NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation

• URL: http://arxiv.org/abs/2605.10813v2
• Date: Fri, 15 May 2026 13:23:05 GMT
• Title: NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
• Abstract summary: LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper writing, but a fundamental question remains: automation for whom?<n>We propose NanoResearch, a multi-agent framework that addresses these gaps through tri-level co-evolution.<n>A skill bank distills recurring operations into compact procedural rules reusable across projects.<n>A memory module maintains user- and project-specific experience that grounds planning decisions in each user's research history.<n>A label-free policy learning converts free-form feedback into persistent parameter updates of the planner, reshaping subsequent coordination.
• Score: 59.19858972597063
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper writing, but a fundamental question remains: automation for whom? Researchers operate under different resource configurations, hold different methodological preferences, and target different output formats. A system that produces uniform outputs regardless of these differences will systematically under-serve every individual user, making personalization a precondition for research automation to be genuinely usable. However, achieving it requires three capabilities that current systems lack: accumulating reusable procedural knowledge across projects, retaining user-specific experience across sessions, and internalizing implicit preferences that resist explicit formalization. We propose NanoResearch, a multi-agent framework that addresses these gaps through tri-level co-evolution. A skill bank distills recurring operations into compact procedural rules reusable across projects. A memory module maintains user- and project-specific experience that grounds planning decisions in each user's research history. A label-free policy learning converts free-form feedback into persistent parameter updates of the planner, reshaping subsequent coordination. These three layers co-evolve: reliable skills produce richer memory, richer memory informs better planning, and preference internalization continuously realigns the loop to each user. Extensive experiments demonstrate that NanoResearch delivers substantial gains over state-of-the-art AI research systems, and progressively refines itself to produce better research at lower cost over successive cycles.

Related papers

• AutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems [7.383658399787325]
  In textbfDASHEN, NetEase's gaming-community app, engineers identify promising directions from research papers, technical reports, and prior production experiments.<n> Promising candidates are then advanced to online A/B tests, and those demonstrating robust gains are submitted to Launch Review.<n>We present textbfAutoLR, initially built as textbfAuto Launch Review and later extended upstream into an autonomous research-to-launch harness.
  arXiv  Detail & Related papers  (2026-09-04T08:30:36Z)
• DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning [58.09293442211248]
  Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks.<n>This report presents DuMate-DeepResearch, a multi-agent DR framework built on the Qianfan Agent Foundry.
  arXiv  Detail & Related papers  (2026-06-05T14:10:48Z)
• AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle [24.50819107720795]
  AutoSci is a memory-centric agentic system for the full scientific research lifecycle.<n>It is organized around four modules: SciMem, SciFlow, SciDAG, and SciEvolve.
  arXiv  Detail & Related papers  (2026-05-29T16:00:04Z)
• AI for Auto-Research: Roadmap & User Guide [107.0834449839233]
  We present an end-to-end analysis of AI across the complete research lifecycle.<n>We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy.<n>We show that greater automation can obscure rather than eliminate failure modes.
  arXiv  Detail & Related papers  (2026-05-18T17:08:26Z)
• AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery [49.77172027295716]
  AutoSOTA is an end-to-end automated research system that advances the latest State-Of-The-Art (SOTA) models published in top-tier AI papers.<n>It successfully discovers 105 new SOTA models that surpass the original reported methods, averaging approximately five hours per paper.
  arXiv  Detail & Related papers  (2026-04-07T07:52:01Z)
• Improving Coherence and Persistence in Agentic AI for System Optimization [9.443037059325086]
  Engram organizes exploration into a sequence of agents that iteratively design, test, and analyze mechanisms.<n>We find that Engram exhibits superior performance across diverse domains including multi-cloud multicast inference, LLM request routing, and optimizing KV cache reuse in databases with natural language queries.
  arXiv  Detail & Related papers  (2026-03-22T17:04:50Z)
• REVERE: Reflective Evolving Research Engineer for Scientific Workflows [44.36828076189902]
  Existing prompt-optimization techniques rely on local signals to update behavior, often broader and recurring patterns across tasks, leading to poor generalization.<n>We introduce Reflective Evolving Research Engineer (REVERE), a framework that continuously learns from Global Training Context.<n>REVERE, via this reflective optimization framework, improves performance over prior state-of-the-art expert-crafted instructions on research coding tasks by 4.50% on SUPER, 3.51% on ResearchCodeBench, and 4.89% on ScienceAgentBench.
  arXiv  Detail & Related papers  (2026-03-21T05:58:30Z)
• SelfAI: Building a Self-Training AI System with LLM Agents [79.10991818561907]
  SelfAI is a general multi-agent platform that combines a User Agent for translating high-level research objectives into standardized experimental configurations.<n>An Experiment Manager orchestrates parallel, fault-tolerant training across heterogeneous hardware while maintaining a structured knowledge base for continuous feedback.<n>Across regression, computer vision, scientific computing, medical imaging, and drug discovery benchmarks, SelfAI consistently achieves strong performance and reduces redundant trials.
  arXiv  Detail & Related papers  (2025-11-29T09:18:39Z)
• Interpretable by Design: Query-Specific Neural Modules for Explainable Reinforcement Learning [0.3655021726150367]
  We architect RL systems as inference engines that can answer diverse queries about their environment.<n>We introduce Query Conditioned Deterministic Inference Networks (QDIN), a unified architecture that treats different types of queries as first-class citizens.<n>Our key empirical finding reveals a fundamental decoupling: inference accuracy can reach near-perfect levels even when control performance remains suboptimal.
  arXiv  Detail & Related papers  (2025-11-11T20:08:32Z)
• Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization [56.674356045200696]
  We propose a novel method to train AI agents to incorporate knowledge and skills for multiple tasks without the need for cumbersome note systems or prior high-quality demonstration data.<n>Our approach employs an iterative process where the agent collects new experiences, receives corrective feedback from humans in the form of hints, and integrates this feedback into its weights.<n>We demonstrate the efficacy of our approach by implementing it in a Llama-3-based agent that, after only a few rounds of feedback, outperforms advanced models GPT-4o and DeepSeek-V3 in tasksets.
  arXiv  Detail & Related papers  (2025-02-03T17:45:46Z)
• BEACON: A Bayesian Optimization Strategy for Novelty Search in Expensive Black-Box Systems [1.204357447396532]
  Novelty search (NS) seeks to uncover diverse system behaviors through simulations or experiments.<n>NS methods typically rely on evolutionary strategies and other meta-heuristics that require dense sampling of the input space.<n>We introduce BEACON, a sample-efficient, Bayesian optimization-inspired approach to NS that is tailored for settings where the input-to-behavior relationship is opaque and costly to evaluate.
  arXiv  Detail & Related papers  (2024-06-05T20:23:52Z)
• Towards Automated Design of Riboswitches [38.46798525594529]
  Experimental screening and selection pipelines for the discovery of novel riboswitches are expensive, time-consuming, and inefficient. We present a new method, libLEARNA, capable of providing RNA focus libraries of diverse variable-length qualified candidates.
  arXiv  Detail & Related papers  (2023-07-17T19:34:59Z)
• Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration [71.95914457415624]
  Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. We propose an alternative formulation that leverages Multi-Agent RL (MARL) to tackle this problem. Our evaluation shows that the MARL formulation consistently outperforms single-agent RL baselines.
  arXiv  Detail & Related papers  (2022-11-29T17:10:24Z)

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.