arXiv AI
Jul 28
LU-500: A Logo Benchmark for Concept Unlearning
arXiv:2607. 24101v1 Announce Type: cross Abstract: Concept unlearning is increasingly used to limit the reproduction of protected or unsafe visual concepts in text-to-image models.
AI agents
Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv AI
Jul 28
Multi-agent DRL-based Lane Change Decision Model for Cooperative Platooning in Mixed Traffic
arXiv:2601. 11809v2 Announce Type: replace Abstract: Connected automated vehicles (CAVs) possess the ability to communicate and coordinate with one another, enabling cooperative platooning that enhances both energy efficiency and traffic flow.
arXiv Machine Learning
Jul 28
Constrained Reinforcement Learning Using Successor Representations
arXiv:2607. 24057v1 Announce Type: new Abstract: Real-world Reinforcement Learning depends on the ability to formulate safety constraints into a policy.
arXiv AI
Jul 28
PD$^3$: A Project Duplication Detection Framework via Adapted Multi-Agent Debate
arXiv:2505. 17492v2 Announce Type: replace Abstract: Project duplication detection is critical for project quality assessment because it helps avoid investment in repeated proposals.
arXiv AI
Jul 28
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
arXiv:2607. 24743v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundamentally a vision-centric challenge: models must absorb knowledge from heterogeneous 2D and 3D medical images, and evaluation protocols must align with radiologists' clinical practice and provide an accurate, fine-grained and factualness-driven assessment.
arXiv AI
Jul 28
Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigation
arXiv:2607. 24006v1 Announce Type: cross Abstract: Cloud telemetry arrives at a scale that, paradoxically, makes intrusion understanding harder rather than easier.
arXiv AI
Jul 28
E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios
arXiv:2607. 23722v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as agents that interact with stateful environments over multiple steps: gathering hidden information, composing tool calls, and committing state changes.
arXiv AI
Jul 28
Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents
arXiv:2607. 24625v1 Announce Type: cross Abstract: Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors.
arXiv AI
Jul 28
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair
arXiv:2607. 24604v1 Announce Type: cross Abstract: Generate--test--revise loops are common in coding agents, but repetition alone provides no reliability guarantee.
arXiv AI
Jul 28
CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding
arXiv:2607. 24582v1 Announce Type: cross Abstract: Long-video understanding increasingly relies on large vision-language models and tool-augmented reasoning, but most systems apply the same inference procedure to every example regardless of difficulty.
arXiv AI
Jul 28
TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning
arXiv:2509. 06278v4 Announce Type: replace Abstract: Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations.
arXiv AI
Jul 28
Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls
arXiv:2607. 24343v1 Announce Type: cross Abstract: Language-model agents act through structured tool calls whose arguments carry different risks.
arXiv AI
Jul 28
DeepFaith: Evidence-Grounded LLMs for Faithful Incident Reporting in Multi-Stage APT Defense
arXiv:2607. 24348v1 Announce Type: cross Abstract: Advanced Persistent Threats (APTs) are difficult to detect and interpret due to their multi-stage and stealthy nature.
arXiv AI
Jul 28
Test-Time Coverage: Test-Conditioned Data Curation for Deployment-Aware Learning
arXiv:2607. 22697v1 Announce Type: new Abstract: Deployed AI systems are often trained from broad candidate data pools, necessitating data curation towards the deployment test distribution.
arXiv AI
Jul 28
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
arXiv:2607. 23802v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has driven recent progress in reasoning-oriented large language models (LLMs) by enabling large-scale optimization.
arXiv AI
Jul 28
Hybrid Advantage Estimation with Unified Critic for VLM Agentic Reinforcement Learning
arXiv:2607. 23605v1 Announce Type: new Abstract: Large Vision-Language Models (VLMs) now act as agents in interactive environments, where success requires coherent reasoning and decision-making across turns.
arXiv AI
Jul 28
MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal UAV Agents
arXiv:2607. 23870v1 Announce Type: cross Abstract: Smart-city airspace is transforming Uncrewed Aerial Vehicles (UAVs) from passive sensing platforms into cyber-physical decision makers that must follow operational rules under degraded observations and ambiguous language.
arXiv AI
Jul 28
Where Is the Cost of Third-Party API Routers in Agentic Software Development?
arXiv:2607. 23624v1 Announce Type: cross Abstract: Third-party API routers have become a common layer that unifies access across increasingly diverse LLM providers.
arXiv AI
Jul 28
OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows
arXiv:2510. 24411v3 Announce Type: replace Abstract: Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms.
arXiv AI
Jul 28
Coherent Without Grounding, Grounded Without Success: Observability and Epistemic Failure
arXiv:2603. 28371v2 Announce Type: replace-cross Abstract: When an agent can articulate why something works, we typically take this as evidence of genuine understanding.