9 papers
Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training
Yiwei Qin, Zhen Huang, Tiantian Mi +5
Data quality determines foundation model performance, yet systematic processing frameworks are lacking. We introduce Data Darwinism, a ten-level taxonomy (L0-L9) that conceptualize…
daVinci-Dev: Agent-native Mid-training for Software Engineering
Ji Zeng, Dayuan Fu, Tiantian Mi +14
Recently, the frontier of Large Language Model (LLM) capabilities has shifted from single-turn code generation to agentic software engineering-a paradigm where models autonomously…
Deploy-Master: Automating the Deployment of 50,000+ Agent-Ready Scientific Tools in One Day
Yi Wang, Zhenting Huang, Zhaohan Ding +6
Open-source scientific software is abundant, yet most tools remain difficult to compile, configure, and reuse, sustaining a small-workshop mode of scientific computing. This deploy…
GRAFT: Grid-Aware Load Forecasting with Multi-Source Textual Alignment and Fusion
Fangzhou Lin, Guoshun He, Zhenyu Guo +2
Electric load is simultaneously affected across multiple time scales by exogenous factors such as weather and calendar rhythms, sudden events, and policies. Therefore, this paper p…
Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training
Dayuan Fu, Yunze Wu, Xiaojie Cai +13
Large Language Model (LLM) agents have recently shown strong potential in domains such as automated coding, deep research, and graphical user interface manipulation. However, train…
InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research
Yunze Wu, Dayuan Fu, Weiye Si +13
AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills…
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
Weizhen Li, Jianbo Lin, Zhuosong Jiang +27
Recent advances in large language models (LLMs) and multi-agent systems have demonstrated remarkable capabilities in complex problem-solving tasks such as deep research, vibe codin…
From predictions to confidence intervals: an empirical study of conformal prediction methods for in-context learning
Zhe Huang, Simone Rossi, Rui Yuan +1
Transformers have become a standard architecture in machine learning, demonstrating strong in-context learning (ICL) abilities that allow them to learn from the prompt at inference…
XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation
Qili Zhang, Qianren Mao, Yangyifei Luo +15
Retrieval-augmented generation (RAG) synergizes the retrieval of pertinent data with the generative capabilities of Large Language Models (LLMs), ensuring that the generated output…