---
title: "Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents"
slug: fork-and-flush-escaping-idea-basins-in-autoresearch-agents
url: https://listedarticles.com/articles/fork-and-flush-escaping-idea-basins-in-autoresearch-agents
canonical_url: https://arxiv.org/abs/2610.07447
content_type: research
language: en
published_at: 2026-10-05T00:00:00.000Z
updated_at: 2026-10-14T08:17:56.211Z
author: "Ziyang Cai et al."
authored_by: human
publisher: "arXiv"
publisher_url: https://arxiv.org/
topics: ["AI Agents", "Research", "Machine Learning", "LLMs"]
license: all-rights-reserved
word_count: 400
reading_minutes: 2
citation: "Ziyang Cai et al., arXiv. \"Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents.\" 5 Oct 2026. https://arxiv.org/abs/2610.07447 (all-rights-reserved)"
# The full text follows. The web page shows an extract and sends readers
# to the source above; quote the citation and link the canonical URL.
---

# Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents

> Microsoft Research paper on idea basins in long-horizon autoresearch agents, and a periodic fork-and-flush intervention that keeps the workspace but resets chat context—reporting +66% vs single-run under equal compute across 13 tasks.

# Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents

**Authors:** Ziyang Cai, Christos Ziakas, Vasilis Kontonis, Tim Pearce, Siddhartha Sen, Akshay Krishnamurthy, Shivam Garg, Dimitris Papailiopoulos

**arXiv:** [2610.07447](https://arxiv.org/abs/2610.07447) · [PDF](https://arxiv.org/pdf/2610.07447) · [HTML](https://arxiv.org/html/2610.07447)

Submitted 5 Oct 2026.

## Abstract

Autoresearch agents tackle open-ended problems by repeatedly proposing candidate solutions, evaluating them, and using feedback to guide subsequent experiments. We show that independent runs of the same agent on the same task often plateau at substantially different scores, with gaps that persist even after considerable additional compute. Embedding their candidate artifacts by functional similarity provides further evidence that trajectories remain in localized regions of the solution space, which we call idea basins. To help agents escape these basins, we study a simple periodic intervention, fork-and-flush. Our method forks the agent into parallel trajectories, each inheriting the accumulated workspace but starting with a fresh chat context. After running each trajectory for a fixed horizon, the agent continues from the highest-scoring one. Across 13 long-horizon research and engineering tasks, with individual agent runs lasting up to several days, fork-and-flush outperformed the single-run and best-of-N baselines by a relative improvement of 66.0% and 44.4%, respectively, on the min-max normalized average score under an equal compute budget.
    

### Additional Features

### References & Citations

    
    Loading...

# Bibliographic and Citation Tools

            Bibliographic Explorer 

        *(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))
            Connected Papers 

        *(*[What is Connected Papers?](https://www.connectedpapers.com/about))
            Litmaps 

        *(*[What is Litmaps?](https://www.litmaps.co/))
            scite Smart Citations 

        *(*[What are Smart Citations?](https://www.scite.ai/))
# Code, Data and Media Associated with this Article

            alphaXiv 

        *(*[What is alphaXiv?](https://alphaxiv.org/))
            CatalyzeX Code Finder for Papers 

        *(*[What is CatalyzeX?](https://www.catalyzex.com))
            DagsHub 

        *(*[What is DagsHub?](https://dagshub.com/))
            Gotit.pub 

        *(*[What is GotitPub?](http://gotit.pub/faq))
            Hugging Face 

        *(*[What is Huggingface?](https://huggingface.co/huggingface))
            ScienceCast 

        *(*[What is ScienceCast?](https://sciencecast.org/welcome))
# Demos

# Recommenders and Search Tools

              Influence Flower 

          *(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))
              CORE Recommender 

          *(*[What is CORE?](https://core.ac.uk/services/recommender))
              IArxiv Recommender
              

          *(*[What is IArxiv?](https://iarxiv.org/about))
# arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).