Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization

• URL: http://arxiv.org/abs/2308.02151v3
• Date: Sun, 5 May 2024 05:04:49 GMT
• Title: Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
• Authors: Weiran Yao, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Yihao Feng, Le Xue, Rithesh Murthy, Zeyuan Chen, Jianguo Zhang, Devansh Arpit, Ran Xu, Phil Mui, Huan Wang, Caiming Xiong, Silvio Savarese,
• Abstract summary: This paper introduces a principled framework for reinforcing large language agents by learning a retrospective model. Our proposed agent architecture learns from rewards across multiple environments and tasks, for fine-tuning a pre-trained language model. Experimental results on various tasks demonstrate that the language agents improve over time.
• Score: 103.70896967077294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objective oriented multi-step tasks on their own, rather than merely responding to queries from human users. Most existing language agents, however, are not optimized using environment-specific rewards. Although some agents enable iterative refinement through verbal feedback, they do not reason and plan in ways that are compatible with gradient-based learning from rewards. This paper introduces a principled framework for reinforcing large language agents by learning a retrospective model, which automatically tunes the language agent prompts from environment feedback through policy gradient. Specifically, our proposed agent architecture learns from rewards across multiple environments and tasks, for fine-tuning a pre-trained language model which refines the language agent prompt by summarizing the root cause of prior failed attempts and proposing action plans. Experimental results on various tasks demonstrate that the language agents improve over time and that our approach considerably outperforms baselines that do not properly leverage gradients from the environment. This demonstrates that using policy gradient optimization to improve language agents, for which we believe our work is one of the first, seems promising and can be applied to optimize other models in the agent architecture to enhance agent performances over time.

Related papers

• Symbolic Learning Enables Self-Evolving Agents [55.625275970720374]
  We introduce agent symbolic learning, a systematic framework that enables language agents to optimize themselves on their own. Agent symbolic learning is designed to optimize the symbolic network within language agents by mimicking two fundamental algorithms in connectionist learning. We conduct proof-of-concept experiments on both standard benchmarks and complex real-world tasks.
  arXiv  Detail & Related papers  (2024-06-26T17:59:18Z)
• MetaReflection: Learning Instructions for Language Agents using Past Reflections [11.028256182234017]
  We introduce MetaReflection, a novel offline reinforcement learning technique that enhances the performance of Language Agents. We demonstrate the efficacy of MetaReflection by evaluating across multiple domains, including complex logical reasoning, biomedical semantic similarity, open world question answering, and vulnerability threat detection.
  arXiv  Detail & Related papers  (2024-05-13T10:51:43Z)
• Towards Objectively Benchmarking Social Intelligence for Language Agents at Action Level [23.833528781431884]
  Social Simulation Tasks in Sandbox (STSS) benchmark is a language-level benchmark for multi-agent simulation. Our evaluative findings highlight that the STSS benchmark is challenging for state-of-the-art language agents.
  arXiv  Detail & Related papers  (2024-04-08T09:25:32Z)
• FireAct: Toward Language Agent Fine-tuning [63.06306936820456]
  We argue for the overlooked direction of fine-tuning LMs to obtain language agents. Fine-tuning Llama2-7B with 500 agent trajectories generated by GPT-4 leads to a 77% HotpotQA performance increase. We propose FireAct, a novel approach to fine-tuning LMs with trajectories from multiple tasks and prompting methods.
  arXiv  Detail & Related papers  (2023-10-09T17:58:38Z)
• Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models [31.509994889286183]
  We introduce Language Agent Tree Search (LATS) -- the first general framework that synergizes the capabilities of language models (LMs) in reasoning, acting, and planning. A key feature of our approach is the incorporation of an environment for external feedback, which offers a more deliberate and adaptive problem-solving mechanism. LATS achieves state-of-the-art pass@1 accuracy (92.7%) for programming on HumanEval with GPT-4 and demonstrates gradient-free performance (average score of 75.9) comparable to gradient-based fine-tuning for web navigation on WebShop with GPT
  arXiv  Detail & Related papers  (2023-10-06T17:55:11Z)
• Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations [63.19448893196642]
  We present a novel framework that harnesses the rich contextual information and semantic representations provided by large language models to analyze behavior graphs. By leveraging this capability, our framework enables personalized and accurate job recommendations for individual users.
  arXiv  Detail & Related papers  (2023-07-10T11:29:41Z)
• Improving Factuality and Reasoning in Language Models through Multiagent Debate [95.10641301155232]
  We present a complementary approach to improve language responses where multiple language model instances propose and debate their individual responses and reasoning processes over multiple rounds to arrive at a common final answer. Our findings indicate that this approach significantly enhances mathematical and strategic reasoning across a number of tasks. Our approach may be directly applied to existing black-box models and uses identical procedure and prompts for all tasks we investigate.
  arXiv  Detail & Related papers  (2023-05-23T17:55:11Z)
• Reflexion: Language Agents with Verbal Reinforcement Learning [44.85337947858337]
  Reflexion is a novel framework to reinforce language agents not by updating weights, but through linguistic feedback. It is flexible enough to incorporate various types (scalar values or free-form language) and sources (external or internally simulated) of feedback signals. For example, Reflexion achieves a 91% pass@1 accuracy on the HumanEval coding benchmark, surpassing the previous state-of-the-art GPT-4 that achieves 80%.
  arXiv  Detail & Related papers  (2023-03-20T18:08:50Z)
• Improving Policy Learning via Language Dynamics Distillation [87.27583619910338]
  We propose Language Dynamics Distillation (LDD), which pretrains a model to predict environment dynamics given demonstrations with language descriptions. We show that language descriptions in demonstrations improve sample-efficiency and generalization across environments.
  arXiv  Detail & Related papers  (2022-09-30T19:56:04Z)

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.