Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents
Paper • 2609.17708 • Published • 54
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
View all activity
Organizations
None yet
upvoted 10
papers 1 day ago
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction
Paper • 2609.18063 • Published • 10
Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training
Paper • 2609.14306 • Published • 10
In-Context Robot Learning with VLM Agents
Paper • 2609.19138 • Published • 16
Agora: Git as Shared Memory for Collective AutoResearch
Paper • 2609.18094 • Published • 41
ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models
Paper • 2609.18487 • Published • 39
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
Paper • 2609.18708 • Published • 62
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
Paper • 2609.17488 • Published • 184
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
Paper • 2609.19134 • Published • 73
Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement
Paper • 2609.13406 • Published • 36
upvoted 10
papers 3 days ago
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Paper • 2609.14857 • Published • 160
StepAudio 3 Realtime Technical Report
Paper • 2609.14005 • Published • 109
StepAudio 3 Music Technical Report
Paper • 2609.16034 • Published • 86
PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
Paper • 2609.17521 • Published • 6
Modality-Autoregressive World-Action Models
Paper • 2609.17524 • Published • 8
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Paper • 2609.11873 • Published • 89
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
Paper • 2609.17523 • Published • 24
AI for Games in the Foundation Model Era
Paper • 2609.16679 • Published • 120
Continual Learning Mechanisms Compose for Long-Horizon Memorization
Paper • 2609.06986 • Published • 325
Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures
Paper • 2609.13463 • Published • 3