7 papers
ToolGate: Token-Efficient Pre-Call Control for Tool-Augmented Vision-Language Agents
Anjie Liu, Yan Song, Zhixun Chen +3
Tool-augmented vision-language agents can acquire external perceptual evidence through OCR, detection, segmentation, and other tools, but executing every proposed tool call is cost…
The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design
Anjie Liu, Ziqin Gong, Yan Song +6
Visual perception in modern Vision-Language Models (VLMs) is constrained by a perceptual bandwidth bottleneck: a broad field of view preserves global context but sacrifices the fin…
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Guibin Zhang, Hejia Geng, Xiaohang Yu +22
The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LL…
Probing the "Psyche'' of Large Reasoning Models: Understanding Through a Human Lens
Yuxiang Chen, Zuohan Wu, Ziwei Wang +6
Large reasoning models (LRMs) have garnered significant attention from researchers owing to their exceptional capability in addressing complex tasks. Motivated by the observed huma…
A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
Anjie Liu, Jianhong Wang, Samuel Kaski +2
Steering cooperative multi-agent reinforcement learning (MARL) towards desired outcomes is challenging, particularly when the global guidance from a human on the whole multi-agent…
Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
Xiangning Yu, Zhuohan Wang, Linyi Yang +5
Chain-of-Thought (CoT) prompting plays an indispensable role in endowing large language models (LLMs) with complex reasoning capabilities. However, CoT currently faces two fundamen…