Update README.md

README.md

@@ -1,11 +1,11 @@
 ---
 title: >-
-  BioProBench: Comprehensive Dataset and Benchmark in Biological Protocol
-  Understanding and Reasoning
-license: cc-by-4.0
+  BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science
+license: cc-by-nc-4.0
 task_categories:
   - text-generation
   - question-answering
+  - text-classification
 language:
   - en
 tags:
@@ -13,43 +13,52 @@ tags:
   - protocol
   - benchmark
   - ai4science
+  - reasoning
 ---
 
 <div align="center">
-  <img src="https://github.com/YuyangSunshine/bioprotocolbench/blob/main/figures/logo-v3.png?raw=true" alt="BioProBench Logo" width="300"/>
-</div>
+  <img src="https://github.com/YuyangSunshine/bioprotocolbench/blob/main/figures/logo-v3.png?raw=true" alt="BioProBench Logo" width="350"/>
+
+  <br />
+  
+  **Empowering Autonomous Science with Rigorous Procedural Reasoning**
 
-# BioProBench: Comprehensive Dataset and Benchmark in Biological Protocol Understanding and Reasoning
+  <br />
 
-[![ArXiv](https://img.shields.io/badge/ArXiv-paper-B31B1B.svg?logo=arXiv&logoColor=Red)](https://arxiv.org/pdf/2505.07889)
-[![Hugging Face](https://img.shields.io/badge/Hugging%20Face-Dataset-FFD210.svg?logo=HuggingFace&logoColor=black)](https://huggingface.co/BioProBench)
-[![GitHub](https://img.shields.io/badge/GitHub-Code-181717.svg?logo=github&logoColor=white)](https://github.com/YuyangSunshine/bioprotocolbench)
-[![Project Page](https://img.shields.io/badge/Project-Page-blue.svg?logo=google-chrome&logoColor=white)](https://yuyangsunshine.github.io/BioPro-Project/)
-[![License: CC BY 4.0](https://img.shields.io/badge/License-CC_BY_4.0-lightgrey.svg)](https://creativecommons.org/licenses/by/4.0/)
+  [![ArXiv](https://img.shields.io/badge/ArXiv-paper-B31B1B.svg?logo=arXiv&logoColor=Red)](https://arxiv.org/pdf/2505.07889)
+  [![Hugging Face](https://img.shields.io/badge/Hugging%20Face-Dataset-FFD210.svg?logo=HuggingFace&logoColor=black)](https://huggingface.co/BioProBench)
+  [![GitHub](https://img.shields.io/badge/GitHub-Code-181717.svg?logo=github&logoColor=white)](https://github.com/YuyangSunshine/bioprotocolbench)
+  [![Project Page](https://img.shields.io/badge/Project-Page-blue.svg?logo=google-chrome&logoColor=white)](https://yuyangsunshine.github.io/BioPro-Project/)
+  [![License: CC BY-NC 4.0](https://img.shields.io/badge/License-CC_BY--NC_4.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc/4.0/)
+</div>
 
 ---
 
 ## 📢 Latest News 
-* ✨ **[2026-03-31]** **Data Split Update!** We have officially released the **Train/Test splits** for each task (PQA, ORD, ERR, GEN, REA), making it easier for the community to train and evaluate models consistently.
-* 🔥 **[2026-03-18]** Our **BioProAgent** is now live on AI4S LAB! [Try it out and order wet-lab experiments here](https://yuyangsunshine.github.io/BioPro-Project/).
-* 🎉 **[2026-03-03]** Our BioProAgent has been accepted by the **ICLR 2026 LLA Workshop!**
-* 📝 **[2026-01-21]** BioProBench paper has been updated with new experimental results.[arXiv](https://arxiv.org/pdf/2505.07889).
-* 🚀 **[2025-12-01]** Code and dataset (v1.0) are released on GitHub.
+* 🛡️ **[2026-07]** **Data Compliance & Robustness Upgrade!** We have rigorously refined our corpus to ensure 100% open-source compliance, resulting in a high-fidelity foundational collection of 22,413 human-written protocols[cite: 2].
+* ✨ **[2026-03]** **Data Split Update!** We have officially released the **Train/Test splits** for each task (PQA, ORD, ERR, GEN, REA), making it easier for the community to train and evaluate models consistently.
+* 🔥 **[2026-03]** Our **BioProAgent** is now live on AI4S LAB! [Try it out and order wet-lab experiments here](https://yuyangsunshine.github.io/BioPro-Project/).
+* 🎉 **[2026-03]** Our BioProAgent has been accepted by the **ICML 2026 LLA Workshop!**
+* 📝 **[2026-01]** BioProBench paper has been updated with new experimental results on frontier models (GPT-5.4, Gemini 3.1 Pro, Claude 4.6 Opus)[cite: 2]. Read the latest on [arXiv](https://arxiv.org/pdf/2505.07889).
 
