{"total":23,"rows":[{"id":"2602.16699","title":"Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents","created":"2026-02-18","cited_by_count":17,"area":"agents"},{"id":"2601.14192","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","created":"2026-01-20","cited_by_count":16,"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":"2606.22388","title":"PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems","created":"2026-06-21","cited_by_count":11,"area":"agents"},{"id":"2606.05622","title":"AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints","created":"2026-06-04","cited_by_count":7,"area":"agents"},{"id":"2607.27083","title":"Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents","created":"2026-07-29","cited_by_count":4,"area":"agents"},{"id":"2608.02670","title":"Permission Denied: Policy-Graded Evaluation of Coding Agents in Hardened Environments","created":"2026-08-02","cited_by_count":3,"area":"agents"},{"id":"2608.10875","title":"VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?","created":"2026-08-11","cited_by_count":3,"area":"agents"},{"id":"2603.03202","title":"Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?","created":"2026-03-03","cited_by_count":2,"area":"agents"},{"id":"2608.24509","title":"PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2605.18854","title":"Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific Discovery","created":"2026-05-13","cited_by_count":1,"area":"agents"},{"id":"2608.01347","title":"Prompt-Induced Waste in Coding Agents: Reasoning, Effort, Harness Design, and End-to-End Cost","created":"2026-08-02","cited_by_count":1,"area":"agents"},{"id":"2608.05519","title":"EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2608.10299","title":"Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2603.01209","title":"Agents Learn Their Runtime: Interpreter Persistence as Training-Time Semantics","created":"2026-03-01","cited_by_count":0,"area":"agents"},{"id":"2605.18597","title":"Latent Action Reparameterization for Efficient Agent Inference","created":"2026-05-18","cited_by_count":0,"area":"agents"},{"id":"2607.10286","title":"Can Agentic Trading Systems Pay for Their Own Intelligence?","created":"2026-07-11","cited_by_count":0,"area":"agents"},{"id":"2607.13396","title":"Set-shifting Behavioral Test for Harnessed Agents","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2608.16370","title":"What Does Context Compression Cost an Agent? Interaction Costs Unrevealed by Task-Completion Metrics","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2609.30662","title":"LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.33980","title":"DynGraphAgentBench: A Benchmark for Agentic Lifecycle Control in Dynamic Graph Anomaly Detection","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.37453","title":"Commitment Hierarchies under Intent Revision: A Belief-Revision Account of Salvage in Tool-Use Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.19589","title":"JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}