{"total":15,"rows":[{"id":"2602.13035","title":"Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL","created":"2026-02-13","cited_by_count":27,"area":null},{"id":"2507.03041","title":"Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards","created":"2025-07-03","cited_by_count":24,"area":null},{"id":"2506.08375","title":"EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2506.23127","title":"Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning","created":"2025-06-29","cited_by_count":9,"area":null},{"id":"2607.11172","title":"STAMP: Provenance-Guided Credit Assignment for Deep Search Agents","created":"2026-07-13","cited_by_count":5,"area":null},{"id":"2606.00547","title":"Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents","created":"2026-05-30","cited_by_count":4,"area":null},{"id":"2604.11611","title":"Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2608.17499","title":"Towards Better Agents for Multi-Turn User Interaction: The Next User Turn Is More Than Context","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2608.29519","title":"FuncRoom-Agent: Sequential Feed-Forward 3D Functional Indoor Scene Generation","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2507.14200","title":"A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2605.11235","title":"Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.17149","title":"A Diagnostic Framework for AI Agent Behavior","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2609.39909","title":"DoGBench: Can Agents Meet Expert Standards for User-Facing Documentation?","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.09560","title":"World Potential Model: Pretrained World Knowledge as Progress Potentials","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.17666","title":"DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}