Paper 2605.03042
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
- Published
- May 2026
- Research lab
- Independent
- Citations
- 9
- GitHub
- 14K stars
01 In brief
Summary
ARIS is an open-source research harness for autonomous ML research, built on the assumption that single-agent long-horizon tasks are unreliable.
It uses cross-model adversarial collaboration: an executor model (e.g., Claude) drives progress while a reviewer from a different model family (e.g., GPT-5.4) critiques artifacts and requests revisions.
The system has three layers: execution (65+ Markdown skills, research wiki, deterministic figure generation), orchestration (five workflows: idea discovery, experiment bridge, auto-review loop, paper writing, rebuttal), and assurance (three-stage evidence-to-claim audit, five-pass editing, proof checking, visual PDF review, citation audit).
A prototype meta-optimization loop proposes harness improvements, gated by reviewer approval.
Deployment includes 3 tested executor platforms, 6+ reviewer models, and 30+ community skills.
An overnight run improved a paper's review score from 5.0 to 7.5/10 over four rounds.
Limitations include no correctness guarantee, audit gaps, reviewer bias amplification, and security concerns with repository-level review.
Future work includes controlled benchmarks and local reviewer models.
The report is observational, not causal evidence of superiority over other systems.
02 From the paper
Abstract
This report describes ARIS (Auto-Research-in-sleep), an open-source research harness for autonomous research, including its architecture, assurance mechanisms, and early deployment experience. The performance of agent systems built on LLMs depends on both the model weights and the harness around them, which governs what information to store, retrieve, and present to the model. For long-horizon research workflows, the central failure mode is not a visible breakdown but a plausible unsupported success: a long-running agent can produce claims whose evidential support is incomplete, misreported, or silently inherited from the executor's framing. Therefore, we present ARIS as a research harness that coordinates machine-learning research workflows through cross-model adversarial collaboration as a default configuration: an executor model drives forward progress while a reviewer from a different model family is recommended to critique intermediate artifacts and request revisions. ARIS has three architectural layers. The execution layer provides more than 65 reusable Markdown-defined skills, model integrations via MCP, a persistent research wiki for iterative reuse of prior findings, and deterministic figure generation. The orchestration layer coordinates five end-to-end workflows with adjustable effort settings and configurable routing to reviewer models. The assurance layer includes a three-stage process for checking whether experimental claims are supported by evidence: integrity verification, result-to-claim mapping, and claim auditing that cross-checks manuscript statements against the claim ledger and raw evidence, as well as a five-pass scientific-editing pipeline, mathematical-proof checks, and visual inspection of the rendered PDF. A prototype self-improvement loop records research traces and proposes harness improvements that are adopted only after reviewer approval.