Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
Paper • 2606.18844 • Published • 14
M Saad Salman
MSS444
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation upvoted a paper 5 days ago
EfficientRollout: System-Aware Self-Speculative Decoding for RL RolloutsOrganizations
None yet
upvoted a paper about 14 hours ago
upvoted 4
papers 5 days ago
From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning
Paper • 2606.17682 • Published • 26
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
Paper • 2606.18967 • Published • 24
Understanding the Behaviors of Environment-aware Information Retrieval
Paper • 2606.16817 • Published • 9
FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines
Paper • 2606.19605 • Published • 10
upvoted 3
papers 6 days ago
ExpRL: Exploratory RL for LLM Mid-Training
Paper • 2606.17024 • Published • 5
A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization
Paper • 2606.16154 • Published • 8
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
Paper • 2606.18023 • Published • 203
upvoted a paper 8 days ago
upvoted 8
papers 9 days ago
Distilling LLM Feedback for Lean Theorem Proving
Paper • 2605.30861 • Published • 3
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
Paper • 2606.12370 • Published • 21
Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions
Paper • 2606.09076 • Published • 61
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling
Paper • 2606.13473 • Published • 90
MiniMax Sparse Attention
Paper • 2606.13392 • Published • 144
Skip a Layer or Loop It? Learning Program-of-Layers in LLMs
Paper • 2606.06574 • Published • 24
LLM Agents Can See Code Repositories
Paper • 2606.14061 • Published • 20
From AGI to ASI
Paper • 2606.12683 • Published • 35
upvoted 2
papers 13 days ago
Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests
Paper • 2606.07379 • Published • 5
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
Paper • 2606.12191 • Published • 67
upvoted a paper 14 days ago