{"total":19,"rows":[{"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":"2606.18829","title":"GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents","created":"2026-06-17","cited_by_count":13,"area":"agents"},{"id":"2606.20683","title":"From Question Answering to Task Completion: A Survey on Agent System and Harness Design","created":"2026-06-14","cited_by_count":12,"area":"agents"},{"id":"2607.12385","title":"PM-Bench: Evaluating Prospective Memory in LLM Agents","created":"2026-07-14","cited_by_count":7,"area":"agents"},{"id":"2607.27834","title":"MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory","created":"2026-07-30","cited_by_count":7,"area":"agents"},{"id":"2605.14678","title":"$\\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2604.10352","title":"ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2606.17328","title":"MemTrace: Probing What Final Accuracy Misses in Long-Term Memory","created":"2026-06-15","cited_by_count":4,"area":"agents"},{"id":"2607.21962","title":"Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings","created":"2026-07-24","cited_by_count":3,"area":"agents"},{"id":"2608.02113","title":"MemArbiter: Decision-Time Memory Arbitration for Long-Horizon LLM Agents","created":"2026-08-03","cited_by_count":3,"area":"agents"},{"id":"2605.06365","title":"From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work","created":"2026-05-07","cited_by_count":2,"area":"agents"},{"id":"2608.19564","title":"Remember, Verify, or Ask? Cross-Family Evaluation of Memory Commitment in LLM Agents","created":"2026-08-20","cited_by_count":2,"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":"2608.30478","title":"Agents in the Large: Perception-Centered Architecture for Persistent Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.24259","title":"MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents","created":"2026-09-21","cited_by_count":1,"area":"agents"},{"id":"2607.16848","title":"Beyond Memory Leaderboards: Evaluating Scientific Memory as Budgeted Context Restoration","created":"2026-07-18","cited_by_count":0,"area":"agents"},{"id":"2608.10042","title":"UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.20729","title":"Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2609.32658","title":"Contract Memory Compiler: Resolve, Then Traverse","created":"2026-09-26","cited_by_count":0,"area":"agents"}],"next_cursor":null}