AI 中文总结
该研究提出自主研究智能体的“生成-排序”范式存在反馈稀疏性问题，类比灰盒模糊测试，指出自动研究需具备密集进展信号与反馈导向搜索能力，强调反馈架构是自动研究的核心瓶颈。
AI 中文摘要
自主研究智能体生成实验的速度快于研究人员验证这些实验的速度，研究人员的应对方式是扩展提议者的规模，并通过学习到的评判器或人工评审对更多样本进行排序。我们认为，这种“生成-排序”范式忽略了反馈稀疏性的问题。在已明确的研究问题范围内，智能体遵循灰盒模糊测试器（greybox fuzzer）的控制循环：它提出一个候选方案，执行该方案，观察反馈，并选择下一步尝试的内容。模糊测试器很少能发现漏洞，但每次执行时覆盖率都能让部分进展变得可观测，随后模糊测试器会利用该信号对输入进行变异并分配资源，而非仅对已完成的运行进行排序。自动研究需要具备相同的两项能力：第一，在最终科学验证可用之前，每个实验应能暴露一种廉价、密集的认知进展信号；第二，该信号应决定下一次干预，使智能体进行搜索而非重复采样。由于优化后的进展信号是指导而非裁决，最终验证仍需使用免受自适应复用的证据来判定什么算作发现。我们提议开展受控测试，以验证候选信号是否能预测已验证的进展、反馈导向的搜索是否比重复采样在单位成本下产生更多已验证的发现，以及受保护的验证是否能减少虚假发现。反馈架构（feedback architecture）与生成同样是自动研究的核心瓶颈。
英文摘要
Agentic auto-research is emerging, but most systems treat scientific discovery as goal-oriented optimization against a final benchmark. This paradigm rewards a sparse final verdict and ignores the exploration that precedes it. When agents optimize only the final score, they overfit to the test conditions and sample blindly rather than search. Within a declared research problem, a research agent and a greybox fuzzer for software analysis face the same sparse feedback. A fuzzer rarely finds a bug directly, but coverage makes partial progress observable on every execution. Fuzzers use that dense signal to mutate inputs and allocate effort, rather than merely rank completed runs. Auto-research needs the same two capabilities. First, each experiment must expose a cheap, dense signal of epistemic progress before final scientific validation is available. Second, that signal must determine the next intervention so the agent searches rather than repeatedly samples. Because the progress signal provides guidance rather than a final verdict, final validation must still evaluate claims using evidence protected from adaptive reuse. We propose controlled tests to determine whether candidate signals predict validated progress, whether feedback-directed search yields more validated discoveries per unit cost than repeated sampling, and whether protected validation reduces false discoveries. In a simulated physics environment, an AI research agent that tracks its intermediate epistemic progress discovers a hidden physical law. Optimization-driven baselines fail because they repeatedly sample and overfit to their existing data instead of probing unfamiliar regimes. Feedback architecture, not generation capacity, is the central bottleneck in auto-research.
