{"total":19,"rows":[{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302,"area":"agents"},{"id":"2405.17935","title":"Tool Learning with Large Language Models: A Survey","created":"2024-05-28","cited_by_count":223,"area":"agents"},{"id":"2601.06112","title":"ReliabilityBench: Evaluating LLM Agent Reliability Under Production-Like Stress Conditions","created":"2026-01-03","cited_by_count":36,"area":"agents"},{"id":"2408.00523","title":"Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models","created":"2024-08-01","cited_by_count":27,"area":"agents"},{"id":"2504.13192","title":"CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent","created":"2025-04-13","cited_by_count":25,"area":"agents"},{"id":"2507.14799","title":"Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree","created":"2025-07-20","cited_by_count":14,"area":"agents"},{"id":"2503.23804","title":"DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents","created":"2025-03-31","cited_by_count":12,"area":"agents"},{"id":"2409.11690","title":"ID-Free Not Risk-Free: LLM-Powered Agents Unveil Risks in ID-Free Recommender Systems","created":"2024-09-18","cited_by_count":10,"area":"agents"},{"id":"2412.10807","title":"Towards Action Hijacking of Large Language Model-based Agent","created":"2024-12-14","cited_by_count":4,"area":"agents"},{"id":"2507.18607","title":"Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents","created":"2025-07-24","cited_by_count":4,"area":"agents"},{"id":"2601.18105","title":"Mitigating the OWASP Top 10 For Large Language Models Applications using Intelligent Agents","created":"2026-01-26","cited_by_count":3,"area":"agents"},{"id":"2604.26274","title":"Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents","created":"2026-04-29","cited_by_count":3,"area":"agents"},{"id":"2504.03185","title":"Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents","created":"2025-04-04","cited_by_count":2,"area":"agents"},{"id":"2403.17860","title":"Illuminating Blind Spots of Language Models with Targeted Agent-in-the-Loop Synthetic Data","created":"2024-03-26","cited_by_count":1,"area":"agents"},{"id":"2604.23483","title":"Agentic Adversarial Rewriting Exposes Architectural Vulnerabilities in Black-Box NLP Pipelines","created":"2026-04-26","cited_by_count":0,"area":"agents"},{"id":"2606.07316","title":"Certifiable Semantic Agreement Among LLM Agents: What the Admissibility Instrument Decides","created":"2026-06-05","cited_by_count":0,"area":"agents"},{"id":"2607.19794","title":"TriAgent: Divergence-Aware Multi-Agent Committees for Cost-Efficient Financial Sentiment Analysis","created":"2026-07-22","cited_by_count":0,"area":"agents"},{"id":"2608.03970","title":"Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input Perturbations","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2609.38270","title":"VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"}],"next_cursor":null}