diff --git a/README.md b/README.md index d6c7ad2..7ec3698 100644 --- a/README.md +++ b/README.md @@ -1181,6 +1181,8 @@ - [Shiling42/web-simulator-by-GPT4](https://github.com/Shiling42/web-simulator-by-GPT4) : Online Interactive Physical Simulation Generated by GPT-4. [shilingliang.com/web-simulator-by-GPT4/](https://shilingliang.com/web-simulator-by-GPT4/) + - [aiXiv](https://github.com/aixiv-org/aiXiv) : "aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists". (**[arXiv 2025](https://arxiv.org/abs/2508.15126)**). An open-access platform with multi-agent architecture for AI and human scientists to submit, review, and refine research papers. [aiXiv Beta Waitlist](https://docs.google.com/forms/d/e/1FAIpQLSdd6nDoI5qQ1lf_mx352NmrSIeFhnIv7zLIjlXEJtiRMoo25A/viewform) + @@ -1203,6 +1205,10 @@ - [仲景](https://github.com/SupritYoung/Zhongjing) : 仲景:首个实现从预训练到 RLHF 全流程训练的中文医疗大模型。 "Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue". (**[arXiv 2023](https://arxiv.org/abs/2308.03549)**). + - [GenoTEX](https://github.com/Liu-Hy/GenoTEX) : "GenoTEX: An LLM Agent Benchmark for Automated Gene Expression Data Analysis". (**[MLCB 2025](https://arxiv.org/abs/2406.15341)**). A benchmark for evaluating LLM agents on gene expression analysis tasks, including dataset selection, preprocessing, and statistical analysis. [liu-hy.github.io/GenoTEX](https://liu-hy.github.io/GenoTEX/) + + - [GenoMAS](https://github.com/Liu-Hy/GenoMAS) : "GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis". (**[arXiv 2025](https://arxiv.org/abs/2507.21035)**). A multi-agent framework integrating guided planning with autonomous error handling for genomic data analysis. [liu-hy.github.io/GenoMAS](https://liu-hy.github.io/GenoMAS/) + @@ -1323,6 +1329,12 @@ - [OpenManus](https://github.com/mannaandpoem/OpenManus) : No fortress, purely open ground. OpenManus is Coming. + - [xhyumiracle/Awesome-AgenticLLM-RL-Papers](https://github.com/xhyumiracle/Awesome-AgenticLLM-RL-Papers) : "The Landscape of Agentic Reinforcement Learning for LLMs: A Survey". (**[arXiv 2025](https://arxiv.org/abs/2509.02547)**). A comprehensive survey on agentic RL for LLMs, covering core capabilities and applications. + + - [CoMAS](https://github.com/Yiting-ZH/CoMAS) : "CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards". (**[arXiv 2025](https://arxiv.org/abs/2510.08529)**). A framework enabling autonomous agent improvement through inter-agent interactions and reinforcement learning. + + - [Achilles Heel of DMAS](https://arxiv.org/abs/2504.07461) : "Achilles Heel of Distributed Multi-Agent Systems". (**[arXiv 2025](https://arxiv.org/abs/2504.07461)**). Studies trustworthiness challenges in distributed multi-agent systems with heterogeneous LLMs. +