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execution. As models, APIs, environments, and requirements evolve, the harness must be continually modified. Before such a change can be made, a developer or coding agent must identify all code locations that implement the target behavior. This is difficult because production harnesses are large, tightly coupled, and behaviorally distributed, while modification requests describe what the system should do and repositories are organized by files and modules. Code search, repository indexing, and long-context processing ease inspection, but still leave this behavior-to-code mapping to be recovered by hand. Behavior localization is therefore a central bottleneck in harness…", "url": "https://arxiv.org/abs/2607.13285", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable", "summary": "arXiv:2607.13285v1 Announce Type: new \nAbstract: The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execution. As models, APIs, environments, and requirements evolve, the harness must be continually modified. Before such a change can be made, a developer or coding agent must identify all code locations that implement the target behavior. This is difficult because production harnesses are large, tightly coupled, and behaviorally distributed, while modification requests describe what the system should do and repositories are organized by files and modules. Code search, repository indexing, and long-context processing ease inspection, but still leave this behavior-to-code mapping to be recovered by hand. Behavior localization is therefore a central bottleneck in harness evolution. We introduce the Harness Handbook, a behavior-centric representation synthesized automatically from a harness codebase via static analysis and LLM-assisted structuring, linking each behavior to its corresponding source. We also introduce Behavior-Guided Progressive Disclosure (BGPD), which guides agents from high-level behaviors to relevant implementation details and verifies candidate locations against the current source. On diverse modification requests from two open-source harnesses, Handbook-Assisted planning improves behavior localization and edit-plan quality while using fewer planner tokens, with the largest gains on scattered sites, rarely executed paths, and cross-module interactions. Evolving complex agentic systems thus depends not only on generating edits, but also on determining where those edits should be made.", "url": "https://arxiv.org/abs/2607.13285", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "d1ff94bdf01b891151d04799802cfbcc75f42908", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases", "summary": "arXiv:2607.13292v1 Announce Type: new Abstract: Autoformalization translates informal natural language into formal, machine-verifiable languages. While most work focuses on individual statements, real formalization efforts are inherently theory-level: they require an entire web of axioms, definitions, and lemmas before target theorems can even be stated. In this position paper, we argue for theory-level autoformalization: formalizing complete theories, including all their inter-dependencies, as structured libraries. We examine the significance of this shift, address alternative views, identify open challenges, and propose three promising paths forward. Our survey of autoformalization is available at https://github.com/marcusm117/Awesome-Autoformalization.", "url": "https://arxiv.org/abs/2607.13292", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases", "summary": "arXiv:2607.13292v1 Announce Type: new \nAbstract: Autoformalization translates informal natural language into formal, machine-verifiable languages. While most work focuses on individual statements, real formalization efforts are inherently theory-level: they require an entire web of axioms, definitions, and lemmas before target theorems can even be stated. In this position paper, we argue for theory-level autoformalization: formalizing complete theories, including all their inter-dependencies, as structured libraries. We examine the significance of this shift, address alternative views, identify open challenges, and propose three promising paths forward. Our survey of autoformalization is available at https://github.com/marcusm117/Awesome-Autoformalization.", "url": "https://arxiv.org/abs/2607.13292", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "ebf9376ea1c55726ef7dc87ebbc400160fdea2e6", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "EZSMT Version 3, Matured", "summary": "arXiv:2607.13344v1 Announce Type: new Abstract: Constraint Answer Set Programming (CASP) is a hybrid reasoning paradigm that combines Answer Set Programming (ASP) with Constraint Processing and Satisfiability Modulo Theories (SMT), enabling powerful declarative encodings of complex combinatorial search problems. This paper presents the design and implementation of EZSMTV3, an extensible SMT-based CASP framework that advances the translational approach to CASP solving. Building upon the foundation of the EZSMT+ system, EZSMTV3 introduces a more expressive input language, supports optimization via weak constraints, and offers