← Back to all news
arXiv AI By Yifeng He, Jicheng Wang, Yinzhe Zhao, Chengyang Shi, Jiachen Liu, Hao Chen

The Greatness of Science Cannot Be Planned: Agentic Auto-Research is Fuzz Testing

Read the original on arXiv AI →

The article argues that agentic auto‑research should be guided by dense, intermediate signals of epistemic progress rather than by sparse final benchmarks. It compares this approach to fuzz testing, where coverage provides continuous feedback that directs input mutation. The authors propose controlled experiments to test whether such signals improve discovery efficiency and reduce false positives, and demonstrate in a simulated physics setting that an AI agent using feedback‑driven search uncovers a hidden law while optimization‑driven baselines fail.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Oct 7

EPOCH: Reliable Discovery through Evidence-Governed Search

EPOCH is an evidence‑governed architecture for AI research agents that improves how candidate discoveries are evaluated and validated. By combining explicit task contracts, typed memory, active falsification, admission checks, and independent replay, EPOCH ensures that each candidate is judged against the strength and scope of its claim. The system achieves state‑of‑the‑art performance on several benchmarks, including AlgoTune, Math14, and AgentHPO, and demonstrates significant advances in executable constructions, algorithm optimization, counterexamples, and proof‑supported results across ten discovery problems.

By Binjie Guo, Aisheng Mo, Ruitong Li, Xinle Deng
agentsbenchmarks
More like this →
arXiv Machine Learning
Sep 23

Recursive self-improvement of AI research agents

The paper introduces AIDE^2, an AI research agent that recursively improves its own code by proposing, benchmarking, and selecting modifications. Over an eight‑day autonomous run, it achieved seven successive improvements—including new search policies and memory mechanisms—that transferred to four held‑out benchmarks in machine learning, algorithm engineering, and weather forecasting. The agent’s best version matched or outperformed a top human‑engineered production research agent and also reduced reward‑hacking rates, despite never optimizing for that metric.

By Dhruv Srikanth, Bingchen Zhao, Dixing Xu, Yuxiang Wu, Zhengyao Jiang
agentsbenchmarks
More like this →