978 citations · 1k across the 14 of their papers we have counts for
15 papers
Learning Simple Test-Time Environments for LLM Web Agents
Junxuan Li, Zijun Liu, Ziyi Huang +4
Large language model (LLM) agents have demonstrated remarkable proficiency in manually constructed environments, yet their performance frequently collapses when transitioned to com…
Learning to Wait: Synchronizing Agents with the Physical World
Yifei She, Ping Zhang, He Liu +6
Real-world agentic tasks, unlike synchronous Markov Decision Processes (MDPs), often involve non-blocking actions with variable latencies, creating a fundamental \textit{Temporal G…
Video Generation Models Are Good Latent Reward Models
Xiaoyue Mi, Wenqing Yu, Jiesong Lian +9
Reward feedback learning (ReFL) has proven effective for aligning image generation with human preferences. However, its extension to video generation faces significant challenges.…
VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning
Boyu Chen, Zikang Wang, Zhengrong Yue +9
By leveraging tool-augmented Multimodal Large Language Models (MLLMs), multi-agent frameworks are driving progress in video understanding. However, most of them adopt static and no…
ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems
Qiaoling Chen, Zijun Liu, Peng Sun +6
Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative d…
Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration
Zijun Liu, Zhennan Wan, Peng Li +3
With the rapid advancement of post-training techniques for reasoning and information seeking, large language models (LLMs) can incorporate a large quantity of retrieved knowledge t…
Inference-Time Scaling for Generalist Reward Modeling
Zijun Liu, Peiyi Wang, Runxin Xu +5
Reinforcement learning (RL) has been widely adopted in post-training for large language models (LLMs) at scale. Recently, the incentivization of reasoning capabilities in LLMs from…
Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalization
Zhitao He, Zijun Liu, Peng Li +5
LLM-based agents have made significant advancements in interactive environments, such as mobile operations and web browsing, and other domains beyond computer using. Current multi-…
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
DeepSeek-AI, Daya Guo, Dejian Yang +195
General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-tho…
AIGS: Generating Science from AI-Powered Automated Falsification
Zijun Liu, Kaiming Liu, Yiqi Zhu +5
Rapid development of artificial intelligence has drastically accelerated the development of scientific discovery. Trained with large-scale observation data, deep neural networks ex…
Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages
Yuanchi Zhang, Yile Wang, Zijun Liu +5
While large language models (LLMs) have been pre-trained on multilingual corpora, their performance still lags behind in most languages compared to a few resource-rich languages. O…
Towards Unified Alignment Between Agents, Humans, and Environment
Zonghan Yang, An Liu, Zijun Liu +11
The rapid progress of foundation models has led to the prosperity of autonomous agents, which leverage the universal capabilities of foundation models to conduct reasoning, decisio…
Enabling Weak LLMs to Judge Response Reliability via Meta Ranking
Zijun Liu, Boqun Kou, Peng Li +4
Despite the strong performance of large language models (LLMs) across a wide range of tasks, they still have reliability issues. Previous studies indicate that strong LLMs like GPT…
A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration
Zijun Liu, Yanzhe Zhang, Peng Li +2
Recent studies show that collaborating multiple large language model (LLM) powered agents is a promising way for task solving. However, current approaches are constrained by using…
An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation
Xuancheng Huang, Zijun Liu, Peng Li +3
Recently, multi-aspect controllable text generation that controls the generated text in multiple aspects (e.g., sentiment, topic, and keywords) has attracted increasing attention.…