foundations for streamlined integration of new constraint types. Rather than implementing custom search procedures, EZSMTV3 leverages state-of-the-art SMT solvers, such as CVC5, YICES, and Z3 to perform reasoning. The paper provides benchmarking results comparing EZS…", "url": "https://arxiv.org/abs/2607.13344", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "EZSMT Version 3, Matured", "summary": "arXiv:2607.13344v1 Announce Type: new \nAbstract: Constraint Answer Set Programming (CASP) is a hybrid reasoning paradigm that combines Answer Set Programming (ASP) with Constraint Processing and Satisfiability Modulo Theories (SMT), enabling powerful declarative encodings of complex combinatorial search problems. This paper presents the design and implementation of EZSMTV3, an extensible SMT-based CASP framework that advances the translational approach to CASP solving. Building upon the foundation of the EZSMT+ system, EZSMTV3 introduces a more expressive input language, supports optimization via weak constraints, and offers foundations for streamlined integration of new constraint types. Rather than implementing custom search procedures, EZSMTV3 leverages state-of-the-art SMT solvers, such as CVC5, YICES, and Z3 to perform reasoning. The paper provides benchmarking results comparing EZSMTV3 with its CASP peers such as CLINGCON, CLINGO[DL], and CLINGO[LP], while showcasing its ability to handle mixed-domain constraints involving both integers and reals. The system provides a robust platform for future extensions and theoretical exploration within the CASP domain.", "url": "https://arxiv.org/abs/2607.13344", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "45958cd0595aaa8d2eaaa8035f8e14d8a72e04e1", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "Set-shifting Behavioral Test for Harnessed Agents", "summary": "arXiv:2607.13396v1 Announce Type: new Abstract: What happens to an LLM agent's tool choice when the reliable tool silently changes within an ongoing session? We borrow set-shifting from cognitive psychology to study how well agents adapt to hidden reliability shifts. Our benchmark mounts tool-skill libraries with redundancies, where many tools solve the same task but differ in hidden reliability. In our evaluation framework, a branched schedule shifts the reliable tool group at hidden boundaries and pairs every shift with a no-shift control. We find that agents, by default, settle on a small recurring routine within a few turns of each boundary, with call shares concentrating on a few discrete values after each reliability shift. We score the set-shifting accuracy for each agent trajectory: the joint probability of routing to the target tool group in every post-shift window. We test ope…", "url": "https://arxiv.org/abs/2607.13396", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "Set-shifting Behavioral Test for Harnessed Agents", "summary": "arXiv:2607.13396v1 Announce Type: new \nAbstract: What happens to an LLM agent's tool choice when the reliable tool silently changes within an ongoing session? We borrow set-shifting from cognitive psychology to study how well agents adapt to hidden reliability shifts. Our benchmark mounts tool-skill libraries with redundancies, where many tools solve the same task but differ in hidden reliability. In our evaluation framework, a branched schedule shifts the reliable tool group at hidden boundaries and pairs every shift with a no-shift control. We find that agents, by default, settle on a small recurring routine within a few turns of each boundary, with call shares concentrating on a few discrete values after each reliability shift. We score the set-shifting accuracy for each agent trajectory: the joint probability of routing to the target tool group in every post-shift window. We test open-weight LLMs in an open-source agentic harness and find qualitatively distinct failure modes across the same set of routines. We also find that set framing, how the toolset presents the alternatives as competing or complementary, shifts the routing dynamics.", "url": "https://arxiv.org/abs/2607.13396", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "c0cfc12c6155aeec8cb4157e75b1f6ec3cd923e4", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "LAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning", "summary": "arXiv:2607.13501v1 Announce Type: new Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LAPO, a self-generated process-supervision method based on backward leave-one-turn attribution. For each search turn, LAPO replaces the turn and its retrieval observation with a fixed [DELETE] placeholder and measures the resulting change in the current policy's mean log-likelihood of the gold answer. This Answer-Likelihood Gain estimates the turn's contribution while preserving all downstream interactions, allowing early evidence to be evaluated in the complete reasoning context. LAPO further applies sign-consistency gating, retaining only normalized process advantages whose directions agree with their raw attribution scores. The method requires n…", "url": "https://arxiv.org/abs/2607.13501", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "LAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning", "summary": "arXiv:2607.13501v1 