{"total":32,"rows":[{"id":"2606.04990","title":"From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents","created":"2026-06-03","cited_by_count":37,"area":"agents"},{"id":"2608.01918","title":"HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses","created":"2026-08-03","cited_by_count":17,"area":"agents"},{"id":"2604.13630","title":"SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment","created":"2026-04-15","cited_by_count":15,"area":"agents"},{"id":"2512.06914","title":"SoK: Trust-Authorization Mismatch in LLM Agent Interactions","created":"2025-12-07","cited_by_count":11,"area":"agents"},{"id":"2510.24358","title":"Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation","created":"2025-10-28","cited_by_count":9,"area":"agents"},{"id":"2601.22984","title":"Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory","created":"2026-01-30","cited_by_count":5,"area":"agents"},{"id":"2603.17621","title":"Complementary RL: Towards Efficient Experience-Driven Agent Learning","created":"2026-03-18","cited_by_count":5,"area":"agents"},{"id":"2608.02464","title":"Real-Time Detection and Repair of LLM Agent Failures","created":"2026-08-03","cited_by_count":5,"area":"agents"},{"id":"2510.22967","title":"MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs","created":"2025-10-27","cited_by_count":4,"area":"agents"},{"id":"2602.05327","title":"ProAct: Agentic Lookahead in Interactive Environments","created":"2026-02-05","cited_by_count":3,"area":"agents"},{"id":"2603.22567","title":"TrustTrade: Human-Inspired Selective Consensus Reduces Decision Uncertainty in LLM Trading Agents","created":"2026-03-23","cited_by_count":3,"area":"agents"},{"id":"2604.12461","title":"CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems","created":"2026-04-14","cited_by_count":3,"area":"agents"},{"id":"2605.08647","title":"AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators","created":"2026-05-09","cited_by_count":3,"area":"agents"},{"id":"2512.06659","title":"The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines","created":"2025-12-07","cited_by_count":2,"area":"agents"},{"id":"2604.07624","title":"Program Analysis Guided LLM Agent for Proof-of-Concept Generation","created":"2026-04-08","cited_by_count":2,"area":"agents"},{"id":"2606.21666","title":"Hallucination as Context Drift: Synchronization Protocols for Multi-Agent LLM Systems","created":"2026-06-19","cited_by_count":2,"area":"agents"},{"id":"2608.06701","title":"Online Monitoring and Corrective Steering of Programming Agents","created":"2026-08-07","cited_by_count":2,"area":"agents"},{"id":"2601.17344","title":"The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents","created":"2026-01-24","cited_by_count":1,"area":"agents"},{"id":"2602.12083","title":"Differentiable Modal Logic for Multi-Agent Diagnosis, Orchestration and Communication","created":"2026-02-12","cited_by_count":1,"area":"agents"},{"id":"2604.25345","title":"Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows","created":"2026-04-28","cited_by_count":1,"area":"agents"},{"id":"2605.17348","title":"Taming \"Zombie'' Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolution","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"id":"2606.06523","title":"Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2606.30555","title":"Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing","created":"2026-06-29","cited_by_count":1,"area":"agents"},{"id":"2606.31522","title":"FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2607.15079","title":"BrainPilot: Automating Brain Discovery with Agentic Research","created":"2026-07-16","cited_by_count":1,"area":"agents"},{"id":"2511.00802","title":"GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents","created":"2025-11-02","cited_by_count":0,"area":"agents"},{"id":"2603.03881","title":"On the Suitability of LLM-Driven Agents for Dark Pattern Audits","created":"2026-03-04","cited_by_count":0,"area":"agents"},{"id":"2607.03628","title":"Swarm-Driven Multi-Agent Reasoning for Smart City Security","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2607.07433","title":"Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks via Universal and Transferable Adversarial HalluSquatting","created":"2026-07-08","cited_by_count":0,"area":"agents"},{"id":"2607.16249","title":"An Agentic Interface for End-to-End Probabilistic Seismic Hazard and Risk Analysis","created":"2026-06-27","cited_by_count":0,"area":"agents"},{"id":"2607.18147","title":"LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2609.09754","title":"LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents","created":"2026-09-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}