An AI Scientist that Doesn't Drift: Taste, Structure, and Falsifiable Findings in a Quadruped Navigation Research Loop

Computer Science > Artificial Intelligence [Submitted on 30 Jul 2026] An AI Scientist that Doesn't Drift: Taste, Structure, and Falsifiable Findings in a Quadruped Navigation Research Loop Yiwen Zhang, Eloise Zeng, Jaeha Lee, Tony Yue Yu Autonomous research loops driven by large language models can run machine-learning experiments at scale but tend to drift toward local refinements of whichever metric they optimise rather than testing the hypotheses that motivate the experiments. We address this structurally and present an AI Scientist for studying generalisation in quadruped robot navigation policies in simulation. Building on the autoresearch paradigm of Karpathy, our loop adds three components: an immutable experiment card that pairs each iteration's prediction with its outcome under a fixed schema, so a falsified hypothesis cannot be retconned; specialised subagents restricted to mechanical roles; and kkanbu, a preference oracle that holds the user's research taste as a typed knowledge graph and is the only component permitted to make subjective judgements. To isolate the oracle we run the identical loop twice across eleven research streams, with and without kkanbu. Neither arm drifts: both falsify roughly three quarters of their own hypotheses, and the best trained policy comes from the oracle-less arm. What the oracle changes is direction, not score: it alone explores test-time adaptation, it authored the winning designs where its arm led, and it carried lessons across streams that the other arm repeatedly re-derived. The scaffold keeps the loop honest; kkanbu decides where it looks. Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Robotics (cs.RO) Cite as: arXiv:2608.07542 [cs.AI]   (or arXiv:2608.07542v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2608.07542 Focus to learn more Submission history From: Tony Yue Yu [view email] [v1] Thu, 30 Jul 2026 21:07:15 UTC (214 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-08 Change to browse by: cs cs.LG cs.MA cs.RO References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation 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 Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)