会员服务
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models
Arxiv
0+阅读 · 6月16日
Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models
Arxiv
0+阅读 · 6月15日
MA-SBI: Misspecification-Aware Simulation-Based Inference via Side-Channel Guidance
Arxiv
0+阅读 · 6月15日
Oops, Wait: Discourse Tokens Matter in Reasoning Model
Arxiv
0+阅读 · 6月15日
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
Arxiv
0+阅读 · 6月14日
Stop When Further Reasoning Won't Help: Attention-State Adaptive Generation in Reasoning Models
Arxiv
0+阅读 · 6月13日
Measuring Weak-to-Strong Legibility of Reasoning Models
Arxiv
0+阅读 · 6月2日
Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models
Arxiv
0+阅读 · 6月10日
interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification
Arxiv
0+阅读 · 5月13日
Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management
Arxiv
0+阅读 · 5月25日
CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabilities of Large Language Models
Arxiv
0+阅读 · 5月28日
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
Arxiv
0+阅读 · 6月9日
Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
Arxiv
0+阅读 · 6月11日
RREDCoT: Segment-Level Reward Redistribution for Reasoning Models
Arxiv
0+阅读 · 6月4日
Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models
Arxiv
0+阅读 · 5月13日
参考链接
微信扫码咨询专知VIP会员
Top