Papers181

#GRPO

LSRIF: Logic-Structured Reinforcement Learning for Instruction Following

Real instructions often have logic like and first-then and if-else and this paper teaches models to notice and obey that logic.

#instruction following#logical structures#parallel constraints

Not triaged yet

Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

Intermediate

Jiajie Zhang, Xin Lv et al.Jan 9arXiv

The paper fixes a big problem in training web-searching AI: rewarding only the final answer makes agents cut corners and sometimes hallucinate.

#deep search agents#reinforcement learning#rubric rewards

Not triaged yet

An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift

Intermediate

Constantinos Karouzos, Xingwei Tan et al.Jan 9arXiv

Preference tuning teaches language models to act the way people like, but those habits can fall apart when the topic or style changes (domain shift).

#preference tuning#domain shift#supervised fine-tuning

Not triaged yet

Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

Beginner

Yuxiang Ji, Yong Wang et al.Jan 8arXiv

The paper teaches an AI to act like a careful traveler: it looks at a photo, forms guesses about where it might be, and uses real map tools to check each guess.

#image geolocalization#map-augmented agent#Thinking with Map

Not triaged yet

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Intermediate

Shih-Yang Liu, Xin Dong et al.Jan 8arXiv

When a model learns from many rewards at once, a popular method called GRPO can accidentally squash different reward mixes into the same learning signal, which confuses training.

#GDPO#GRPO#multi-reward reinforcement learning

Not triaged yet

RelayLLM: Efficient Reasoning via Collaborative Decoding

Intermediate

Chengsong Huang, Tong Zheng et al.Jan 8arXiv

RelayLLM lets a small model do the talking and only asks a big model for help on a few, truly hard tokens.

#token-level collaboration#<call>n</call> command#collaborative decoding

Not triaged yet

Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing

Beginner

Runze He, Yiji Cheng et al.Jan 8arXiv

Re-Align is a new way for AI to make and edit pictures by thinking in clear steps before drawing.

#In-Context Image Generation#Reference-based Image Editing#Structured Reasoning

Not triaged yet

Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction

Beginner

Muzhao Tian, Zisu Huang et al.Jan 8arXiv

Long-term AI helpers remember past chats, but using all memories can trap them in old ideas (Memory Anchoring).

#steerable memory#memory anchoring#long-term agents

Not triaged yet

SmartSearch: Process Reward-Guided Query Refinement for Search Agents

Intermediate

Tongyu Wen, Guanting Dong et al.Jan 8arXiv

SmartSearch teaches search agents to fix their own bad search queries while they are thinking, not just their final answers.

#Search agents#Process rewards#Query refinement

Not triaged yet

AgentOCR: Reimagining Agent History via Optical Self-Compression

Intermediate

Lang Feng, Fuchao Yang et al.Jan 8arXiv

AgentOCR turns an agent’s long text history into pictures so it can remember more using fewer tokens.

#AgentOCR#optical self-compression#visual tokens

Not triaged yet

Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization

Intermediate

Mizanur Rahman, Mohammed Saidul Islam et al.Jan 8arXiv

This paper teaches a model to turn a question about a table into both a short answer and a clear, correct chart.

#Text-to-Visualization#Reinforcement Learning#GRPO

Not triaged yet

ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing

Beginner

Hengjia Li, Liming Jiang et al.Jan 6arXiv

ThinkRL-Edit teaches an image editor to think first and draw second, which makes tricky, reasoning-heavy edits much more accurate.

#reasoning-centric image editing#reinforcement learning#chain-of-thought

Not triaged yet

8 9 10 11 12