DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2607.06507v1
• Date: Tue, 07 Jul 2026 17:09:36 GMT
• Title: DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation
• Abstract summary: DynaKRAG formulates multi-hop evidence acquisition as state-conditioned control over atomic evidence operations.<n>With Qwen2.5-7B-Instruct, DynaKRAG achieves F1 scores of 0.5998 on HotpotQA, 0.5340 on 2Wiki, and 0.3061 on MuSiQue.
• Score: 12.710406983346013
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-hop retrieval-augmented generation (RAG) acquires evidence sequentially, with each new document potentially revealing missing facts, bridge entities, query defects, or sufficient support for answering. Existing methods provide useful operations such as iterative retrieval, query reformulation, evidence critique, and sufficiency judging, but typically organize them within method-specific pipelines or predefined control topologies. This leaves underexplored how to learn a shared state-conditioned policy that chooses among currently valid evidence operations. We introduce DynaKRAG, which formulates multi-hop evidence acquisition as state-conditioned control over atomic evidence operations. At each step, a validity layer constructs the executable action set, and a learned controller selects the next operation. The resulting transition updates the evidence state and may enable new operations at subsequent steps. With Qwen2.5-7B-Instruct, DynaKRAG achieves F1 scores of 0.5998 on HotpotQA, 0.5340 on 2Wiki, and 0.3061 on MuSiQue, outperforming the strongest controlled baseline on all three benchmarks. Replacing the learned controller with a uniform-valid policy reduces F1 by 3.96--5.78 points, while removing sufficiency feedback hurts all three datasets. Controlled retrieval-cap experiments further show that additional retrieval is not uniformly beneficial. Together, these results demonstrate the benefit of coordinating retrieval, diagnosis, and gap-directed acquisition under an evolving evidence state.

Related papers

• S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement? [66.17176838165994]
  Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience.<n>It remains unclear whether an agent can actively test its behavior, judge the resulting experience, and use that experience to improve future decisions.<n>We introduce textbfStextsuperscript3Gym, an interactive benchmark for evaluating LLM self-improvement.
  arXiv  Detail & Related papers  (2026-08-31T17:05:41Z)
• EviBack: Search-Agent Reinforcement Learning via Evidence-Constrained Teacher Backoff [12.413369909547699]
  EviBack is an evidence- constrained Teacher backoff that supplies auxiliary super- vision to such groups.<n>A fully automated, end-to-end GPT- 5.5-assisted APE pipeline starts from a manually authored single-prompt dual-task Teacher.
  arXiv  Detail & Related papers  (2026-07-27T02:59:27Z)
• Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkit [8.665845754660458]
  AI-generated video detection GenVidBench and AIGVDBench are the de facto leaderboards.<n>Most evaluation protocols leave uncontrolled confounds that can inflate reported generalizations.<n>A 20-paper survey finds none applying all six standard controls that would catch this.<n>We combine them into an audited protocol and apply it to six representative feature sources.
  arXiv  Detail & Related papers  (2026-06-30T00:29:53Z)
• Divide and Cooperate: Role-Decomposed Multi-Agent LLM Training with Cross-Agent Learning Signals [10.378290102256534]
  existing approaches typically couple evidence acquisition and answer generation within a single policy.<n>We propose DAC (Divide and Cooperate), a role-decomposed multi-agent training framework that divides agentic search into two cooperative subtasks.<n>The generator serves a dual role as both an answer producer and an evidence sufficiency verifier, abstaining when retrieved evidence is insufficient.
  arXiv  Detail & Related papers  (2026-06-09T10:40:55Z)
• Diagnosing Evidence Utilization in Long-Context and Retrieval-Augmented Language Models under Matched Evidence Conditions [0.0]
  A model may answer from parametric priors, fail to use evidence that is present, or cite relevant text without converting it into the final answer.<n>This paper introduces a four-condition diagnostic protocol for evidence-utilization evaluation.
  arXiv  Detail & Related papers  (2026-06-04T22:44:57Z)
• Meta-Modal Agent: Sequential Evidence Routing for Missing-Modality Candidate Reranking [12.476704430465754]
  We introduce the Meta-Modal Agent (MMA), a large language model based candidate-pool reranker that treats missingness as a sequential evidence-routing problem.<n>MMA is trained with balanced missingnesstask reinforcement learning over masked-modality episodes.<n>MMA is evaluated in two variants: MMA-Auto, which uses only automated text, image, and graph tools, and MMA-Interactive, which additionally permits clarification questions grounded in surviving modalities as an upper-bound diagnostic.
  arXiv  Detail & Related papers  (2026-05-24T11:22:03Z)
• AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation [6.314380942821944]
  We propose AdaGATE, a training-free evidence controller for multi-hop RAG.<n>AdaGATE frames evidence selection as a token-constrained repair problem.<n>We evaluate AdaGATE on HotpotQA under clean, redundancy, and noise injected retrieval conditions.
  arXiv  Detail & Related papers  (2026-05-04T14:45:49Z)
• CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning [50.98972985136333]
  CodaRAG is a framework that evolves retrieval from passive lookup into active associative discovery.<n>CodaRAG achieves absolute gains of 7-10% in retrieval recall and 3-11% in generation accuracy.
  arXiv  Detail & Related papers  (2026-04-12T02:50:40Z)
• Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics [89.1999907891494]
  We present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox.<n>Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures.<n>We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies.
  arXiv  Detail & Related papers  (2025-10-01T07:59:03Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• GERE: Generative Evidence Retrieval for Fact Verification [57.78768817972026]
  We propose GERE, the first system that retrieves evidences in a generative fashion. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-04-12T03:49:35Z)
• Disentangle Your Dense Object Detector [82.22771433419727]
  Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors is compromised to lots of conjunctions that may not hold. We propose Disentangled Dense Object Detector (DDOD), in which simple and effective disentanglement mechanisms are designed and integrated into the current state-of-the-art detectors.
  arXiv  Detail & Related papers  (2021-07-07T00:52:16Z)

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.