Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs
Paper • 2609.04753 • Published • 12
Chanuk Lee
tally0818
AI & ML interests
LLM post-training
Recent Activity
upvoted a paper 3 days ago
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments upvoted a paper 3 days ago
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?Organizations
None yet
upvoted a paper 1 day ago
upvoted 2
papers 3 days ago
upvoted a paper 4 days ago
upvoted 4
papers 7 days ago
Multi-Turn On-Policy Distillation with Prefix Replay
Paper • 2607.04763 • Published • 14
SHAPE of Chain-of-Thought in Math Reasoning
Paper • 2608.28600 • Published • 31
Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase
Paper • 2608.29310 • Published • 27
Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement
Paper • 2608.31046 • Published • 144
upvoted a paper 18 days ago
upvoted a paper 20 days ago
upvoted 5
papers 21 days ago
SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning
Paper • 2608.14277 • Published • 35
Intern-S2-Preview: Scientific Agentic Foundation Model
Paper • 2608.13505 • Published • 72
Stealing Reasoning Traces from Proprietary LLM APIs
Paper • 2608.09867 • Published • 117
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers
Paper • 2608.06867 • Published • 111
Self-Supervised Visual On-Policy Distillation
Paper • 2608.14144 • Published • 170
upvoted 3
papers 25 days ago
upvoted 2
papers 28 days ago