多個智能體靠共享Git倉庫累積推理成果

Computer Science > Artificial Intelligence arXiv:2610.

04862 (cs) [Submitted on 4 Oct 2026] Title:GitSwarm: Decentralized Compounding Inference Authors:Vedant Shah, Ankur Samanta, Paras Dahal, Mikhail Plekhanov, Carole-Jean Wu, Scott Yih, Remi Munos, Rob Fergus, Jakob Foerster, Ruslan Salakhutdinov, Sanjeev Arora, Jason Weston, Aaron Courville, Anirudh Goyal View a PDF of the paper titled GitSwarm: Decentralized Compounding Inference, by Vedant Shah and 13 other authors View PDF HTML (experimental) Abstract:Long-horizon problem solving and scientific research require computation to accumulate across successive attempts.

Partial solutions, experimental findings, and unsuccessful approaches can inform later work, yet most inference-time computation is organized around individual trajectories or candidates rather than a persistent body of reusable work.

We call this paradigm compounding inference: organizing inference-time computation so that intermediate work persists and can be inspected, extended, combined, or challenged by subsequent computation.

We instantiate compounding inference in GitSwarm, an asynchronous system where homogeneous agents independently decide how to advance a task while collaborating through structured persistent memory.

Agents explore, experiment, verify, refine, and synthesize previous work in a shared, branch-able Git repository.Atomic commits preserve intermediate artifacts, while explicit semantic dependencies record how later contributions build on work across branches.

We evaluate GitSwarm on long-horizon problem solving and sustained GPU-backed experimental research.On IMOProofBench-Advanced, GitSwarm solves all 30 problems in one run using GPT-5.5.On ProgramBench, it achieves a $79.4\%$ mean score, versus $65.

1\%$ for the strongest reported baseline under the stated budget.On three neural architecture research tasks (Residual Matrix Transformer, Looped Transformer, NanoChat), GitSwarm improves upon the starting architectures through successive experimentation.

Beyond final performance, we measure whether computation accumulates: on ProgramBench, $94.7\%$ of contributions are subsequently built upon, while the selected solution's ancestry covers $82-93\%$ of the contribution graph.

These results show that inference-time computation can accumulate across otherwise independent episodes, forming an evolving body of work that subsequent inference can reuse.Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2610.04862 [cs.AI] (or arXiv:2610.

04862v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2610.

04862 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Vedant Shah [view email] [v1] Sun, 4 Oct 2026 02:03:24 UTC (1,298 KB) Full-text links: Access Paper: View a PDF of the paper titled GitSwarm: Decentralized Compounding Inference, by Vedant Shah and 13 other authorsView PDFHTML (experimental)TeX Source view license Current browse context: cs.

AI < prev | next > new | recent | 2026-10 Change to browse by: cs cs.LG References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading...BibTeX formatted citation × loading...

Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.

ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?

) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.

AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?

) Author Venue Institution Topic About arXivLabs 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.Which authors of this paper are endorsers?| Disable MathJax (What is MathJax?)