Let LLMs Break Free from Overthinking via Self-Braking Tuning
Paper
•
2505.14604
•
Published
•
23
PotentialApplication
-
-
AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
Paper • 2505.16944 • Published • 8 -
Training Step-Level Reasoning Verifiers with Formal Verification Tools
Paper • 2505.15960 • Published • 7 -
The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
Paper • 2505.15134 • Published • 6 -
Reward Reasoning Model
Paper • 2505.14674 • Published • 35 -
General-Reasoner: Advancing LLM Reasoning Across All Domains
Paper • 2505.14652 • Published • 22 -
Fine-tuning Quantized Neural Networks with Zeroth-order Optimization
Paper • 2505.13430 • Published • 10 -
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
Paper • 2505.14681 • Published • 9 -
The Hallucination Tax of Reinforcement Finetuning
Paper • 2505.13988 • Published • 8 -
TabSTAR: A Foundation Tabular Model With Semantically Target-Aware Representations
Paper • 2505.18125 • Published • 111 -
QwenLong-CPRS: Towards infty-LLMs with Dynamic Context Optimization
Paper • 2505.18092 • Published • 43 -
Synthetic Data RL: Task Definition Is All You Need
Paper • 2505.17063 • Published • 10 -
NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning
Paper • 2505.16022 • Published • 3 -
ARM: Adaptive Reasoning Model
Paper • 2505.20258 • Published • 43 -
Learning to Reason without External Rewards
Paper • 2505.19590 • Published • 29 -
Interleaved Reasoning for Large Language Models via Reinforcement Learning
Paper • 2505.19640 • Published • 13 -
Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective
Paper • 2505.17652 • Published • 6 -
UFT: Unifying Supervised and Reinforcement Fine-Tuning
Paper • 2505.16984 • Published • 3 -
Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs
Paper • 2505.19075 • Published • 21 -
Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Credit Assignment
Paper • 2505.11821 • Published • 13 -
Text2Grad: Reinforcement Learning from Natural Language Feedback
Paper • 2505.22338 • Published • 7 -
The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
Paper • 2505.22617 • Published • 122 -
Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem
Paper • 2506.03295 • Published • 17 -
ConfQA: Answer Only If You Are Confident
Paper • 2506.07309 • Published • 10 -
ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists
Paper • 2506.01241 • Published • 9 -
Prefix Grouper: Efficient GRPO Training through Shared-Prefix Forward
Paper • 2506.05433 • Published • 4 -
RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
Paper • 2506.08672 • Published • 31 -
Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
Paper • 2505.24726 • Published • 223 -
ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning
Paper • 2504.21370 • Published • 1