{"total":31,"rows":[{"id":"2607.14777","title":"SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning","created":"2026-07-16","cited_by_count":32,"area":"agents"},{"id":"2608.25593","title":"JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution","created":"2026-08-26","cited_by_count":16,"area":"agents"},{"id":"2603.22862","title":"The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration","created":"2026-03-24","cited_by_count":14,"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":"2605.24002","title":"Harnessing AtomisticSkills for Agentic Atomistic Research","created":"2026-05-18","cited_by_count":6,"area":"agents"},{"id":"2605.25200","title":"GroupTravelBench: Benchmarking LLM Agents on Multi-Person Travel Planning","created":"2026-05-24","cited_by_count":5,"area":"agents"},{"id":"2606.17698","title":"EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent","created":"2026-06-16","cited_by_count":5,"area":"agents"},{"id":"2605.11225","title":"PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement","created":"2026-05-11","cited_by_count":4,"area":"agents"},{"id":"2608.05013","title":"OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents","created":"2026-08-04","cited_by_count":4,"area":"agents"},{"id":"2605.22643","title":"Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety","created":"2026-05-21","cited_by_count":3,"area":"agents"},{"id":"2606.21169","title":"Trip+: Benchmarking Agents in Personalized Interactive Travel Planning","created":"2026-06-19","cited_by_count":3,"area":"agents"},{"id":"2608.27260","title":"What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents","created":"2026-08-27","cited_by_count":3,"area":"agents"},{"id":"2609.08944","title":"SkillAdam: Stable and Efficient Skill Evolution for Agents","created":"2026-09-08","cited_by_count":3,"area":"agents"},{"id":"2604.07733","title":"CivBench: Progress-Based Evaluation for LLMs' Strategic Decision-Making in Civilization V","created":"2026-04-09","cited_by_count":2,"area":"agents"},{"id":"2606.08340","title":"Benchmarking Open-Ended Multi-Agent Coordination in Language Agents","created":"2026-06-06","cited_by_count":2,"area":"agents"},{"id":"2606.08200","title":"Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents","created":"2026-06-06","cited_by_count":1,"area":"agents"},{"id":"2607.14989","title":"OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios","created":"2026-07-16","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":"2609.02074","title":"CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning","created":"2026-09-02","cited_by_count":1,"area":"agents"},{"id":"2609.23490","title":"BabelArena: A Large-Scale Multilingual Benchmark for LLM Agents","created":"2026-09-20","cited_by_count":1,"area":"agents"},{"id":"2603.23875","title":"Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios","created":"2026-03-25","cited_by_count":0,"area":"agents"},{"id":"2607.23124","title":"AgentOmnia: Scaling Agentic Models for Full-Scenario Applications","created":"2026-07-25","cited_by_count":0,"area":"agents"},{"id":"2608.25039","title":"LifePlanner: Evaluating LLM Agents for Geo-spatial Planning with Social Media Data","created":"2026-08-25","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":"2609.32754","title":"Adaptive Consistency Graph for Long-Horizon Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33920","title":"HyperMCTS: Hypergraph-Augmented MCTS for Long-Horizon LLM Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34710","title":"FromPitch2Board: Benchmarking LLM Agents in Long-Horizon Football Management","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.34930","title":"PDEU-Bench: Benchmarking the Personalized Planning Lifecycle of Tool-Calling LLM Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.04178","title":"SHarP: Saliency-based Pruning of Agent Harnesses","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.11655","title":"Harness Evolution Hits a Ceiling: When Weight Training Should Begin","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.12957","title":"JoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}