Agora把科研寫進Git

Papers arxiv:2609.

18094 Copy markdown Agora: Git as Shared Memory for Collective AutoResearch Published on Sep 16 · Submitted by Yifan Zhang on Sep 17 · NVIDIA Upvote 39 +31 Authors: Yifan Zhang ,Yunheng Zou ,Shaokun Zhang ,Jian Hu ,Hao Zhang ,Binfeng Xu ,Jan Kautz ,Yi Dong Abstract Autonomous research loops such as AutoResearch show that one coding agent can improve a training setup unattended.

Run several of them and each session starts from scratch, so more agents tend to mean more duplicated search rather than more discovery.

Agora is a shared memory for such agents: research is recorded as an append-only directed acyclic graph (DAG) stored in Git, so that every claim is a commit anyone can check out and rerun.

Each result, insight, hypothesis, verification, and report is an immutable commit whose parent edges say what it builds on; a derived index exposes the frontier, the neglected branches, and the verification status of each claim, and a diversity-aware selection rule keeps the community from collapsing onto one leader.

We describe the system and report its first sustained use: a run of nearly 12 days in which 13 language-model workers, with no assigned tasks and no central planner, worked on a weight-transfer problem.Given 141 pretrained donor models and a frozen 119.

6M-parameter attention-SSM hybrid whose dimensions match no donor, the workers had to initialize the target without training data or gradient updates.They published 1,703 contributions and drove the evaluator from 3.39 to 1.899 bits per byte, closing 62% of the gap to a trained GPT-2 124M.

The winning recipe compresses donor next-token statistics into the target's embedding and output head, then adds a short-range context signal through sparse edits to attention, feed-forward, and state-space blocks.

Its 145-commit ancestry spans 15 accounts, and 165 independent reproductions were posted, none of which failed.

We describe the single mid-run human intervention that pulled the community out of a monoculture, what the trace does and does not establish, and the controlled comparison that would settle whether shared research state improves discovery per unit of compute.

View arXiv page View PDF Project page GitHub 19 Add to collection Community yifAI Paper author Paper submitter 1 day ago Agora: Git as Shared Memory for Collective AutoResearch Reply librarian-bot about 4 hours ago This is an automated message from the Librarian Bot.

I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development (2026) Loreley: Repository-Scale Program Evolution with Quality-Diversity Search (2026) Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills (2026) AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement (2026) CrossAudit: A Git-Native, Cross-Vendor Audit Loop for Agentic Science (2026) StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments (2026) Zero-Shot Self-Orchestration with Ledger-Based Control for Improved LLM Coding Performance (2026) Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend Reply EditPreview Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images Comment · Sign up or log in to comment Upvote 39 +27 Get this paper in your agent: hf papers read 2609.18094 Don't have the latest CLI?curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0 No model linking this paper Cite arxiv.org/abs/2609.

18094 in a model README.md to link it from this page.Datasets citing this paper 0 No dataset linking this paper Cite arxiv.org/abs/2609.18094 in a dataset README.md to link it from this page.Spaces citing this paper 0 No Space linking this paper Cite arxiv.org/abs/2609.18094 in a Space README.

md to link it from this page.Collections including this paper 0 No Collection including this paper Add this paper to a collection to link it from this page.