{"total":21,"rows":[{"id":"2407.08713","title":"GTA: A Benchmark for General Tool Agents","created":"2024-07-11","cited_by_count":77,"area":"agents"},{"id":"2412.18174","title":"INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent","created":"2024-12-24","cited_by_count":64,"area":"agents"},{"id":"2502.13897","title":"DataSciBench: An LLM Agent Benchmark for Data Science","created":"2025-02-19","cited_by_count":57,"area":"agents"},{"id":"2405.08944","title":"Challenges in Deploying Long-Context Transformers: A Theoretical Peak Performance Analysis","created":"2024-05-14","cited_by_count":44,"area":"agents"},{"id":"2407.20242","title":"BadRobot: Jailbreaking Embodied LLM Agents in the Physical World","created":"2024-07-16","cited_by_count":43,"area":"agents"},{"id":"2405.20267","title":"Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions","created":"2024-05-30","cited_by_count":42,"area":"agents"},{"id":"2508.21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers","created":"2025-08-28","cited_by_count":37,"area":"agents"},{"id":"2408.15971","title":"BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems","created":"2024-08-28","cited_by_count":26,"area":"agents"},{"id":"2505.24671","title":"Multiple LLM Agents Debate for Equitable Cultural Alignment","created":"2025-05-30","cited_by_count":21,"area":"agents"},{"id":"2408.15299","title":"TourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineering","created":"2024-08-27","cited_by_count":9,"area":"agents"},{"id":"2412.17061","title":"Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration","created":"2024-12-22","cited_by_count":9,"area":"agents"},{"id":"2411.02457","title":"A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles","created":"2024-11-04","cited_by_count":6,"area":"agents"},{"id":"2412.13549","title":"EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents","created":"2024-12-18","cited_by_count":6,"area":"agents"},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2605.12991","title":"Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy","created":"2026-05-13","cited_by_count":3,"area":"agents"},{"id":"2606.16364","title":"Looking Is Not Picking: An Attention-Segment Account of Tool-Selection Failures in LLM Agents","created":"2026-06-15","cited_by_count":3,"area":"agents"},{"id":"2411.19547","title":"Training Agents with Weakly Supervised Feedback from Large Language Models","created":"2024-11-29","cited_by_count":1,"area":"agents"},{"id":"2507.23633","title":"MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided Querying","created":"2025-07-31","cited_by_count":1,"area":"agents"},{"id":"2602.21265","title":"ToolMATH: A Diagnostic Benchmark for Long-Horizon Tool Use under Systematic Tool-Catalog Constraints","created":"2026-02-24","cited_by_count":1,"area":"agents"},{"id":"2603.13017","title":"Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation","created":"2026-03-13","cited_by_count":0,"area":"agents"},{"id":"2603.18788","title":"Mi:dm K 2.5 Pro","created":"2026-03-19","cited_by_count":0,"area":"agents"}],"next_cursor":null}