Research map / Large language models / Agents, code and math
BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science
Yuyang Liu, Liuzhenghao Lv, Xiancheng Zhang, Jingya Wang, Li Yuan, Yonghong Tian
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add structured chain-of-thought prompting (REA-ERR vs ERR) | QwQ-32b · BioProBench ERR | F1: 59.41% -> 71.40% | Improved |
| add zero-shot CoT prompting to protocol generation | Claude-3-7-sonnet · BioProBench GEN | Step Recall: 0.4280 to 0.3918 | Hurt |
| add BioProCorpus retrieval (ProAgent) for PQA | Gemini-2.5-pro-exp · BioProBench PQA | accuracy: 15 points to 85.08% | Improved |
| add BioProCorpus retrieval (ProAgent) for ERR | Gemini-2.5-pro-exp · BioProBench ERR | F1: 59.27% -> 81.9% | Improved |
| add BioProCorpus retrieval (ProAgent) for GEN | Claude-3-7-sonnet · BioProBench GEN | Step Recall: 42.8% to 62.24% | Improved |
| add BioProBench RAG module on external benchmark | ProAgent base model · LAB-Bench protocol subset (108 questions) | accuracy: 56% -> 67% | Improved |
| perturb numerical values in PQA context (ablation) | PQA evaluation · BioProBench PQA | accuracy | No clear effect |
| add one-shot CoT exemplar instead of zero-shot | GEN prompting · BioProBench GEN | mixed metrics | Mixed |
Closest papers by meaning
- BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics (ICML 2026 · similarity 0.86)
- AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite (ICLR 2026 · similarity 0.85)
- BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks (NeurIPS 2026 · similarity 0.85)
- ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows (ICLR 2026 · similarity 0.85)
- CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research (NeurIPS 2025 · similarity 0.85)
- SciAgentGym: Benchmarking Multi-Step Scientific Tool-Use in LLM Agents (ICML 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
