Adapting LLM Agents Through Communication

Kuan Wang, Yadong Lu, Michael Santacroce, Yeyun Gong, Chao Zhang, yelong shen

Primary Area: representation learning for computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: LLM, agent, NLP, AI

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We introduce the Learning through Communication (LTC) paradigm for training large language models, enhancing their adaptability to new tasks through structured interactions.

Abstract: Recent advancements in large language models (LLMs) have shown potential for human-like agents. To help these agents adapt to new tasks without extensive human supervision, we propose the Learning through Communication (LTC) paradigm, a novel training approach enabling LLM agents to improve continuously through interactions with their environments and other agents. Through iterative exploration and PPO training, LTC empowers the agent to assimilate short-term experiences into long-term memory. To optimize agent interactions for task-specific learning, we introduce three structured communication patterns: Monologue, Dialogue, and Analogue—tailored for common tasks such as decision-making, knowledge-intensive reasoning, and numerical reasoning. We evaluated LTC on three datasets: ALFWorld (decision-making), HotpotQA (knowledge-intensive reasoning), and GSM8k (numerical reasoning). On ALFWorld, it exceeds the instruction tuning baseline by 12% in success rate. On HotpotQA, LTC surpasses the instruction-tuned LLaMA-7B agent by 5.1% in EM score, and it outperforms the instruction-tuned 9x larger PaLM-62B agent by 0.6%. On GSM8k, LTC outperforms the CoT-Tuning baseline by 3.6% in accuracy. The results showcase the versatility and efficiency of the LTC approach across diverse domains. We will open-source our code to promote further development of the community.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1240