Reinforcing Question Answering Agents with Minimalist Policy Gradient Optimization

• URL: http://arxiv.org/abs/2505.17086v1
• Date: Tue, 20 May 2025 18:33:03 GMT
• Title: Reinforcing Question Answering Agents with Minimalist Policy Gradient Optimization
• Authors: Yihong Wu, Liheng Ma, Muzhi Li, Jiaming Zhou, Jianye Hao, Ho-fung Leung, Irwin King, Yingxue Zhang, Jian-Yun Nie,
• Abstract summary: Mujica is a planner that decomposes questions into acyclic graph of subquestions and a worker that resolves questions via retrieval and reasoning.<n>MyGO is a novel reinforcement learning method that replaces traditional policy updates with gradient Likelihood Maximum Estimation.<n> Empirical results across multiple datasets demonstrate the effectiveness of MujicaMyGO in enhancing multi-hop QA performance.
• Score: 80.09112808413133
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Models (LLMs) have demonstrated remarkable versatility, due to the lack of factual knowledge, their application to Question Answering (QA) tasks remains hindered by hallucination. While Retrieval-Augmented Generation mitigates these issues by integrating external knowledge, existing approaches rely heavily on in-context learning, whose performance is constrained by the fundamental reasoning capabilities of LLMs. In this paper, we propose Mujica, a Multi-hop Joint Intelligence for Complex Question Answering, comprising a planner that decomposes questions into a directed acyclic graph of subquestions and a worker that resolves questions via retrieval and reasoning. Additionally, we introduce MyGO (Minimalist policy Gradient Optimization), a novel reinforcement learning method that replaces traditional policy gradient updates with Maximum Likelihood Estimation (MLE) by sampling trajectories from an asymptotically optimal policy. MyGO eliminates the need for gradient rescaling and reference models, ensuring stable and efficient training. Empirical results across multiple datasets demonstrate the effectiveness of Mujica-MyGO in enhancing multi-hop QA performance for various LLMs, offering a scalable and resource-efficient solution for complex QA tasks.

Related papers

• Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models? [62.579951798437115]
  This work investigates iterative approximate evaluation for arbitrary prompts.<n>It introduces Model Predictive Prompt Selection (MoPPS), a Bayesian risk-predictive framework.<n>MoPPS reliably predicts prompt difficulty and accelerates training with significantly reduced rollouts.
  arXiv  Detail & Related papers  (2025-07-07T03:20:52Z)
• Decompositional Reasoning for Graph Retrieval with Large Language Models [1.034893617526558]
  Large Language Models (LLMs) excel at many NLP tasks, but struggle with multi-hop reasoning and factual consistency.<n>We propose a novel retrieval approach that integrates textual knowledge graphs into the LLM reasoning process via query decomposition.<n>Our method decomposes complex questions into sub-questions, retrieves relevant textual subgraphs, and composes a question-specific knowledge graph to guide answer generation.
  arXiv  Detail & Related papers  (2025-06-16T11:44:28Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>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.<n>Existing RAG frameworks, which usually follows the retrieve-then-read paradigm, often struggle with multi-hop QA with temporal information.<n>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)
• 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)
• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization [49.362750475706235]
  Reinforcement Learning (RL) plays a crucial role in aligning large language models with human preferences and improving their ability to perform complex tasks.<n>We introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model.<n> Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.
  arXiv  Detail & Related papers  (2024-10-11T23:29:20Z)
• Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
  Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning. We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
  arXiv  Detail & Related papers  (2024-06-20T13:08:09Z)
• Addressing the issue of stochastic environments and local decision-making in multi-objective reinforcement learning [0.0]
  Multi-objective reinforcement learning (MORL) is a relatively new field which builds on conventional Reinforcement Learning (RL) This thesis focuses on what factors influence the frequency with which value-based MORL Q-learning algorithms learn the optimal policy for an environment.
  arXiv  Detail & Related papers  (2022-11-16T04:56:42Z)
• KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering [28.18555591429343]
  We propose a novel framework named Knowledge Enhanced Contrastive Prompt-tuning (KECP) Instead of adding pointer heads to PLMs, we transform the task into a non-autoregressive Masked Language Modeling (MLM) generation problem. Our method consistently outperforms state-of-the-art approaches in few-shot settings by a large margin.
  arXiv  Detail & Related papers  (2022-05-06T08:31:02Z)
• Simultaneously Evolving Deep Reinforcement Learning Models using Multifactorial Optimization [18.703421169342796]
  This work proposes a framework capable of simultaneously evolving several DQL models towards solving interrelated Reinforcement Learning tasks. A thorough experimentation is presented and discussed so as to assess the performance of the framework.
  arXiv  Detail & Related papers  (2020-02-25T10:36:57Z)

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.