ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA
Recent advances in large language models (LLMs) have significantly improved multi-hop question answering (QA) through direct Chain-of-Thought (CoT) reasoning. However, the irreversible nature of CoT leads to error accumulation, making it challenging to correct mistakes in multi-hop reasoning. This paper introduces ReAgent: a Reversible multi-Agent collaborative framework augmented with explicit backtracking mechanisms, enabling reversible multi-hop reasoning. By incorporating text-based retrieval, information aggregation and validation, our system can detect and correct errors mid-reasoning, leading to more robust and interpretable QA outcomes. The framework and experiments serve as a foundation for future work on error-tolerant QA systems. Empirical evaluations across three benchmarks indicate ReAgent's efficacy, yielding average about 6\% improvements against baseline models.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-hop Question AnsweringQuestion AnsweringRetrievalSimilar Papers 제목 키워드 기반
RareAgent: Self-Evolving Reasoning for Drug Repurposing in Rare Diseases
Computational drug repurposing for rare diseases is especially challenging when no prior associations exist between drugs and target diseases. Therefore, knowledge graph completion and message-passing GNNs have little re…
Knowledge Graph CompletionCAREAgent: Clinical Agent with Structured Reasoning and Tool-Integrated for Order Generation
Clinical order generation serves as a critical bridge between clinical decision-making and real-world practice, translating medical decisions into concrete and executable orders. Existing agents mainly focus on coarse-gr…
Reinforcement LearningExploring Reasoning Reward Model for Agents
Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such …
Reinforcement LearningPerception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection
The rapid advancement of generative models presents a significant challenge to existing deepfake detection methods, particularly given the widespread dissemination of highly realistic AI-generated images. Although Multim…
DeepFake DetectionCreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine
We present CreAgentive, an agent workflow driven multi-category creative generation engine that addresses four key limitations of contemporary large language models in writing stories, drama and other categories of creat…