Announce Type: new \nAbstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LAPO, a self-generated process-supervision method based on backward leave-one-turn attribution. For each search turn, LAPO replaces the turn and its retrieval observation with a fixed [DELETE] placeholder and measures the resulting change in the current policy's mean log-likelihood of the gold answer. This Answer-Likelihood Gain estimates the turn's contribution while preserving all downstream interactions, allowing early evidence to be evaluated in the complete reasoning context. LAPO further applies sign-consistency gating, retaining only normalized process advantages whose directions agree with their raw attribution scores. The method requires no additional reward model, teacher, verifier, or LLM-as-a-Judge. Across seven knowledge-intensive question-answering datasets with local retrieval, LAPO achieves an average exact-match score of 0.326, outperforming the strongest step-reward baseline, IGPO, by 0.053. Ablations show complementary benefits from backward attribution and sign-consistency gating, demonstrating that policy-derived retrospective attribution can provide effective process supervision for multi-turn search agents.", "url": "https://arxiv.org/abs/2607.13501", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "c4a2438dc2c94709e5b284e03b4e1c92a2f9c359", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "How Far Can Root Cause Analysis Go on Real-World Telemetry Data?", "summary": "arXiv:2607.13548v1 Announce Type: new Abstract: Identifying root causes in production microservice failures requires reasoning over large-scale, multimodal telemetry spanning metrics, logs, and traces, a problem that has proved resistant to both classical and LLM-based approaches. The OpenRCA dataset exemplifies these challenges: it is large-scale, multimodal, and lacks detailed domain knowledge, and yields consistently low accuracy across all existing methods. We show that classical causal discovery methods and existing LLM-based multi-agent systems fail to reliably identify root causes on this benchmark, and present a Structured Multi-Agent RCA pipeline that substantially outperforms existing LLM-based and classical baselines, supporting both domain-knowledge and knowledge-free operating modes. To diagnose where failures originate, we introduce a reverse reasoning agent that, given th…", "url": "https://arxiv.org/abs/2607.13548", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "How Far Can Root Cause Analysis Go on Real-World Telemetry Data?", "summary": "arXiv:2607.13548v1 Announce Type: new \nAbstract: Identifying root causes in production microservice failures requires reasoning over large-scale, multimodal telemetry spanning metrics, logs, and traces, a problem that has proved resistant to both classical and LLM-based approaches. The OpenRCA dataset exemplifies these challenges: it is large-scale, multimodal, and lacks detailed domain knowledge, and yields consistently low accuracy across all existing methods. We show that classical causal discovery methods and existing LLM-based multi-agent systems fail to reliably identify root causes on this benchmark, and present a Structured Multi-Agent RCA pipeline that substantially outperforms existing LLM-based and classical baselines, supporting both domain-knowledge and knowledge-free operating modes. To diagnose where failures originate, we introduce a reverse reasoning agent that, given the correct answer, identifies which signals in the extracted anomalies support it and determines whether Stage~1 had access to those signals, classifying each failure as Reasoning Gap (evidence present but unused) or Data Ambiguity (evidence genuinely absent). This analysis reveals that the required evidence is present in the vast majority of failures: the bottleneck is not data access but the agent's ability to reason over it correctly. We further introduce an automated rule mining pipeline that systematically extracts discrimination rules from reverse reasoning reports, reducing reliance on manual knowledge curation. Across all configurations, model reasoning capability and domain knowledge are the primary constraints: stronger models embed more domain expertise, and explicit knowledge injection partially compensates for this gap. Reasoning performance remains practically bounded even when evidence extraction is perfect: scaffold engineering and better data pipelines alone cannot close this gap; progress requires improvements at the model level.", "url": "https://arxiv.org/abs/2607.13548", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "6738533e44045c62bcf06f16dd7be6d6238c68ac", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling", "summary": "arXiv:2607.13558v1 Announce Type: new Abstract: Urban region profiling constitutes a core problem in urban computing, supporting applications such as population estimation, economic assessment, and environmental monitoring. Existing methods typically formulate this task as multimodal representation learning, fusing heterogeneous urban data, e.g., satellite imagery, points of