 ---
 
 ## 🌟 Introduction
-**BioProBench** is the first large-scale, integrated multi-task benchmark for biological protocol understanding and reasoning, specifically designed for Large Language Models (LLMs). It moves beyond simple QA to encompass a comprehensive suite of tasks critical for procedural text comprehension in life sciences.
+
+The realization of autonomous scientific experimentation is currently limited by LLMs' struggle to grasp the strict procedural logic and accuracy required by biological protocols[cite: 2]. 
+
+Enter **BioProBench**—the first large-scale, integrated multi-task benchmark dedicated specifically to procedural reasoning in biological contexts[cite: 2]. Moving beyond basic declarative knowledge and simple QA, BioProBench is designed to test the structured, causal, and conditional logic required for true scientific automation[cite: 2].
 
 <div align="center">
   <img src="https://github.com/YuyangSunshine/bioprotocolbench/blob/main/figures/overview.png?raw=true" alt="BioProBench Overview" width="1000"/>
 </div>
 
-### Key Features:
-* 📚 **Large-scale Data:** Built upon **27K original biological protocols**, yielding nearly **556K high-quality structured instances**.
-* 🎯 **Comprehensive Tasks:** 5 core tasks: **PQA** (Question Answering), **ORD** (Step Ordering), **ERR** (Error Correction), **GEN** (Generation), and **REA** (Reasoning).
-* 🧬 **Broad Domain Coverage:** Covers **16 biological subdomains** from 6 major repositories.
-* 🔬 **Standardized Evaluation:** A robust framework combining NLP metrics with novel domain-specific measures.
+### 🚀 Key Features
+* 📚 **Unprecedented Scale:** Grounded in **22,413** professionally authored, human-written protocols[cite: 2].
+* 🧩 **Rich Task Diversity:** Systematically constructed into a dataset of **523,784** structured task instances[cite: 2].
+* 🎯 **5 Core Procedural Tasks:** Covers Protocol Question Answering (**PQA**), Step Ordering (**ORD**), Error Correction (**ERR**), Protocol Generation (**GEN**), and Protocol Reasoning (**REA**)[cite: 2].
+* 🧬 **Broad Domain Coverage:** Spans **16 biological subfields** sourced from **5 authoritative repositories**[cite: 2].
+* 🔬 **Standardized Evaluation:** Features a rigorous benchmark utilizing novel, domain-specific metrics (e.g., Step Recall, Step Precision) to accurately quantify structural fidelity[cite: 2].
 
 ---
 
@@ -59,40 +68,48 @@ tags:
   <img src="https://github.com/YuyangSunshine/bioprotocolbench/blob/main/figures/samples.jpg?raw=true" alt="BioProBench Samples" width="1000"/>
 </div>
 
-We provide standardized JSON files for each task, now including **Train** and **Test** splits:
+We provide standardized JSON files for each task, meticulously partitioned into **Train** and **Test** splits to facilitate model fine-tuning and rigorous evaluation[cite: 2]:
 
-| Task | Description | Files |
+| Task Identifier | Core Objective | Available Files |
 | :--- | :--- | :--- |
-| **PQA** | Protocol Question Answering | `PQA_train.json`, `PQA_test.json` |
-| **ORD** | Step Ordering | `ORD_train.json`, `ORD_test.json` |
-| **ERR** | Error Correction | `ERR_train.json`, `ERR_test.json` |
-| **GEN** | Protocol Generation | `GEN_train.json`, `GEN_test.json` |
-| **Raw** | Full Protocol Corpus | `Bio-protocol.json`, `Protocol-io.json`, etc. |
+| **PQA** | Question Answering (Reagents, Parameters, Operations) | `PQA_train.json`, `PQA_test.json` |
+| **ORD** | Step Ordering (Procedural hierarchy & causal logic) | `ORD_train.json`, `ORD_test.json` |
+| **ERR** | Error Correction (Safety & validity risk identification) | `ERR_train.json`, `ERR_test.json` |
+| **GEN** | Protocol Generation (Long-form procedural synthesis) | `GEN_train.json`, `GEN_test.json` |
+| **REA** | Protocol Reasoning (Structured Chain-of-Thought) | `REA_train.json`, `REA_test.json` |
+| **Raw Corpus** | Foundational BioProCorpus | `protocols-io.json`, `Nature-Protocols.json`, etc. |
 
