5 papers
Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training
Miaosen Zhang, Yishan Liu, Shuxia Lin +8
Supervised fine-tuning (SFT) is computationally efficient but often yields inferior generalization compared to reinforcement learning (RL). This gap is primarily driven by RL's use…
RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents
Jialiang Zhu, Gongrui Zhang, Xiaolong Ma +17
LLM-based deep research agents are largely built on the ReAct framework. This linear design makes it difficult to revisit earlier states, branch into alternative search directions,…
InfoAgent: Advancing Autonomous Information-Seeking Agents
Gongrui Zhang, Jialiang Zhu, Ruiqi Yang +15
Building Large Language Model agents that expand their capabilities by interacting with external tools represents a new frontier in AI research and applications. In this paper, we…
CCA: Collaborative Competitive Agents for Image Editing
Tiankai Hang, Shuyang Gu, Dong Chen +2
This paper presents a novel generative model, Collaborative Competitive Agents (CCA), which leverages the capabilities of multiple Large Language Models (LLMs) based agents to exec…
MageBench: Bridging Large Multimodal Models to Agents
Miaosen Zhang, Qi Dai, Yifan Yang +6
LMMs have shown impressive visual understanding capabilities, with the potential to be applied in agents, which demand strong reasoning and planning abilities. Nevertheless, existi…