8 papers
ArenaFlow: From Trajectory Ranking to Hierarchical Credit Propagation for Open-Ended Agent RL
Qiang Zhang, Ruixue Ding, Fanrui Zhang +9
Reinforcement learning has substantially improved large language model (LLM) agents in verifiable domains, but remains difficult to apply to open-ended agent tasks, where solutions…
ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning
Fanrui Zhang, Ruixue Ding, Qiang Zhang +13
Training open-ended agents via reinforcement learning (RL) is hindered by the lack of verifiable gold answers and scalable rubrics. Moreover, even near the model's capability bound…
FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization
Qingchuan Zhang, He Cao, Hao Li +6
Molecular optimization seeks to improve a molecule through small structural edits while preserving similarity to the starting compound. Recent language-model approaches typically t…
VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
Qiuchen Wang, Shihang Wang, Yu Zeng +9
Effectively retrieving, reasoning, and understanding multimodal information remains a critical challenge for agentic systems. Traditional Retrieval-augmented Generation (RAG) metho…
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
Qiang Zhang, Boli Chen, Fanrui Zhang +14
Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast soluti…
Tongyi DeepResearch Technical Report
Tongyi DeepResearch Team, Baixuan Li, Bo Zhang +54
We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous…
VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning
Qiuchen Wang, Ruixue Ding, Yu Zeng +6
Effectively retrieving, reasoning and understanding visually rich information remains a challenge for RAG methods. Traditional text-based methods cannot handle visual-related infor…
ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents
Qiuchen Wang, Ruixue Ding, Zehui Chen +4
Understanding information from visually rich documents remains a significant challenge for traditional Retrieval-Augmented Generation (RAG) methods. Existing benchmarks predominant…