ACC: Compiling Agent Trajectories for Long-Context Training
Paper • 2605.21850 • Published • 56
M Saad Salman
MSS444
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
ACC: Compiling Agent Trajectories for Long-Context Training upvoted a paper 3 days ago
The Unlearnability Phenomenon in RLVR for Language ModelsOrganizations
None yet
upvoted a paper 1 day ago
upvoted 4
papers 3 days ago
The Unlearnability Phenomenon in RLVR for Language Models
Paper • 2605.16787 • Published • 5
On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists
Paper • 2605.20668 • Published • 11
Generative Recursive Reasoning
Paper • 2605.19376 • Published • 25
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
Paper • 2605.21468 • Published • 44
upvoted 11
papers 5 days ago
RewardHarness: Self-Evolving Agentic Post-Training
Paper • 2605.08703 • Published • 9
EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
Paper • 2605.13941 • Published • 24
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Paper • 2605.06527 • Published • 44
Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
Paper • 2605.14892 • Published • 47
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
Paper • 2605.14386 • Published • 59
Self-Distilled Agentic Reinforcement Learning
Paper • 2605.15155 • Published • 108
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
Paper • 2605.13301 • Published • 155
Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
Paper • 2605.15871 • Published • 16
Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
Paper • 2605.15301 • Published • 22
Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
Paper • 2605.02290 • Published • 39
Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR
Paper • 2605.15726 • Published • 32
upvoted 4
papers 10 days ago
Reward Hacking in Rubric-Based Reinforcement Learning
Paper • 2605.12474 • Published • 5
Do not copy and paste! Rewriting strategies for code retrieval
Paper • 2605.08299 • Published • 10
Continual Harness: Online Adaptation for Self-Improving Foundation Agents
Paper • 2605.09998 • Published • 17
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
Paper • 2605.12483 • Published • 10