From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Training Retrieval-Augmented Generation Agents

• URL: http://arxiv.org/abs/2509.23071v1
• Date: Sat, 27 Sep 2025 02:53:09 GMT
• Title: From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Training Retrieval-Augmented Generation Agents
• Abstract summary: We propose EviPath, an evidence-anchored reasoning path synthesis paradigm for RAG agent development.<n>EviPath comprises: (i) Abductive Subtask Planning, which decomposes the problem into sub-questions and iteratively plans an optimal solution path based on the dependencies between them; (ii) Faithful Sub-question Answering, which uses supporting evidence to construct a proxy environment to generate reasoning thoughts and answers for each sub-question; and (iii) Conversational Fine-Tuning, which formats the complete agent-environment interaction trajectory into a dialogue format suitable for Supervised Fine-Tuning
• Score: 47.06655345033574
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Retrieval-augmented generation agents development is hindered by the lack of process-level supervision to effectively guide agentic capabilities like task decomposition, retriever invocation, and stepwise decision-making. While reinforcement learning offers a potential solution, it suffers from sparse rewards and the limited reasoning capabilities of large language models (LLMs). Meanwhile, existing data synthesis methods only produce chain-of-thought rationales and fail to model environmental interactions. In this paper, we propose EviPath, an evidence-anchored reasoning path synthesis paradigm for RAG agent development. EviPath comprises: (i) Abductive Subtask Planning, which decomposes the problem into sub-questions and iteratively plans an optimal solution path based on the dependencies between them; (ii) Faithful Sub-question Answering, which uses supporting evidence to construct a proxy environment to generate reasoning thoughts and answers for each sub-question; and (iii) Conversational Fine-Tuning, which formats the complete agent-environment interaction trajectory into a dialogue format suitable for Supervised Fine-Tuning. EviPath allows LLMs to learn complex reasoning and tool-use capabilities directly from synthesized data. Extensive experiments on widely-used question-answering benchmarks show that an 8B parameter model trained with EviPath-synthesized data significantly and consistently outperforms state-of-the-art baselines with a double-digit absolute EM gain of 14.7% in open-domain question answering.

Related papers

• Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents [9.918296068965665]
  Ideation plays a pivotal role in scientific discovery.<n>Agentic-Ideation is a novel framework comprising an automated trajectory synthesis pipeline and a specialized agentic LLM trained for scientific ideation.
  arXiv  Detail & Related papers  (2026-06-30T07:07:51Z)
• ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation [23.934630478971517]
  ToE is a hierarchical evidence reasoning framework for automated fact-checking.<n>ToE integrates a reinforcement learning-driven multi-source retrieval agent, an evidence evaluation agent, and an argument tree aggregation algorithm.<n>We show that ToE achieves improvements ranging from 4 to 24 percentage points over competitive baselines.
  arXiv  Detail & Related papers  (2026-06-26T05:35:27Z)
• LOGIGEN: Logic-Driven Generation of Verifiable Agentic Tasks [4.6880826836662814]
  We introduce textbfLOGIGEN, a logic-driven framework that synthesizes verifiable training data.<n>On $2$-Bench, LOGIGEN-32B(RL) achieves a textbf79.5% success rate, substantially outperforming the base model.
  arXiv  Detail & Related papers  (2026-02-28T08:35:30Z)
• Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervision [11.159231524113764]
  Reinforcement Learning (RL) has emerged as a pivotal mechanism for enhancing the complex reasoning capabilities of Multimodal Large Language Models (MLLMs)<n>In this paper, we propose the textbfGuided Verifier framework to address these structural limitations.<n>We develop a specialized data synthesis pipeline targeting multimodal hallucinations, constructing textbfCoRe dataset of process-level negatives and textbfCorrect-guide textbfReasoning trajectories to train the guided verifier.
  arXiv  Detail & Related papers  (2026-02-04T07:38:42Z)
• KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering [64.62317305868264]
  We present textbfKBQA-R1, a framework that shifts the paradigm from text imitation to interaction optimization via Reinforcement Learning.<n>Treating KBQA as a multi-turn decision process, our model learns to navigate the knowledge base using a list of actions.<n>Experiments on WebQSP, GrailQA, and GraphQuestions demonstrate that KBQA-R1 achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-10T17:45:42Z)
• Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search [70.63903518295785]
  We introduce RepoSearch-R1, a novel agentic reinforcement learning framework driven by Monte-carlo Tree Search.<n>Based on RepoSearch-R1, we construct a RepoQA-Agent specifically designed for repository question-answering tasks.
  arXiv  Detail & Related papers  (2025-10-30T09:10:36Z)
• Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models [64.49342399229529]
  We argue that post-hoc attribution can be reframed as a reasoning problem, where answers are decomposed into constituent units, each tied to specific context.<n>We introduce DecompTune, a post-training method that teaches models to produce answer decompositions as intermediate reasoning steps.<n>Across extensive experiments and ablations, DecompTune substantially improves attribution quality, outperforming prior methods and matching or exceeding state-of-the-art frontier models.
  arXiv  Detail & Related papers  (2025-10-29T17:58:59Z)
• Following the TRACE: A Structured Path to Empathetic Response Generation with Multi-Agent Models [19.450298798183166]
  Empathetic response generation is a crucial task for creating more human-like and supportive conversational agents.<n>Existing methods face a core trade-off between the analytical depth of specialized models and the generative fluency of Large Language Models.<n>We propose TRACE, a novel framework that models empathy as a structured cognitive process by decomposing the task into a pipeline for analysis and synthesis.
  arXiv  Detail & Related papers  (2025-09-26T04:20:37Z)
• Audited Reasoning Refinement: Fine-Tuning Language Models via LLM-Guided Step-Wise Evaluation and Correction [1.41282143488996]
  Training a task-specific small reasoning model is challenging when direct human supervision or high-quality labels are scarce.<n>We propose Reason-Refine-then-Align (R2tA), which turns refined model rationales into supervision for training task-specific reasoning models.
  arXiv  Detail & Related papers  (2025-09-15T21:47:52Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges [6.615766570234612]
  Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to overcome the knowledge limitations of Large Language Models.<n>To address these challenges, the field has shifted toward Reasoning Agentic RAG, a paradigm that embeds decision-making and adaptive tool use directly into the retrieval process.
  arXiv  Detail & Related papers  (2025-06-12T07:01:56Z)
• MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning [43.66966457772646]
  MA-RAG orchestrates a collaborative set of specialized AI agents to tackle each stage of the RAG pipeline with task-aware reasoning.<n>Our design allows fine-grained control over information flow without any model fine-tuning.<n>This modular and reasoning-driven architecture enables MA-RAG to deliver robust, interpretable results.
  arXiv  Detail & Related papers  (2025-05-26T15:05:18Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Successive Prompting for Decomposing Complex Questions [50.00659445976735]
  Recent works leverage the capabilities of large language models (LMs) to perform complex question answering in a few-shot setting. We introduce Successive Prompting'', where we iteratively break down a complex task into a simple task, solve it, and then repeat the process until we get the final solution. Our best model (with successive prompting) achieves an improvement of 5% absolute F1 on a few-shot version of the DROP dataset.
  arXiv  Detail & Related papers  (2022-12-08T06:03:38Z)
• Paired Examples as Indirect Supervision in Latent Decision Models [109.76417071249945]
  We introduce a way to leverage paired examples that provide stronger cues for learning latent decisions. We apply our method to improve compositional question answering using neural module networks on the DROP dataset.
  arXiv  Detail & Related papers  (2021-04-05T03:58:30Z)

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.