interest, textual descriptions, and 3D building information, into latent embeddings for prediction. However, these approaches are largely correlation-driven, assume cross-modal consistency, and rely on static pipelines, which limit their robustness in heterogeneous or unseen urban regions. We propose UrbanAgent, an agentic framework that reframes urban region profiling as a reasoning-driven inference problem. UrbanAgent instantiates an independent agent for each data modality and performs structured multi-agent coll…", "url": "https://arxiv.org/abs/2607.13558", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling", "summary": "arXiv:2607.13558v1 Announce Type: new \nAbstract: Urban region profiling constitutes a core problem in urban computing, supporting applications such as population estimation, economic assessment, and environmental monitoring. Existing methods typically formulate this task as multimodal representation learning, fusing heterogeneous urban data, e.g., satellite imagery, points of interest, textual descriptions, and 3D building information, into latent embeddings for prediction. However, these approaches are largely correlation-driven, assume cross-modal consistency, and rely on static pipelines, which limit their robustness in heterogeneous or unseen urban regions. We propose UrbanAgent, an agentic framework that reframes urban region profiling as a reasoning-driven inference problem. UrbanAgent instantiates an independent agent for each data modality and performs structured multi-agent collaborative reasoning to explicitly address cross-modal inconsistencies rather than absorbing them into a single representation. In addition, UrbanAgent extends indicator prediction as a closed-loop process of active evidence acquisition and iterative reasoning, enabling agents to verify uncertain inferences through tool-augmented retrieval of external knowledge optimized via reinforcement learning. Extensive experiments on global urban datasets for Carbon emissions, GDP, and Population estimation show that UrbanAgent consistently outperforms existing baselines, achieving an average improvement of 8.1% in R2, and exhibiting strong generalization performance in unseen-city settings.", "url": "https://arxiv.org/abs/2607.13558", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } }, { "id": "c1ec6242def3ab0a711405ffeabbb41db62e2b87", "source_id": "arxiv_ai", "source": "arXiv — Artificial Intelligence", "category": "ai", "engine": "rss", "title": "AI advice suppresses people's willingness to say \"I don't know\", even when the advice is wrong and accuracy is incentivized", "summary": "arXiv:2607.13562v1 Announce Type: new Abstract: Knowing when to say \"I don't know\" is fundamental to human judgment, yet AI assistants offer a fluent answer to almost any question. In five experiments (N = 3,132; four preregistered, one direct replication), participants answered difficult questions and could always decline to respond. We engineered the questions so that AI advice was wrong, separating AI use from its accuracy. Merely having access to AI nearly eliminated participants' willingness to suspend judgment, and this held whether the advice was actively requested or simply displayed. Consequently, participants answered more questions but were correct about a third as often as when AI was unavailable-yet their confidence nearly doubled. Incentivizing accuracy and penalizing inaccuracy led participants to seek and follow AI advice less, answer more accurately, and suspend judgmen…", "url": "https://arxiv.org/abs/2607.13562", "image": "", "published": "2026-07-16T04:00:00+00:00", "score": 84.19, "color": "#b09cff", "raw": { "title": "AI advice suppresses people's willingness to say \"I don't know\", even when the advice is wrong and accuracy is incentivized", "summary": "arXiv:2607.13562v1 Announce Type: new \nAbstract: Knowing when to say \"I don't know\" is fundamental to human judgment, yet AI assistants offer a fluent answer to almost any question. In five experiments (N = 3,132; four preregistered, one direct replication), participants answered difficult questions and could always decline to respond. We engineered the questions so that AI advice was wrong, separating AI use from its accuracy. Merely having access to AI nearly eliminated participants' willingness to suspend judgment, and this held whether the advice was actively requested or simply displayed. Consequently, participants answered more questions but were correct about a third as often as when AI was unavailable-yet their confidence nearly doubled. Incentivizing accuracy and penalizing inaccuracy led participants to seek and follow AI advice less, answer more accurately, and suspend judgment more often, though still far less than when AI was unavailable. As AI suggestions grow ubiquitous and unsolicited, they may not simply affect answer accuracy; they may even alter the metacognitive threshold at which people decide whether they know enough to answer.", "url": "https://arxiv.org/abs/2607.13562", "image": "", "published": "Thu, 16 Jul 2026 00:00:00 -0400" } } ], "count": 20, "cached_at": "2026-07-16T09:47:10+00:00" }
Save file
Quick jump
open a path
Open