mlsanityData to 7 Oct 2026

Self-evolving search agents

23 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: search, retrieval, self-evolving, knowledge, search agents

Key facts. Self-evolving search agents: 23 papers on arXiv since 2024 (data through 7 Oct 2026). 4 of its 23 mapped papers (17%) cite “EvolveSearch: An Iterative Self-Evolving Search Agent” (2025, arXiv 2505.22501). 2 of its 23 mapped papers (9%) cite “Dr. Zero: Self-Evolving Search Agents without Training Data” (2026, arXiv 2601.07055). 3 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

3 new since 17 Sep

  1. Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation also fits: Self-evolving LLM agents
  2. GraphCert: Bootstrap Agentic Graph Reasoning with Certified Evidence Rubrics also fits: Synthetic reasoning data and bootstrapping
  3. Self-Evolving Search Index

Foundations

Most cited by papers here

  1. EvolveSearch: An Iterative Self-Evolving Search Agent2025cited by 4 here
  2. Dr. Zero: Self-Evolving Search Agents without Training Data2026cited by 2 here
  3. Repurposing Synthetic Data for Fine-grained Search Agent Supervision2025cited by 1 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 1 here
  2. 2023Reinforced Self-Training (ReST) for Language Modelingcited by 1 here
  3. 2023Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Modelscited by 1 here
  4. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 4 here
  5. 2024Self-Rewarding Language Modelscited by 2 here
  6. 2024Self-Play Preference Optimization for Language Model Alignmentcited by 1 here
  7. 2026Dr. Zero: Self-Evolving Search Agents without Training Datacited by 2 here
17 more it builds on, not in this chain
  1. 2022Large Language Models Can Self-Improvecited by 2 here
  2. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 1 here
  3. 2023Does Synthetic Data Generation of LLMs Help Clinical Text Mining?cited by 1 here
  4. 2023ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agentcited by 1 here
  5. 2024Self-playing Adversarial Language Game Enhances LLM Reasoningcited by 1 here
  6. 2024Large Language Models Can Self-Improve At Web Agent Taskscited by 1 here
  7. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 2 here
  8. 2024Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judgecited by 1 here
  9. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Datacited by 3 here
  10. 2025EvolveSearch: An Iterative Self-Evolving Search Agentcited by 4 here
  11. 2025SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learningcited by 1 here
  12. 2025R-Zero: Self-Evolving Reasoning LLM from Zero Datacited by 3 here
  13. 2025A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systemscited by 1 here
  14. 2025Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVRcited by 1 here
  15. 2025WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learningcited by 2 here
  16. 2025EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecyclecited by 2 here
  17. 2025Search Self-play: Pushing the Frontier of Agent Capability without Supervisioncited by 3 here

The 24 most cited of 34.

Browse

20 of 23, ranked 6–25

  1. 4RAGShaper: Eliciting Sophisticated Agentic RAG Skills via Automated Data Synthesis20260
  2. 5SE-Search: Self-Evolving Search Agent via Memory and Dense Reward20260
  3. 6A Dynamic Self-Evolving Extraction System20260
  4. 7ROZA Graphs: Self-Improving Near-Deterministic RAG through Evidence-Centric Feedback20260
  5. 8Knowledge-Graph Paths as Intermediate Supervision for Self-Evolving Search Agents20260
  6. 9SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory20260
  7. 10EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents20260
  8. 11Towards Recursive Self-Evolving Agentic Literature Retrieval20260
  9. 12Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki20260
  10. 13PhotoCraft: Agentic Reasoning with Hierarchical Self-Evolving Memory for Deep Image Search20260
All 20
  1. 14BEATS: Bootstrapping E-commerce Attribute Taxonomies for Search through Iterative Human-AI Collaboration20260
  2. 15When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval20260
  3. 16EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval20260
  4. 17LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning20260
  5. 18SearchMaster: Grounded and Regulated Self-Play for Search Agents20260
  6. 19CoEvoKG: Co-Evolving Knowledge Graphs with Self-Evolving Search Agents20260
  7. 20BizSage: A Self-Evolving Multi-Agent Framework for Business Research with Efficient Knowledge Retrieval20260
  8. 21Language Models can Self-Improve at State-Value Estimation for Better Search20250
  9. 22SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs20250
  10. 23Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance20240