一次反思不够：通过多假设失败归因进行自我修正的自主研究
One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution
AI总结：
提出SAGE框架，通过多假设失败归因（MHFA）机制将实验失败恢复转化为结构化因果诊断，显著提升自主研究代理的可靠性和产出质量。
摘要：
自主研究代理现在可以起草假设、编写代码、运行实验并生成论文，但当实验失败时，它们仍然脆弱。在主流范式下，失败恢复通常委托给单一的自由形式反思：将丰富的指标、日志和设计选择轨迹压缩成一份口头批评，这往往导致局部试错或硬性转向，丢弃有用的上下文。我们提出SAGE，一个自我修正、自主、基于经验的实验者，以解决这一失败恢复瓶颈。其核心机制——多假设失败归因（MHFA）——将恢复视为结构化的因果诊断。通过分析动态轨迹特征，MHFA系统性地生成多个基于证据的失败解释，独立评估其严重性，并将验证后的根本原因确定性地路由到正确的干预级别（假设、实验设计或实现）。为保证科学诚实性，SAGE进一步采用基于经验的报告机制，明确将草拟结果约束为实际测量值，修正幻觉数字。在12个主题、5个领域的基准测试中，SAGE将包含指标的输出从42%提升到92%，工件质量从5.00/10提升到6.75/10，并盲评超过AI-Scientist-v2（52.0 vs. 48.2），增益集中在代码开发和执行方面。尽管完全自主的科学写作和生成会议级论文对整个领域来说仍然是臭名昭著的困难开放问题，但SAGE成功生成了显著更可靠和更高质量的科学工件。最终，通过将结构化恢复与显式基础约束相结合，SAGE显著优于单一反思范式，为未来的自主研究建立了高度可信的基础。
英文摘要：
Autonomous research agents can now draft hypotheses, write code, run experiments, and produce papers, but they remain brittle when experiments fail. Under the prevailing paradigm, failure recovery is usually delegated to a single free-form reflection: a rich trajectory of metrics, logs, and design choices is compressed into one verbal critique, which often leads either to localized trial-and-error or to hard pivots that discard useful context. We propose SAGE, a Self-correcting, Autonomous, Grounded Experimenter, to tackle this failure-recovery bottleneck. Its core mechanism, Multi-Hypothesis Failure Attribution (MHFA), treats recovery as a structured causal diagnosis. By analyzing dynamic trajectory features, MHFA systematically generates multiple evidence-grounded explanations for a failure, independently evaluates their severity, and deterministically routes the verified root cause to the correct intervention level (hypothesis, experimental design, or implementation). To guarantee scientific honesty, SAGE further employs a grounded reporting mechanism that explicitly constrains drafted results to actual measured values, redacting hallucinated numbers. On a 12-topic, 5-domain benchmark, SAGE increases metrics-bearing outputs from 42% to 92% over a reflection baseline, improves artifact quality from 5.00 to 6.75/10, and blindly outscores AI-Scientist-v2 (52.0 vs. 48.2), with gains concentrated in code development and execution. While fully autonomous scientific writing and generating conference-ready papers remain notoriously difficult open problems for the entire field, SAGE successfully produces significantly more reliable and higher-quality scientific artifacts. Ultimately, by coupling structured recovery with explicit grounding constraints, SAGE significantly outperforms monolithic reflection paradigms, establishing a highly trustworthy foundation for future autonomous research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
