{"total":24,"rows":[{"id":"2306.13304","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","created":"2023-06-23","cited_by_count":274,"area":"agents"},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212,"area":"agents"},{"id":"2509.18970","title":"LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions","created":"2025-09-23","cited_by_count":50,"area":"agents"},{"id":"2402.10196","title":"A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents","created":"2024-02-15","cited_by_count":22,"area":"agents"},{"id":"2410.12409","title":"Revealing the Barriers of Language Agents in Planning","created":"2024-10-16","cited_by_count":20,"area":"agents"},{"id":"2505.11368","title":"GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents","created":"2025-05-16","cited_by_count":14,"area":"agents"},{"id":"2411.07228","title":"ChemToolAgent: The Impact of Tools on Language Agents for Chemistry Problem Solving","created":"2024-11-11","cited_by_count":11,"area":"agents"},{"id":"2604.04202","title":"ClawArena: Benchmarking AI Agents in Evolving Information Environments","created":"2026-04-05","cited_by_count":11,"area":"agents"},{"id":"2601.09760","title":"Investigating Tool-Memory Conflicts in Tool-Augmented LLMs","created":"2026-01-14","cited_by_count":6,"area":"agents"},{"id":"2604.18874","title":"How Adversarial Environments Mislead Agentic AI?","created":"2026-04-20","cited_by_count":5,"area":"agents"},{"id":"2606.21409","title":"Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents","created":"2026-06-19","cited_by_count":3,"area":"agents"},{"id":"2606.29279","title":"Manufactured Confidence: How Memory Consolidation Turns Hearsay into Confident Facts","created":"2026-06-28","cited_by_count":3,"area":"agents"},{"id":"2608.25553","title":"When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory","created":"2026-08-26","cited_by_count":3,"area":"agents"},{"id":"2605.07830","title":"CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2608.10676","title":"Self-Correcting Long-Horizon Search Agents via Tree-Structured Memory","created":"2026-08-11","cited_by_count":1,"area":"agents"},{"id":"2608.13921","title":"When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict","created":"2026-08-14","cited_by_count":1,"area":"agents"},{"id":"2608.26295","title":"MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Models","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2609.03588","title":"KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2609.05587","title":"Agents Trust Tools Too Much: Measuring Reliance on Unreliable Tools","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2605.29224","title":"Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents","created":"2026-05-28","cited_by_count":0,"area":"agents"},{"id":"2609.28854","title":"Persuaded, Not Informed: Incentive-Misaligned Witnesses Defeat In-Context Grounding","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.36855","title":"When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.38866","title":"When Context Changes: Understanding Update Failures in LLMs","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.01618","title":"Agents Are Systems, Not Models: Rethinking Agentic Evaluation","created":"2026-10-01","cited_by_count":0,"area":"agents"}],"next_cursor":null}