Let LLMs Break Free from Overthinking via Self-Braking Tuning
Paper
•
2505.14604
•
Published
•
19
PotentialApplication
-
-
AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
Paper • 2505.16944 • Published • 6 -
Training Step-Level Reasoning Verifiers with Formal Verification Tools
Paper • 2505.15960 • Published • 6 -
The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
Paper • 2505.15134 • Published • 3 -
Reward Reasoning Model
Paper • 2505.14674 • Published • 30 -
General-Reasoner: Advancing LLM Reasoning Across All Domains
Paper • 2505.14652 • Published • 17 -
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