MARS: A Multi-Agent Framework Incorporating Socratic Guidance for Automated Prompt Optimization
Paper
•
2503.16874
•
Published
•
44
programmer.ie
Papers I have written about on my blog.
-
-
System Prompt Optimization with Meta-Learning
Paper • 2505.09666 • Published • 70 -
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
Paper • 2505.23380 • Published • 23 -
DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
Paper • 2505.23754 • Published • 15 -
Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence
Paper • 2505.20325 • Published • 45 -
Reward Reasoning Model
Paper • 2505.14674 • Published • 35 -
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper • 2503.18878 • Published • 118 -
Pre-trained Large Language Models Learn Hidden Markov Models In-context
Paper • 2506.07298 • Published • 17