{"total":15,"rows":[{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219,"area":null},{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2510.03999","title":"LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions","created":"2025-10-05","cited_by_count":7,"area":null},{"id":"2608.03764","title":"GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2507.15501","title":"ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2608.11242","title":"Lost in Context Compaction: When LLM Systems Drop Side Constraints","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2608.27391","title":"CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.08015","title":"From Version Conflicts to Decision Conflicts: Selective Revalidation for Long-Running AI Agents","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2411.08449","title":"Towards Evaluating Large Language Models for Graph Query Generation","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2604.10557","title":"LLMs Should Incorporate Explicit Mechanisms for Human Empathy","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2606.13715","title":"WorkBench Revisited: Workplace Agents Two Years On","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2609.02095","title":"READY or Not: Reliable Enterprise Agent Deployment","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.37953","title":"Topological Coherence for Self-evolving Multi-agent Systems","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02627","title":"Lost in the Request: How Communication Variation Disrupts Retrieval and Action in Email Agents","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}