ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent

• URL: http://arxiv.org/abs/2312.10003v1
• Date: Fri, 15 Dec 2023 18:20:15 GMT
• Title: ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
• Authors: Renat Aksitov, Sobhan Miryoosefi, Zonglin Li, Daliang Li, Sheila Babayan, Kavya Kopparapu, Zachary Fisher, Ruiqi Guo, Sushant Prakash, Pranesh Srinivasan, Manzil Zaheer, Felix Yu, Sanjiv Kumar
• Abstract summary: We develop a ReAct-style LLM agent with the ability to reason and act upon external knowledge. We refine the agent through a ReST-like method that iteratively trains on previous trajectories. Starting from a prompted large model and after just two iterations of the algorithm, we can produce a fine-tuned small model.
• Score: 50.508669199496474
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Answering complex natural language questions often necessitates multi-step reasoning and integrating external information. Several systems have combined knowledge retrieval with a large language model (LLM) to answer such questions. These systems, however, suffer from various failure cases, and we cannot directly train them end-to-end to fix such failures, as interaction with external knowledge is non-differentiable. To address these deficiencies, we define a ReAct-style LLM agent with the ability to reason and act upon external knowledge. We further refine the agent through a ReST-like method that iteratively trains on previous trajectories, employing growing-batch reinforcement learning with AI feedback for continuous self-improvement and self-distillation. Starting from a prompted large model and after just two iterations of the algorithm, we can produce a fine-tuned small model that achieves comparable performance on challenging compositional question-answering benchmarks with two orders of magnitude fewer parameters.

Related papers

• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks. However, they still struggle with problems requiring multi-step decision-making and environmental feedback. We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability [19.722009684115434]
  Retrieve-augmented generation (RAG) frameworks have emerged as a promising solution to multi-hop question answering(QA) tasks. Existing RAG frameworks, which usually follows the retrieve-then-read paradigm, often struggle with multi-hop QA with temporal information. This paper proposes a novel framework called review-then-refine, which aims to enhance LLM performance in multi-hop QA scenarios with temporal information.
  arXiv  Detail & Related papers  (2024-12-19T17:48:23Z)
• An Entailment Tree Generation Approach for Multimodal Multi-Hop Question Answering with Mixture-of-Experts and Iterative Feedback Mechanism [14.479060028732803]
  We argue that the current methods of multi-modal multi-hop question answering still mainly face two challenges. The retrieved evidence containing a large amount of redundant information leads to a significant drop in performance. The reasoning process without interpretable reasoning steps makes the model difficult to discover the logical errors for handling complex questions.
  arXiv  Detail & Related papers  (2024-12-08T05:47:55Z)
• Disentangling Memory and Reasoning Ability in Large Language Models [97.26827060106581]
  We propose a new inference paradigm that decomposes the complex inference process into two distinct and clear actions. Our experiment results show that this decomposition improves model performance and enhances the interpretability of the inference process.
  arXiv  Detail & Related papers  (2024-11-20T17:55:38Z)
• RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
  Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs. In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
  arXiv  Detail & Related papers  (2024-10-18T03:45:19Z)
• RAG-Modulo: Solving Sequential Tasks using Experience, Critics, and Language Models [5.0741409008225755]
  Large language models (LLMs) have emerged as promising tools for solving challenging robotic tasks. Most existing LLM-based agents lack the ability to retain and learn from past interactions. We propose RAG-Modulo, a framework that enhances LLM-based agents with a memory of past interactions and incorporates critics to evaluate the agents' decisions.
  arXiv  Detail & Related papers  (2024-09-18T20:03:32Z)
• Recursive Introspection: Teaching Language Model Agents How to Self-Improve [30.086494067593268]
  We develop RISE: Recursive IntroSpEction, an approach for fine-tuning large language models. Our experiments show that RISE enables Llama2, Llama3, and Mistral models to improve themselves with more turns on math reasoning tasks.
  arXiv  Detail & Related papers  (2024-07-25T17:35:59Z)
• MrRank: Improving Question Answering Retrieval System through Multi-Result Ranking Model [4.173772253427094]
  Large Language Models (LLMs) often struggle with hallucinations and outdated information. To address this, Information Retrieval (IR) systems can be employed to augment LLMs with up-to-date knowledge. We propose an approach that leverages learning-to-rank techniques to combine heterogeneous IR systems.
  arXiv  Detail & Related papers  (2024-06-09T11:00:01Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)
• Rethinking with Retrieval: Faithful Large Language Model Inference [91.66406351103484]
  We propose a novel post-processing approach, rethinking with retrieval (RR) RR retrieves relevant external knowledge based on the reasoning steps obtained from the chain-of-thought prompting. We evaluate the effectiveness of RR through extensive experiments with GPT-3 on three complex reasoning tasks.
  arXiv  Detail & Related papers  (2022-12-31T22:35:34Z)

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.