-### 🔗 Useful Links
-* **Official Website:** [BioPro-Project Page](https://yuyangsunshine.github.io/BioPro-Project/)
-* **GitHub Repository:** [bioprotocolbench](https://github.com/YuyangSunshine/bioprotocolbench) (Code for evaluation & training)
+*Note: Data derived from openly licensed sources is publicly available. Please refer to our [licensing details](https://github.com/YuyangSunshine/bioprotocolbench) for usage terms.*
 
 ---
 
-## 🔬 Key Findings
-We evaluated 12 mainstream LLMs. Our findings reveal:
-* **Surface vs. Deep Understanding:** Models perform well on QA (~70% Acc) but struggle with deep procedural logic.
-* **Reasoning Bottleneck:** Performance drops significantly on **Step Ordering** and **Protocol Generation** (BLEU < 15%), highlighting the difficulty of managing temporal dependencies.
-* **Bio-specific Models:** Interestingly, some bio-specific models lag behind general LLMs in capturing intricate procedural dependencies, suggesting a need for larger reasoning capacity.
+## 🔬 Key Findings from Frontier LLMs
+
+We evaluated 10 mainstream state-of-the-art LLMs, alongside a suite of the latest 2026 frontier models[cite: 2]. Our rigorous evaluation reveals:
+* **The Comprehension Plateau:** While top-tier models excel at basic declarative comprehension, performance degrades significantly on tasks demanding deep reasoning, quantitative precision, and safety awareness[cite: 2].
+* **The Generation Bottleneck:** Models struggle profoundly with long-form procedural generation (GEN task). Even the most advanced models omit necessary experimental steps, underscoring that open-ended procedural planning remains a formidable challenge[cite: 2].
+* **The Power of Grounding:** To mitigate these issues, we introduce **ProAgent**. Grounded in our BioProCorpus via a Retrieval-Augmented Generation (RAG) framework, ProAgent substantially advances the state-of-the-art, significantly improving procedural step recall and reasoning accuracy[cite: 2].
+
+---
+
+## 🔗 Useful Links & Resources
+* 🌐 **Project Website:** [Explore BioProBench](https://yuyangsunshine.github.io/BioPro-Project/)
+* 💻 **GitHub Repository:** [bioprotocolbench](https://github.com/YuyangSunshine/bioprotocolbench) (Evaluation scripts, training code, and ProAgent implementation)
 
 ---
 
 ## 🤝 Contributing & Contact
-We welcome contributions such as new protocol sources, additional domains, or novel tasks!
+We welcome contributions from the community to help pave the way for reliable AI in autonomous science! Whether it's suggesting new protocol sources, expanding biological domains, or proposing novel procedural tasks, your input is valued.
 - **Email:** sunshineliuyuyang@gmail.com
-- **Issues:** Feel free to open an issue on our [GitHub](https://github.com/YuyangSunshine/bioprotocolbench).
+- **Issues:** Feel free to open an issue or submit a PR on our [GitHub](https://github.com/YuyangSunshine/bioprotocolbench).
 
 ## 📜 Citation
+If you find BioProBench or ProAgent useful in your research, please consider citing our work:
+
 ```bibtex
-@misc{bioprotocolbench2025,
-  title={BioProBench: Comprehensive Dataset and Benchmark in Biological Protocol Understanding and Reasoning},
-  author={Yuyang Liu, Liuzhenghao Lv, Xiancheng Zhang, Jingya Wang, Li Yuan, Yonghong Tian},
-  year={2025},
-  url={[https://arxiv.org/pdf/2505.07889](https://arxiv.org/pdf/2505.07889)}
+@inproceedings{liu2026bioprobench,
+  title={BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science},
+  author={Liu, Yuyang and Lv, Liuzhenghao and Zhang, Xiancheng and Wang, Jingya and Yuan, Li and Tian, Yonghong},
+  booktitle={Proceedings of the 43rd International Conference on Machine Learning (ICML)},
+  year={2026}
 }