pith. sign in

arxiv: 2507.05241 · v2 · pith:I5F2RL6Dnew · submitted 2025-07-07 · 💻 cs.AI · cs.CL

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

classification 💻 cs.AI cs.CL
keywords agentsreasoningscientificadvancementsagentcapabilitiesdeepexam
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Deep Research in Physical Sciences: A Multi-Agent Framework and Comprehensive Benchmark

    physics.comp-ph 2026-06 unverdicted novelty 7.0

    PhySciBench benchmark shows current AI models achieve at most 33.5% accuracy on physical science tasks; DelveAgent framework improves accuracy by up to 7.5 points and cuts costs to one-third.

  2. ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning

    cs.LG 2026-05 unverdicted novelty 7.0

    ReCrit frames critic interaction as a correctness-transition problem and uses quadrant-based RL rewards to improve LLM performance on scientific reasoning benchmarks by rewarding corrections and robustness while penal...

  3. Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis

    cs.CL 2026-04 unverdicted novelty 7.0

    DataPRM is a new process reward model for data analysis agents that detects silent errors via environment interaction and ternary rewards, yielding 7-11% gains on benchmarks and further RL improvements.

  4. Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis

    cs.CL 2026-04 unverdicted novelty 7.0

    DataPRM is an environment-aware generative process reward model that improves LLM data analysis agents by 7-11% on benchmarks via active verification and reflection-aware ternary rewards.

  5. IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review

    cs.IR 2026-04 unverdicted novelty 7.0

    IntrAgent uses a two-stage pipeline of section ranking and iterative reading to perform content-grounded literature information retrieval, achieving 13.2% higher accuracy than RAG and agent baselines on the new IntraB...

  6. Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

    cs.CL 2026-06 unverdicted novelty 6.0

    Arbor combines a coordinator, executors, and a hypothesis tree to enable cumulative autonomous research, outperforming Codex and Claude Code by over 2.5x on six real tasks and reaching 86.36% Any Medal on MLE-Bench Lite.

  7. SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning

    cs.AI 2026-05 unverdicted novelty 6.0

    SciResearcher automates creation of diverse scientific reasoning tasks from academic evidence to train an 8B model that sets new SOTA at 19.46% on HLE-Bio/Chem-Gold and gains 13-15% on SuperGPQA-Hard-Biology and TRQA-...

  8. SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning

    cs.AI 2026-05 unverdicted novelty 5.0

    SciResearcher is a new agentic data-construction framework that trains an 8B model via supervised fine-tuning and reinforcement learning to reach 19.46% on HLE-Bio/Chem-Gold and 13-15% gains on related biology and lit...

  9. EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale

    cs.AI 2026-04 unverdicted novelty 5.0

    EvoMaster is a self-evolving agent framework that achieves state-of-the-art results on scientific benchmarks by enabling iterative hypothesis refinement and knowledge accumulation across domains.

  10. SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research

    cs.AI 2026-05 unverdicted novelty 4.0

    SciAtlas builds a large-scale multi-disciplinary academic knowledge graph and a neuro-symbolic retrieval system to support automated scientific research tasks such as literature review and idea positioning.

  11. AI for Auto-Research: Roadmap & User Guide

    cs.AI 2026-05 unverdicted novelty 4.0

    The paper delivers a stage-by-stage roadmap for AI in research, showing reliable assistance in retrieval and tool tasks but fragility in novelty and judgment, advocating human-governed collaboration.

  12. EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale

    cs.AI 2026-04 conditional novelty 4.0

    EvoMaster is an open-source agent framework whose iterative self-evolution loop achieves the highest average score on 9 of 10 scientific agent benchmarks compared to OpenHands, OpenClaw, and Codex.

  13. The Agentification of Scientific Research: A Physicist's Perspective

    cs.AI 2026-04 unverdicted novelty 3.0

    AI will evolve from a research tool into a collaborator, fundamentally reshaping scientific collaboration, discovery, publishing, and evaluation while requiring continuous learning and idea diversity for original cont...