# SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?

arXiv: https://arxiv.org/abs/2507.05241 · HTML: https://mlsanity.com/paper/2507.05241/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Builds on (most cited first, 19 of 19)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [Absolute Zero: Reinforced Self-play Reasoning with Zero Data](https://mlsanity.com/paper/2505.03335/) (2025)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [Learning to Reason without External Rewards](https://mlsanity.com/paper/2505.19590/) (2025)
- [WebDancer: Towards Autonomous Information Seeking Agency](https://mlsanity.com/paper/2505.22648/) (2025)
- [ToRL: Scaling Tool-Integrated RL](https://mlsanity.com/paper/2503.23383/) (2025)
- [Maximizing Confidence Alone Improves Reasoning](https://mlsanity.com/paper/2505.22660/) (2025)
- [MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2503.03686/) (2025)

## Built on by (most cited first, 30 of 47)

- [AgentFold: Long-Horizon Web Agents with Proactive Context Management](https://mlsanity.com/paper/2510.24699/) (2025)
- [Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving](https://mlsanity.com/paper/2507.06229/) (2025)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [Tongyi DeepResearch Technical Report](https://mlsanity.com/paper/2510.24701/) (2025)
- [WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning](https://mlsanity.com/paper/2509.13305/) (2025)
- [CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution](https://mlsanity.com/paper/2512.23880/) (2025)
- [LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios](https://mlsanity.com/paper/2508.17692/) (2025)
- [Toward Generalist Autonomous Research via Hypothesis-Tree Refinement](https://mlsanity.com/paper/2606.11926/) (2026)
- [BrowseMaster: Towards Scalable Web Browsing via Tool-Augmented Programmatic Agent Pair](https://mlsanity.com/paper/2508.09129/) (2025)
- [TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture](https://mlsanity.com/paper/2510.01279/) (2025)
- [SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents](https://mlsanity.com/paper/2602.12984/) (2026)
- [Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning](https://mlsanity.com/paper/2509.21193/) (2025)
- [Scaling Generalist Data-Analytic Agents](https://mlsanity.com/paper/2509.25084/) (2025)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [FlowSearch: Advancing deep research with dynamic structured knowledge flow](https://mlsanity.com/paper/2510.08521/) (2025)
- [Can We Predict Before Executing Machine Learning Agents?](https://mlsanity.com/paper/2601.05930/) (2026)
- [AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents](https://mlsanity.com/paper/2603.27490/) (2026)
- [RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context](https://mlsanity.com/paper/2511.18743/) (2025)
- [Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale](https://mlsanity.com/paper/2512.20469/) (2025)
- [InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem](https://mlsanity.com/paper/2602.14367/) (2026)
- [EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale](https://mlsanity.com/paper/2604.17406/) (2026)
- [Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge](https://mlsanity.com/paper/2509.06079/) (2025)
- [AlphaApollo: A System for Deep Agentic Reasoning](https://mlsanity.com/paper/2510.06261/) (2025)
- [CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning](https://mlsanity.com/paper/2510.13166/) (2025)
- [ASI-Evolve: AI Accelerates AI](https://mlsanity.com/paper/2603.29640/) (2026)
- [Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis](https://mlsanity.com/paper/2604.24198/) (2026)
- [AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle](https://mlsanity.com/paper/2605.31468/) (2026)
- [MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pipeline Parallelism](https://mlsanity.com/paper/2511.11373/) (2025)
- [Unifying Dynamic Tool Creation and Cross-Task Experience Sharing through Cognitive Memory Architecture](https://mlsanity.com/paper/2512.11303/) (2025)
- [HarmonyCell: Automating Single-Cell Perturbation Modeling under Semantic and Distribution Shifts](https://mlsanity.com/paper/2603.01396/) (2026)

## Abstract (arXiv)

The rapid advancements of AI agents have ignited the long-held ambition of leveraging them to accelerate scientific discovery. Achieving this goal requires a deep understanding of the frontiers of human knowledge. As such, Humanity's Last Exam (HLE) provides an exceptionally challenging touchstone for evaluating scientific AI agents. In this work, we aim to construct the foundational architecture for general-purpose agents and validate the capabilities through leading performance on HLE. To achieve this, we introduce X-Master, a tool-augmented reasoning agent designed to emulate human researchers by interacting flexibly with external tools during its reasoning process. This agent, guided by the conceptualization of code as an interaction language, can flexibly leverage built-in Python libraries and our customized tools to augment the reasoning. We further scale its capabilities through X-Masters, a scattered-and-stacked agentic workflow that systematically enhances breadth and depth of reasoning. Our open-source solution, X-Masters, sets a new state-of-the-art record on HLE with a score of 32.1%, surpassing OpenAI's and Google's Deep Research (26.6% and 26.9%) and becoming the first to exceed the 30% threshold. This work allows us to gain a deeper understanding of complex task-solving and accumulates valuable experience that can inform future advancements, guiding subsequent model training.