Papers10

#credit assignment

Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration

This paper teaches AI to look things up on the web and fix its own mistakes mid-thought instead of starting over from scratch.

#search-integrated reasoning#reinforcement learning#credit assignment

MARS: Modular Agent with Reflective Search for Automated AI Research

Intermediate

Jiefeng Chen, Bhavana Dalvi Mishra et al.Feb 2arXiv

MARS is an AI agent that runs AI research like a careful scientist and thrifty engineer at the same time.

#MARS#budget-aware MCTS#reflective memory

Scaling Multiagent Systems with Process Rewards

Intermediate

Ed Li, Junyu Ren et al.Jan 30arXiv

This paper teaches AI teams to get better by scoring every move they make, not just the final answer.

#multiagent reinforcement learning#process rewards#AI feedback

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment

Intermediate

Haoyou Deng, Keyu Yan et al.Jan 28arXiv

DenseGRPO teaches image models using lots of small, timely rewards instead of one final score at the end.

#DenseGRPO#flow matching#GRPO

The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models

Beginner

Zanlin Ni, Shenzhi Wang et al.Jan 21arXiv

Diffusion language models can write tokens in any order, but that freedom can accidentally hurt their ability to reason well.

#diffusion language model#arbitrary order generation#autoregressive training

InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning

Intermediate

Matthew Y. R. Yang, Hao Bai et al.Jan 20arXiv

The paper introduces Intervention Training (InT), a simple way for a language model to find and fix the first wrong step in its own reasoning using a short, targeted correction.

#Intervention Training#credit assignment#LLM reasoning

Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning

Intermediate

Zhiyuan Hu, Yunhai Hu et al.Jan 14arXiv

This paper introduces MATTRL, a way for multiple AI agents to learn from their own conversations at test time using short, reusable text notes instead of retraining their weights.

#multi-agent systems#test-time reinforcement learning#experience retrieval

Evolving Programmatic Skill Networks

Intermediate

Haochen Shi, Xingdi Yuan et al.Jan 7arXiv

This paper teaches a computer agent to grow a toolbox of skills that are real, runnable programs, not just text ideas.

#Programmatic Skill Network#continual learning#symbolic programs

Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs

Intermediate

Junbo Li, Peng Zhou et al.Dec 18arXiv

Turn-PPO is a new way to train chatty AI agents that act over many steps, by judging each conversation turn as one whole action instead of judging every single token.

#Turn-PPO#multi-turn reinforcement learning#agentic LLMs

TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models

Intermediate

Zheng Ding, Weirui YeDec 9arXiv

TreeGRPO teaches image generators using a smart branching tree so each training run produces many useful learning signals instead of just one.

#TreeGRPO#reinforcement learning#diffusion models