{"total":52,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2508.09726","title":"Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning","created":"2025-08-13","cited_by_count":75,"area":"lr"},{"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":"2601.09708","title":"Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning","created":"2026-01-14","cited_by_count":24,"area":"vla"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2510.08457","title":"ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping","created":"2025-10-09","cited_by_count":17,"area":"lr"},{"id":"2510.04474","title":"DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2608.24696","title":"On-policy Distillation with Verifiable Reward","created":"2026-08-25","cited_by_count":15,"area":"distill"},{"id":"2512.21540","title":"Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model","created":"2025-12-25","cited_by_count":13,"area":"lr"},{"id":"2508.10026","title":"SABER: Switchable and Balanced Training for Efficient LLM Reasoning","created":"2025-08-08","cited_by_count":12,"area":"lr"},{"id":"2602.09953","title":"ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning","created":"2026-02-10","cited_by_count":9,"area":"lr"},{"id":"2512.19995","title":"Schoenfeld's Anatomy of Mathematical Reasoning by Language Models","created":"2025-12-23","cited_by_count":8,"area":"lr"},{"id":"2601.11340","title":"Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2510.27042","title":"e1: Learning Adaptive Control of Reasoning Effort","created":"2025-10-30","cited_by_count":6,"area":"lr"},{"id":"2606.18089","title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","created":"2026-06-16","cited_by_count":5,"area":"lr"},{"id":"2602.05539","title":"Steering Large Reasoning Models towards Concise Reasoning via Flow Matching","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2602.09591","title":"On the Optimal Reasoning Length for RL-Trained Language Models","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2605.05365","title":"ZAYA1-8B Technical Report","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2606.03077","title":"Libra: Efficient Resource Management for Agentic RL Post-Training","created":"2026-06-02","cited_by_count":4,"area":"agents"},{"id":"2608.13505","title":"Intern-S2-Preview: Scientific Agentic Foundation Model","created":"2026-08-13","cited_by_count":4,"area":"agents"},{"id":"2510.03259","title":"Verifying Meta-Awareness via Predictive Rewards in Reasoning Models","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2510.10168","title":"Concise Reasoning in the Lens of Lagrangian Optimization","created":"2025-10-11","cited_by_count":3,"area":"lr"},{"id":"2510.23486","title":"Learning to Reason Efficiently with Discounted Reinforcement Learning","created":"2025-10-27","cited_by_count":3,"area":"lr"},{"id":"2602.10004","title":"ESTAR: Early-Stopping Token-Aware Reasoning For Efficient Inference","created":"2026-02-10","cited_by_count":3,"area":"lr"},{"id":"2603.00296","title":"Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning","created":"2026-02-27","cited_by_count":3,"area":"lr"},{"id":"2603.08659","title":"CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning","created":"2026-03-09","cited_by_count":3,"area":"lr"},{"id":"2605.08441","title":"DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2606.22716","title":"Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards","created":"2026-06-21","cited_by_count":3,"area":"lr"},{"id":"2511.09158","title":"Efficient Reasoning via Reward Model","created":"2025-11-12","cited_by_count":2,"area":"lr"},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2608.26070","title":"Prefix Sliding for efficient test-time scaling","created":"2026-08-26","cited_by_count":2,"area":"lr"},{"id":"2602.01198","title":"A State-Transition Framework for Efficient LLM Reasoning","created":"2026-02-01","cited_by_count":1,"area":"lr"},{"id":"2602.04265","title":"Boosting LLM Reasoning via Human-Inspired Reward Shaping","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2607.09786","title":"Length Penalties Make Chain-of-Thought Less Monitorable","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2608.02876","title":"BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2510.05943","title":"EARL: Efficient Agentic Reinforcement Learning Systems for Large Language Models","created":"2025-10-07","cited_by_count":0,"area":"agents"},{"id":"2601.08010","title":"CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation","created":"2026-01-12","cited_by_count":0,"area":"lr"},{"id":"2602.00760","title":"APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2604.02322","title":"Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2604.27039","title":"Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.09806","title":"LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.22211","title":"CLORE: Content-Level Optimization for Reasoning Efficiency","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2606.20295","title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.01849","title":"Decomposer: Learning to Decompile Symbolic Music to Programs","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.21793","title":"QLPO: Quadrant-weighted Sampling for Length-aware Policy Optimization","created":"2026-07-23","cited_by_count":0,"area":"lr"},{"id":"2608.17414","title":"REChart: Reasoning-Efficient Chart Editing with Large Reasoning Models","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2608.26141","title":"AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2609.20846","title":"Rewarding Efficient Reasoning Improves Abstention on Underspecified Tasks in Reasoning Models","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2609.29664","title":"To Think or Not to Think: Allocating Reasoning Where It Helps","created":"2026-08-30","cited_by_count":0,"area":"lr"},{"id":"2609.34718","title":"Quality Determines Direction, Length Shapes Magnitude: Length Control for Open-Ended Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.38854","title":"Mitigating the Length-Scaling Tax with Online Distillation","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}