{"total":17,"rows":[{"id":"2506.21605","title":"MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents","created":"2025-06-20","cited_by_count":84,"area":"agents"},{"id":"2602.16313","title":"MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks","created":"2026-02-18","cited_by_count":84,"area":"agents"},{"id":"2603.01045","title":"Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems","created":"2026-03-01","cited_by_count":20,"area":"agents"},{"id":"2504.05370","title":"EduPlanner: LLM-Based Multi-Agent Systems for Customized and Intelligent Instructional Design","created":"2025-04-07","cited_by_count":18,"area":"agents"},{"id":"2410.20666","title":"Guide-LLM: An Embodied LLM Agent and Text-Based Topological Map for Robotic Guidance of People with Visual Impairments","created":"2024-10-28","cited_by_count":10,"area":"agents"},{"id":"2601.20730","title":"AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts","created":"2026-01-28","cited_by_count":9,"area":"agents"},{"id":"2506.12666","title":"LIFELONG SOTOPIA: Evaluating Social Intelligence of Language Agents Over Lifelong Social Interactions","created":"2025-06-14","cited_by_count":8,"area":"agents"},{"id":"2605.17641","title":"Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents","created":"2026-05-17","cited_by_count":6,"area":"agents"},{"id":"2505.23662","title":"ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactions","created":"2025-05-29","cited_by_count":5,"area":"agents"},{"id":"2510.07414","title":"Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation","created":"2025-10-08","cited_by_count":4,"area":"agents"},{"id":"2608.05141","title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2512.18080","title":"From Prompt to Product: A Human-Centered Benchmark of Agentic App Generation Systems","created":"2025-12-19","cited_by_count":1,"area":"agents"},{"id":"2603.14597","title":"D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing","created":"2026-03-15","cited_by_count":1,"area":"agents"},{"id":"2603.25770","title":"ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation","created":"2026-03-26","cited_by_count":1,"area":"agents"},{"id":"2601.20276","title":"Beyond the Needle's Illusion: Decoupled Evaluation of Evidence Access and Use under Semantic Interference at 326M-Token Scale","created":"2026-01-28","cited_by_count":0,"area":"agents"},{"id":"2606.17041","title":"MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2609.14976","title":"MemRiskBench: Trace-Aware Risk-Preserving Evaluation for Long-Horizon LLM Agents","created":"2026-09-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}