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

Source: https://huggingface.co/papers/2605.10813 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

NanoResearch is a multi-agent framework that enhances research automation through personalized assistance by accumulating reusable skills, maintaining user-specific experience, and internalizing implicit preferences through co-evolving components.

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, makingpersonalizationa precondition forresearch automationto be genuinely usable. However, achieving it requires three capabilities that current systems lack: accumulating reusableprocedural knowledgeacross projects, retaininguser-specific experienceacross sessions, and internalizingimplicit preferencesthat resist explicit formalization. We propose NanoResearch, amulti-agent frameworkthat addresses these gaps through tri-levelco-evolution. Askill bankdistills recurring operations into compact procedural rules reusable across projects. Amemory modulemaintains user- and project-specific experience that grounds planning decisions in each user’s research history. Alabel-free policy learningconverts 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.

View arXiv pageView PDFGitHub910Add to collection

Get this paper in your agent:

hf papers read 2605\.10813

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.10813 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.10813 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.10813 in a Space README.md to link it from this page.

Collections including this paper1