-
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents
score 13
机构: Cambridge;入选 HF Daily Papers;HF 热度: 54 upvotes (+4);有代码实现;关键词(3): deployment, coding, reasoning
-
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
score 10
入选 HF Daily Papers;HF 热度: 73 upvotes (+4);有代码实现;关键词(2): fine-tuning, reasoning
-
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
score 10
入选 HF Daily Papers;HF 热度: 62 upvotes (+4);有代码实现;关键词(2): PPO, state space
-
Agora: Git as Shared Memory for Collective AutoResearch
score 10
入选 HF Daily Papers;HF 热度: 42 upvotes (+4);有代码实现;关键词(1): coding
-
Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX
score 9
入选 HF Daily Papers;HF 热度: 22 upvotes (+4);有代码实现
-
In-Context Robot Learning with VLM Agents
score 9
入选 HF Daily Papers;HF 热度: 16 upvotes (+3);有代码实现;关键词(4): deployment, agentic, vision-language, embodied
-
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents
score 8
入选 HF Daily Papers;HF 热度: 31 upvotes (+4);关键词(2): deployment, tool use
-
Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control
score 8
入选 HF Daily Papers;HF 热度: 30 upvotes (+4);关键词(3): distillation, serving, real-time
-
A Zeroth-Order Paradigm for LLM Preference Alignment
score 8
入选 HF Daily Papers;HF 热度: 22 upvotes (+4);关键词(1): fine-tuning
-
PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection
score 9
入选 HF Daily Papers;HF 热度: 10 upvotes (+3);有代码实现;关键词(1): vision-language