7 citations · 7 across the 15 of their papers we have counts for
7 papers · 1 filter
Process Reward Informed Tree Rollout for Effective Multi-Turn RL
Xintong Li, Sha Li, Yuwei Zhang +8
Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories fo…
BOOKMARKS: Efficient Active Storyline Memory for Role-playing
Letian Peng, Ziche Liu, Yiming Huang +4
Memory systems are critical for role-playing agents (RPAs) to maintain long-horizon consistency. However, existing RPA memory methods (e.g., profiling) mainly rely on incremental s…
CocoaBench: Evaluating Unified Digital Agents in the Wild
CocoaBench Team, Shibo Hao, Zhining Zhang +29
LLM agents now perform strongly in software engineering, deep research, GUI automation, and various other applications, while recent agent scaffolds and models are increasingly int…
Training Language Models to Generate Quality Code with Program Analysis Feedback
Feng Yao, Zilong Wang, Liyuan Liu +7
Code generation with large language models (LLMs), often termed vibe coding, is increasingly adopted in production but fails to ensure code quality, particularly in security (e.g.,…
Attention Reveals More Than Tokens: Training-Free Long-Context Reasoning with Attention-guided Retrieval
Yuwei Zhang, Jayanth Srinivasa, Gaowen Liu +1
Large Language Models (LLMs) often exhibit substantially shorter effective context lengths than their claimed capacities, especially when handling complex reasoning tasks that requ…
OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation
Zilong Wang, Yuedong Cui, Li Zhong +4
Office automation significantly enhances human productivity by automatically finishing routine tasks in the workflow. Beyond the basic information extraction studied in much of the…
Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
Zilong Wang, Zifeng Wang, Long Le +9
Retrieval augmented generation (RAG) combines the generative abilities of large language models (LLMs) with external knowledge sources to provide more accurate and up-to-date respo…