{"total":19,"rows":[{"id":"2510.14545","title":"Agentic Entropy-Balanced Policy Optimization","created":"2025-10-16","cited_by_count":40,"area":"agents"},{"id":"2603.01050","title":"MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline","created":"2026-03-01","cited_by_count":20,"area":"agents"},{"id":"2606.28733","title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","created":"2026-06-27","cited_by_count":15,"area":"agents"},{"id":"2601.04888","title":"SmartSearch: Process Reward-Guided Query Refinement for Search Agents","created":"2026-01-08","cited_by_count":14,"area":"agents"},{"id":"2601.11888","title":"Agentic-R: Learning to Retrieve for Agentic Search","created":"2026-01-17","cited_by_count":11,"area":"agents"},{"id":"2510.00568","title":"ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards","created":"2025-10-01","cited_by_count":10,"area":"agents"},{"id":"2605.29307","title":"GrepSeek: Training Search Agents for Direct Corpus Interaction","created":"2026-05-28","cited_by_count":10,"area":"agents"},{"id":"2602.07035","title":"DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents","created":"2026-02-03","cited_by_count":8,"area":"agents"},{"id":"2505.12065","title":"Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents","created":"2025-05-17","cited_by_count":5,"area":"agents"},{"id":"2510.04695","title":"Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents","created":"2025-10-06","cited_by_count":4,"area":"agents"},{"id":"2606.12384","title":"APPO: Agentic Procedural Policy Optimization","created":"2026-06-10","cited_by_count":4,"area":"agents"},{"id":"2601.11037","title":"BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search","created":"2026-01-16","cited_by_count":3,"area":"agents"},{"id":"2605.24486","title":"AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning","created":"2026-05-23","cited_by_count":3,"area":"agents"},{"id":"2605.30838","title":"COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search Agents","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2606.01830","title":"CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged Feedback","created":"2026-06-01","cited_by_count":0,"area":"agents"},{"id":"2608.17282","title":"DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation","created":"2026-08-18","cited_by_count":0,"area":"agents"},{"id":"2609.06702","title":"PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents","created":"2026-09-06","cited_by_count":0,"area":"agents"},{"id":"2609.35760","title":"TokenCast: Forecasting Token Consumption During LLM Agent Execution","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.38807","title":"PatchHolmes: Agentic Patch Retrieval via Listwise Selection","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}