| title | DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck |
|---|---|
| authors | Shubham Agarwal, Akshat Gupta, Mike Heddes, Dilara Soylu, Rui Meng, Patrick Tser Jern Kon, Jiefeng Chen, Mert Cemri, Shu Liu, Abe Gonzalez, Akanksha Jain, Bhavana Dalvi Mishra, Linfeng Song, Vilobh Meshram, Xiangru Tang, Jinsung Yoon, Aditya Parameswaran, Ion Stoica, Vahab Mirrokni, Burak Gokturk, Parthasarathy Ranganathan, Tomas Pfister, Nanyun Peng, Chun-Liang Li |
| date | 2026-10-12 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.17184 |
| affiliation | |
| upvotes | 16 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Evaluation has been central to advances in AI, and it is equally critical to autonomous discovery. Yet scaling autonomous discovery to real-world engineering challenges faces a fundamental bottleneck: the cost of evaluating progress. In real settings, a single true evaluation, such as a full benchmark or serving trace, can take hours, so a search can afford only a handful of true evaluations. We present DuoDiscover, a search system that jointly discovers what to optimize and how to evaluate progress efficiently, through three mechanisms. First, each worker in a fleet of coding agents co-discovers an optimization target and a fast, tailored proxy evaluator, which we call a yardstick. The agent then hill-climbs the yardstick rather than the true evaluation. Second, since search can exploit gaps between a yardstick and the true objective, fidelity tests continually recheck each yardstick's ranking and invalidate any that drift. Third, the fleet is bottom-up, with no central decomposition of the problem. A lightweight orchestrator spawns and terminates agents, briefs running ones, and seeds new agents with others' confirmed work. DuoDiscover enables autonomous optimization from software to chip architecture. We demonstrate DuoDiscover on two repository-level benchmarks and four GPU and TPU kernel suites covering hundreds of kernels. On SWE-fficiency, it doubles the average speedup of human experts. On SOL-Exec, it ranks first on 121 of 235 kernels and in the top three on 212. On the heavily optimized vLLM and SQLite engines, DuoDiscover achieves 1.92times and 1.38times gains over the base code. On a CPU microarchitecture optimization task with evaluations of up to 28 hours, DuoDiscover surpasses both AlphaEvolve-based ArchAgent v2 and the best human design, with 1.65times ArchAgent v2's gain in 16.7 days versus more than 40 days, advancing the frontier of autonomous chip design. |
cite
@misc{agarwal2026duodiscover,
title={DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck},
author={Shubham Agarwal and Akshat Gupta and Mike Heddes and Dilara Soylu and Rui Meng and Patrick Tser Jern Kon and Jiefeng Chen and Mert Cemri and Shu Liu and Abe Gonzalez and Akanksha Jain and Bhavana Dalvi Mishra and Linfeng Song and Vilobh Meshram and Xiangru Tang and Jinsung Yoon and Aditya Parameswaran and Ion Stoica and Vahab Mirrokni and Burak Gokturk and Parthasarathy Ranganathan and Tomas Pfister and Nanyun Peng and Chun-Liang Li},
year={2026},
eprint={2610.17184},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.17184}
}