PoAct: Policy and Action Dual-Control Agent for Generalized Applications

2025-01-13 · Guozhi Yuan, Youfeng Liu, Jingli Yang, Wei Jia, Kai Lin, Yansong Gao, Shan He, Zilin Ding, Haitao Li

Based on their superior comprehension and reasoning capabilities, Large Language Model (LLM) driven agent frameworks have achieved significant success in numerous complex reasoning tasks. ReAct-like agents can solve various intricate problems step-by-step through progressive planning and tool calls, iteratively optimizing new steps based on environmental feedback. However, as the planning capabilities of LLMs improve, the actions invoked by tool calls in ReAct-like frameworks often misalign with complex planning and challenging data organization. Code Action addresses these issues while also introducing the challenges of a more complex action space and more difficult action organization. To leverage Code Action and tackle the challenges of its complexity, this paper proposes Policy and Action Dual-Control Agent (PoAct) for generalized applications. The aim is to achieve higher-quality code actions and more accurate reasoning paths by dynamically switching reasoning policies and modifying the action space. Experimental results on the Agent Benchmark for both legal and generic scenarios demonstrate the superior reasoning capabilities and reduced token consumption of our approach in complex tasks. On the LegalAgentBench, our method shows a 20 percent improvement over the baseline while requiring fewer tokens. We conducted experiments and analyses on the GPT-4o and GLM-4 series models, demonstrating the significant potential and scalability of our approach to solve complex problems.

📄 PDF Abstract BibTeX arXiv:2501.07054

Code (0)

등록된 구현이 없습니다.

Tasks

Large Language Model

TopoAct: Visually Exploring the Shape of Activations in Deep Learning

2019-12-13 · Archit Rathore, Nithin Chalapathi, Sourabh Palande, Bei Wang

Deep neural networks such as GoogLeNet, ResNet, and BERT have achieved impressive performance in tasks such as image and text classification. To understand how such performance is achieved, we probe a trained deep neural…

Anomaly Detection Deep Learning Image Classification text-classification+2

Residual Policy Learning for Powertrain Control

2022-12-15 · Lindsey Kerbel, Beshah Ayalew, Andrej Ivanco, Keith Loiselle

Eco-driving strategies have been shown to provide significant reductions in fuel consumption. This paper outlines an active driver assistance approach that uses a residual policy learning (RPL) agent trained to provide r…

Reinforcement Learning (RL)

Enhancing Aerial Combat Tactics through Hierarchical Multi-Agent Reinforcement Learning

2025-05-13 · Ardian Selmonaj, Oleg Szehr, Giacomo Del Rio, Alessandro Antonucci 외

This work presents a Hierarchical Multi-Agent Reinforcement Learning framework for analyzing simulated air combat scenarios involving heterogeneous agents. The objective is to identify effective Courses of Action that le…

Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

Specialized Deep Residual Policy Safe Reinforcement Learning-Based Controller for Complex and Continuous State-Action Spaces

2023-10-15 · Ammar N. Abbas, Georgios C. Chasparis, John D. Kelleher

Traditional controllers have limitations as they rely on prior knowledge about the physics of the problem, require modeling of dynamics, and struggle to adapt to abnormal situations. Deep reinforcement learning has the p…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Safe Reinforcement Learning

HAFO: A Force-Adaptive Control Framework for Humanoid Robots in Intense Interaction Environments

2025-11-25 · Chenhui Dong, Haozhe Xu, Wenhao Feng, Zhipeng Wang 외 arxiv

Reinforcement learning (RL) controllers have made impressive progress in humanoid locomotion and light-weight object manipulation. However, achieving robust and precise motion control with intense force interaction remai…

Reinforcement Learning