会员服务
RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models
Arxiv
0+阅读 · 2月19日
Entropy After $\langle \texttt{/Think} \rangle$ for reasoning model early exiting
Arxiv
0+阅读 · 2月19日
Training Large Reasoning Models Efficiently via Progressive Thought Encoding
Arxiv
0+阅读 · 2月18日
VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models
Arxiv
0+阅读 · 2月18日
Should You Use Your Large Language Model to Explore or Exploit?
Should You Use Your Large Language Model to Explore or Exploit?
Arxiv
0+阅读 · 2月17日
Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning
Arxiv
0+阅读 · 2月16日
The Interspeech 2026 Audio Reasoning Challenge: Evaluating Reasoning Process Quality for Audio Reasoning Models and Agents
Arxiv
0+阅读 · 2月15日
Statistical Early Stopping for Reasoning Models
Arxiv
0+阅读 · 2月15日
To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks
Arxiv
0+阅读 · 2月11日
ESTAR: Early-Stopping Token-Aware Reasoning For Efficient Inference
Arxiv
0+阅读 · 2月10日
Bridging Efficiency and Transparency: Explainable CoT Compression in Multimodal Large Reasoning Models
Arxiv
0+阅读 · 2月10日
interwhen: A Generalizable Framework for Verifiable Reasoning with Test-time Monitors
Arxiv
0+阅读 · 2月5日
MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models
Arxiv
0+阅读 · 2月7日
ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning
Arxiv
0+阅读 · 2月10日
Free(): Learning to Forget in Malloc-Only Reasoning Models
Arxiv
0+阅读 · 2月10日
参考链接
微信扫码咨询专知VIP会员
Top