Red Queen Gödel Machine：智能体与评估器协同进化框架
The Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators
研究者提出 Red Queen Gödel Machine（RQGM），一个在非平稳效用下实现递归自我改进的进化框架，让学习到的评估器与智能体共同进化。在 DeepSWE 上，RQGM 低推理投入下通过 82.1% 的留出任务，优于固定评估器基线的 75.0%，并接近高投入的 GPT-6 Astra。
Authors:Alex Iacob, Andrej Jovanović, William F. Shen, Daniel Burkhardt, Meghdad Kurmanji, Nurbek Tastan, Lorenzo Sani, Niccolò Alberto Elia Venanzi, Jiayi Nie, Ambroise Odonnat, Zeyu Cao, Bill Marino, Xinchi Qiu, Rika Antonova, Nicholas D. Lane
Abstract:Self-improving agents are state-of-the-art on agentic coding benchmarks, yet their search methods assume a stationary evaluation criterion. This ignores a central feature of evolution: species adapt as their environments change with them. We introduce the Red Queen Gödel Machine (RQGM), an evolutionary framework for recursive self-improvement under non-stationary utilities. This allows learned evaluators to improve alongside the agents they guide. On DeepSWE, the RQGM improves over its fixed-evaluator baseline by adding a complementary agent-as-a-judge code-review signal: a co-evolved reviewer grades coder patches to guide search. At low reasoning effort, the RQGM coder passes 82.1% of held-out tasks against the baseline's 75.0%, and nearly matches the GPT-6 Astra model at high effort. In scientific paper writing and reviewing, and Olympiad-level proof writing and grading, co-evolved evaluators provide an evaluation criterion. Anchored to human IMO grades, a co-evolved grader writes its own milestone rubric and exceeds static baselines at a 3x lower search cost, driving the prover to the best mean score. Since the RQGM can modify the search objective across epochs, it can regularize the search. For example, the RQGM reduces self-preference bias via an additional adversarial objective to discover reviewers equally stringent on AI and human work. Guided by these calibrated reviewers, co-evolved writers reach 1.78x-1.86x higher acceptance rates than the baseline under an agent-as-a-judge panel. The RQGM enables self-improving systems where agents and evaluators recursively bootstrap each other beyond static evaluation.
| Comments: | 9 pages main text + 31 pages appendix (40 pages total, incl. references); Preliminary preprint; work in progress. Keywords: self-improving agents, learned evaluation, multi-agent systems, auto-mated scientific discovery, controlled utility evolution, co-evolutionary search, autoresearch |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Neural and Evolutionary Computing (cs.NE) |
| ACM classes: | I.2.6; I.2.8; I.2.11 |
| Cite as: | arXiv:2606.26294 [cs.LG] |
| (or arXiv:2606.26294v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2606.26294 arXiv-issued DOI via DataCite |
Submission history
From: Alex Iacob [view email]
[v1]
Wed, 24 Jun 2026 18:38:26 UTC (1,058 KB)
[v2]
Mon, 29 Jun 2026 17:13:25 UTC (1,116 KB)
[v3]
Thu, 8 Oct 2026 10:42:36 UTC (1,394 KB)
来源：arXiv cs.AI · arxiv.org