会员服务
Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use Agents
Arxiv
0+阅读 · 10月2日
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Arxiv
0+阅读 · 10月2日
Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation
Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation
Arxiv
0+阅读 · 10月2日
Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
Arxiv
0+阅读 · 10月2日
Learning to Reason for Hallucination Span Detection
Arxiv
0+阅读 · 10月2日
FOR-Prompting: From Objection to Revision via an Asymmetric Prompting Protocol
Arxiv
0+阅读 · 10月2日
Through the Valley: Path to Effective Long CoT Training for Small Language Models
Arxiv
0+阅读 · 10月1日
ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis
Arxiv
0+阅读 · 10月1日
MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
Arxiv
0+阅读 · 9月30日
Learning to Rank Chain-of-Thought: Using a Small Model
Arxiv
0+阅读 · 9月30日
Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions
Arxiv
0+阅读 · 9月30日
Unspoken Hints: Accuracy Without Acknowledgement in LLM Reasoning
Arxiv
0+阅读 · 9月30日
Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
Arxiv
0+阅读 · 9月30日
Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm
Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm
Arxiv
0+阅读 · 9月30日
Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm
Arxiv
0+阅读 · 9月28日
参考链接
微信扫码咨询专知VIP会员
Top