paper-with-me

Papers

Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki

2026-05-25 · Haoliang Ming, Feifei Li, Xiaoqing Wu, Wenhui Que arxiv

LLM agents require retrieval to behave less like one-shot context fetching and more like reasoning: searching, reading, traversing, and deciding when evidence is sufficient. Yet current Retrieval-Augmented Generation (RAG) systems organize external knowledge as flat chunks retrieved by embedding similarity, exposing a retrieval-as-lookup interface ill-suited to iterative reasoning agents. We propose LLM-Wiki, an agent-native retrieval system that operationalizes the Retrieval-as-Reasoning paradigm by treating external knowledge as a compilable, composable, and self-evolving structure rather than a static retrieval index. LLM-Wiki compiles documents into structured Wiki pages with bidirectional links, exposes search, read, and link-following operations through standard tool-calling interfaces, and introduces an Error Book for persistent structural and semantic self-correction. LLM-Wiki achieves state-of-the-art results on HotpotQA, MuSiQue, and 2WikiMultiHopQA, outperforming HippoRAG 2, LightRAG, and GraphRAG by 2.0-8.1 F1 points. On AuthTrace, LLM-Wiki achieves the best overall accuracy, with especially strong gains on multi-document structured queries, confirming that compilation-based retrieval generalizes beyond chain-style multi-hop reasoning.

📄 PDF Abstract BibTeX arXiv:2605.25480

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning

2026-05-16 · Yongfeng Huang, Ruiying Chen, James Cheng arxiv

Retrieval-Augmented Generation (RAG) is widely employed to mitigate risks such as hallucinations and knowledge obsolescence in medical question answering, yet its predominantly single-round, static retrieval paradigm mis…

Question AnsweringAnswer Selection

EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval

2026-07-14 · Jiashi Lin, Changhong Jiang, Xiangru Lin, Ruifei Zhang 외 arxiv

Retrieval-augmented generation (RAG) has emerged as a critical paradigm for grounding Multimodal Large Language Models (MLLMs) in external knowledge. Recent GraphRAG methods introduce structured entity-relation graphs to…

Knowledge Graphs

Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection

2026-06-01 · Sihang Zeng, Matthew Thompson, Ruth Etzioni, Meliha Yetisgen arxiv

Modeling patient trajectories from longitudinal electronic health records (EHRs) requires reasoning over sparse, noisy, and long-context multimodal sequences. Existing LLM-based multi-agent systems address context length…

Multi-agent Reinforcement LearningTrajectory Modeling

DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning

2026-08-01 · An Lanji, Dawei Liu, Jin Li, Haoran Xu 외 arxiv

Tool-integrated vision-language agents have made remarkable progress on compositional and multi-step visual reasoning. Yet their outputs frequently exhibit unfaithfulness: the stated reasoning path diverges from the comp…

Multimodal ReasoningVisual Reasoning

SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language Models

2025-07-17 · Xiangyu Dong, Haoran Zhao, Jiang Gao, Haozhou Li 외

Recent advances in vision-language navigation (VLN) were mainly attributed to emerging large language models (LLMs). These methods exhibited excellent generalization capabilities in instruction understanding and task rea…

Vision-Language Navigation