Adapting LLM Agents with Universal Feedback in Communication

• URL: http://arxiv.org/abs/2310.01444v3
• Date: Sun, 14 Apr 2024 03:47:19 GMT
• Title: Adapting LLM Agents with Universal Feedback in Communication
• Authors: Kuan Wang, Yadong Lu, Michael Santacroce, Yeyun Gong, Chao Zhang, Yelong Shen,
• Abstract summary: We introduce Learning through Communication (LTC) to facilitate the training for large language models (LLMs) agents. We design a universal buffer to store all the feedback, and an iterative pipeline to enable an LLM agent to explore and update its policy. We evaluate the efficacy of our LTC approach on four diverse datasets.
• Score: 42.42697243815094
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in large language models (LLMs) have demonstrated potential for LLM agents. To facilitate the training for these agents with both linguistic feedback and non-linguistic reward signals, we introduce Learning through Communication (LTC). We design a universal buffer to store all the feedback, and an iterative pipeline to enable an LLM agent to explore and update its policy in an given environment. To optimize agent interactions for task-specific learning with our universal buffer and pipeline, we introduce diverse communication patterns tailored for both single-agent and multi-agent environments. We evaluate the efficacy of our LTC approach on four diverse datasets: ALFWorld (single-agent), HotpotQA (multi-agent collaboration), Chameleon (multi-agent competition), and GSM8k (multi-agent teacher-student). On these data sets, LTC outperforms the supervised instruction fine-tuning baselines by 3.6% to 12%. These results highlight the versatility and efficiency of LTC in facilitating online adaptation for LLM agents.

Related papers

• Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining [40.21546440726592]
  We propose a novel multi-agent collaborative data selection mechanism for large language models (LLMs) pretraining. In this framework, each data selection method serves as an independent agent, and an agent console is designed to dynamically integrate the information from all agents.
  arXiv  Detail & Related papers  (2024-10-10T16:45:28Z)
• LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions [8.55917897789612]
  We focus on the cooperative tasks of multiple agents with a common goal and communication among them. We also consider human-in/on-the-loop scenarios enabled by the language component in the framework.
  arXiv  Detail & Related papers  (2024-05-17T22:10:23Z)
• Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models [56.00992369295851]
  Open-sourced Large Language Models (LLMs) have achieved great success in various NLP tasks, however, they are still far inferior to API-based models when acting as agents. This paper delivers three key observations: (1) the current agent training corpus is entangled with both formats following and agent reasoning, which significantly shifts from the distribution of its pre-training data; (2) LLMs exhibit different learning speeds on the capabilities required by agent tasks; and (3) current approaches have side-effects when improving agent abilities by introducing hallucinations. We propose Agent-FLAN to effectively Fine-tune LANguage models for Agents.
  arXiv  Detail & Related papers  (2024-03-19T16:26:10Z)
• EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents [65.38474102119181]
  We propose EnvGen, a framework to adaptively create training environments. We train a small RL agent in a mixture of the original and LLM-generated environments. We find that a small RL agent trained with EnvGen can outperform SOTA methods, including a GPT-4 agent, and learns long-horizon tasks significantly faster.
  arXiv  Detail & Related papers  (2024-03-18T17:51:16Z)
• Mutual Enhancement of Large Language and Reinforcement Learning Models through Bi-Directional Feedback Mechanisms: A Case Study [1.3597551064547502]
  We employ a teacher-student learning framework to tackle problems of Large Language Models (LLMs) and reinforcement learning (RL) models. Within this framework, the LLM acts as a teacher, while the RL model acts as a student. We propose a practical algorithm to address the problem and conduct empirical experiments to evaluate the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-01-12T14:35:57Z)
• SpeechAgents: Human-Communication Simulation with Multi-Modal Multi-Agent Systems [53.94772445896213]
  Large Language Model (LLM)-based multi-agent systems have demonstrated promising performance in simulating human society. We propose SpeechAgents, a multi-modal LLM based multi-agent system designed for simulating human communication.
  arXiv  Detail & Related papers  (2024-01-08T15:01:08Z)
• Large Language Model Enhanced Multi-Agent Systems for 6G Communications [94.45712802626794]
  We propose a multi-agent system with customized communication knowledge and tools for solving communication related tasks using natural language. We validate the effectiveness of the proposed multi-agent system by designing a semantic communication system.
  arXiv  Detail & Related papers  (2023-12-13T02:35:57Z)
• Building Cooperative Embodied Agents Modularly with Large Language Models [104.57849816689559]
  We address challenging multi-agent cooperation problems with decentralized control, raw sensory observations, costly communication, and multi-objective tasks instantiated in various embodied environments. We harness the commonsense knowledge, reasoning ability, language comprehension, and text generation prowess of LLMs and seamlessly incorporate them into a cognitive-inspired modular framework. Our experiments on C-WAH and TDW-MAT demonstrate that CoELA driven by GPT-4 can surpass strong planning-based methods and exhibit emergent effective communication.
  arXiv  Detail & Related papers  (2023-07-05T17:59:27Z)
• Multi-Agent Transfer Learning in Reinforcement Learning-Based Ride-Sharing Systems [3.7311680121118345]
  Reinforcement learning (RL) has been used in a range of simulated real-world tasks. In this paper we investigate the impact of TL transfer parameters with fixed source and target roles.
  arXiv  Detail & Related papers  (2021-12-01T11:23:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.