analiza aiqbench
This paper introduces AutoSciRub, a framework that enhances autonomous scientific agents by generating executable rubrics before task execution to ensure rigorous evaluation. By decomposing underspecified instructions into verifiable criteria, the system significantly improves performance on research benchmarks while reducing methodological errors. This approach represents a critical advancement in aligning AI agents with the strict evidential standards required for genuine scientific discovery.
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
arXiv:2608.31076v1 Announce Type: cross Abstract: Autonomous scientific research agents are increasingly applied to end-to-end scientific workflows, including literature review, data analysis, experimentation, and report generation. However, open-ended research tasks often do not clearly specify the analyses, methods, and success criteria required to complete the task. As a result, agents may miss important analyses, use inappropriate methods, or draw conclusions that are insufficiently supported by evidence. To address the problem, we present AutoSciRub, an evaluation-first framework that induces a task-specific executable rubric before research execution, and uses it to guide execution, criterion-level verification as well as iterative revision. AutoSciRub decomposes an underspecified instruction into atomic scientific goals, grounds them in relevant literature and task-visible data, and synthesizes specific, actionable, and verifiable criteria. The resulting rubric makes implicit experimental and evidential requirements explicit, providing guidance for experiments and analyses. During revision, rubric-guided verification identifies unmet criteria and enables targeted refinement of the research report and its supporting artifacts. On ResearchClawBench, AutoSciRub consistently improves all tested configurations, with an average gain of 2.08 points across three backbone LLMs under the fixed Codex harness and 2.95 points across three agent harnesses using a fixed DeepSeek-V4-Flash backbone. On a randomly sampled 20-task subset of AstaBench E2E Discovery, AutoSciRub further achieves an average improvement of 16.8 points across three agent harnesses, while maintaining or increasing the number of successfully completed tasks. These results demonstrate that evaluation-first guidance provides an effective and generalizable control mechanism for autonomous scientific research (Code: https://github.com/zjunlp/AutoSciRub).
Abstract:Autonomous scientific research agents are increasingly applied to end-to-end scientific workflows, including literature review, data analysis, experimentation, and report generation. However, open-ended research tasks often do not clearly specify the analyses, methods, and success criteria required to complete the task. As a result, agents may miss important analyses, use inappropriate methods, or draw conclusions that are insufficiently supported by evidence. To address the problem, we present AutoSciRub, an evaluation-first framework that induces a task-specific executable rubric before research execution, and uses it to guide execution, criterion-level verification as well as iterative revision. AutoSciRub decomposes an underspecified instruction into atomic scientific goals, grounds them in relevant literature and task-visible data, and synthesizes specific, actionable, and verifiable criteria. The resulting rubric makes implicit experimental and evidential requirements explicit, providing guidance for experiments and analyses. During revision, rubric-guided verification identifies unmet criteria and enables targeted refinement of the research report and its supporting artifacts. On ResearchClawBench, AutoSciRub consistently improves all tested configurations, with an average gain of 2.08 points across three backbone LLMs under the fixed Codex harness and 2.95 points across three agent harnesses using a fixed DeepSeek-V4-Flash backbone. On a randomly sampled 20-task subset of AstaBench E2E Discovery, AutoSciRub further achieves an average improvement of 16.8 points across three agent harnesses, while maintaining or increasing the number of successfully completed tasks. These results demonstrate that evaluation-first guidance provides an effective and generalizable control mechanism for autonomous scientific research (Code: this https URL).
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Software Engineering (cs.SE)
arXiv:2608.31076 [cs.CL]
(or arXiv:2608.31076v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.31076 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 275 cuvinte
Subiecte conexe
Building trust in AI agents: A production-ready evaluation framework with Amazon Bedrock AgentCore
AWS · 16 oct. 2026
Granite 4.1 LLMs: How They’re Built
Hugging Face · 29 apr. 2026
GenRubric: Self-Evolving Rubric Generation for Scalable LLM Evaluation
arXiv · 1 sept. 2026
Deconfusing Corrigibility
AI Alignment Forum · 17 oct. 2026