AutoResearch runs ML research from idea to paper with cross-model review
EvoMap's AutoResearch is an Apache-2.0 agent pipeline that discovers ML research ideas from recent papers, runs experiments, records the evidence, and requires at least three distinct models during idea generation so one model never approves its own work.
Image: GitHub
Why it mattersResearch groups that let one model both propose and review its own experiments now have an open pipeline that separates the two roles, persists every run to disk, and preserves negative results instead of forcing every experiment into a success.
EvoMap published AutoResearch on GitHub, an open-source agent workflow that runs the full loop from an ML research idea to a package of experiment code, logs, metrics, critic reports and blind reviews. The repository was created on 15 August 2026, was last pushed on 1 September, and has reached 1,362 stars and 91 forks. It is Apache-2.0 licensed. A named team of six researchers is listed as the authors, including project leaders Haoyang Zhang and Junjie Wang from the Infinite Evolution Lab at EvoMap, and the README links to an arXiv preprint at 2608.17906.
What it runs
The pipeline takes one of three entry points. Give it a research idea and it plans the experiment, writes code, executes runs, analyses results, and produces an independent review. Ask it to discover directions and it collects recent papers, developer discussions and open-source trends, filters them, and generates candidate ideas with experiment plans. Ask for the full workflow and it does both. Every stage writes to disk: research plans, code, run logs, metrics, failure causes, critic reports and blind reviews are all saved in named directories under data/, so a run can be inspected, taken over by a human, or resumed after an interruption.
At least three models
The core design rule is that idea generation and critic stages require at least three distinct model identities, counted by underlying model rather than by endpoint. The README states it as a hard independence requirement: the preflight script fails if the configured providers do not offer enough distinct models for the multi-model stages. This is the mechanism against one model both proposing an idea and reviewing it favourably. The Idea Forge stage is where the three-way check runs, and the list of models is declared in config/providers.local.json rather than hard-coded to Gemini, GPT or Claude.
How failed results are kept
The capability table points out one design choice. AutoResearch preserves evidence and stops when a hypothesis fails, rather than continuing to search for a framing that turns the run into a success. Failed runs stay in data/experiments/ with their logs and metrics, and the blind-review outputs treat a negative result as a finished record rather than a task to fix. Pilot runs test feasibility at lower cost before a full experiment starts, so a plan can be dropped before it spends a large model budget.
For a team running ML experiments with a coding agent, the workflow makes two things concrete that are usually informal. First, the separation of proposer and reviewer becomes a preflight check that has to pass. Second, the record on disk is the primary artefact, so a later reader can trace a claim back to the run that produced it. The trade-off is a Linux machine with Python 3.10 or newer, multiple provider credentials, and a real API budget for the multi-model stages. The value is that idea generation and experiment execution become inspectable rather than hidden inside a single conversation.
Source
EvoMap/AutoResearch on GitHub and the arXiv preprint at 2608.17906
This item was written by an AI system from the linked source. Reveneau is responsible for what it publishes.
Get AI News in your inbox
New developer tools, model and agent releases, and how teams are actually using them to release software. Short, and only when there is something worth reading.
