{"total":19,"rows":[{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2510.19363","title":"LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts","created":"2025-10-22","cited_by_count":29,"area":"lr"},{"id":"2602.10560","title":"When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning","created":"2026-02-11","cited_by_count":9,"area":"lr"},{"id":"2604.15148","title":"IG-Search: Step-Level Information Gain Rewards for Search-Augmented Reasoning","created":"2026-04-16","cited_by_count":9,"area":"lr"},{"id":"2605.22511","title":"Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning","created":"2026-05-21","cited_by_count":9,"area":"lr"},{"id":"2510.13272","title":"Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation","created":"2025-10-15","cited_by_count":6,"area":"lr"},{"id":"2602.00845","title":"Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward","created":"2026-01-31","cited_by_count":6,"area":"lr"},{"id":"2507.22716","title":"From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs","created":"2025-07-30","cited_by_count":5,"area":"lr"},{"id":"2604.17265","title":"MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search","created":"2026-04-19","cited_by_count":5,"area":"lr"},{"id":"2602.11551","title":"SIGHT: Reinforcement Learning with Self-Evidence and Information-Gain Diverse Branching for Search Agent","created":"2026-02-12","cited_by_count":3,"area":"lr"},{"id":"2606.15532","title":"EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management","created":"2026-06-14","cited_by_count":3,"area":"lr"},{"id":"2607.12267","title":"Track, Rank, Crack: Epistemic Working Memory Scales Multi-Hop Reasoning in Language Agents","created":"2026-07-14","cited_by_count":2,"area":"lr"},{"id":"2510.20691","title":"Plan Then Retrieve: Reinforcement Learning-Guided Complex Reasoning over Knowledge Graphs","created":"2025-10-23","cited_by_count":1,"area":"lr"},{"id":"2602.05818","title":"TKG-Thinker: Towards Dynamic Reasoning over Temporal Knowledge Graphs via Agentic Reinforcement Learning","created":"2026-02-05","cited_by_count":1,"area":"lr"},{"id":"2511.09109","title":"Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning","created":"2025-11-12","cited_by_count":0,"area":"lr"},{"id":"2511.18715","title":"HuggingR$^{4}$: A Progressive Reasoning Framework for Discovering Optimal Model Companions","created":"2025-11-24","cited_by_count":0,"area":"lr"},{"id":"2512.20458","title":"Laser: Governing Long-Horizon Agentic Search via Structured Protocol and Context Register","created":"2025-12-23","cited_by_count":0,"area":"lr"},{"id":"2605.13534","title":"Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2606.28566","title":"R$^2$-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search","created":"2026-06-26","cited_by_count":0,"area":"lr"}],"next_cursor":null}