COMPOSITE-Stem

• URL: http://arxiv.org/abs/2604.09836v2
• Date: Thu, 16 Apr 2026 21:01:25 GMT
• Title: COMPOSITE-Stem
• Abstract summary: COMPOSITE-STEM is a benchmark of 70 expert-written tasks in physics, biology, chemistry, and mathematics.<n>Our benchmark combines exact-match grading and criterion-based rubrics with an-as-a-jury grading protocol.<n>The top-performing model achieves 21%, demonstrating that COMPOSITE-STEM captures capabilities beyond current agent reach.
• Score: 32.17652486099204
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI agents hold growing promise for accelerating scientific discovery; yet, a lack of frontier evaluations hinders adoption into real workflows. Expert-written benchmarks have proven effective at measuring AI reasoning, but most at this stage have become saturated and only measure performance on constrained outputs. To help address this gap, we introduce COMPOSITE-STEM, a benchmark of 70 expert-written tasks in physics, biology, chemistry, and mathematics, curated by doctoral-level researchers. Our benchmark combines exact-match grading and criterion-based rubrics with an LLM-as-a-jury grading protocol, allowing more flexible assessment of scientifically meaningful outputs. Using an adapted multimodal Terminus-2 agent harness within the Harbor agentic evaluation framework, we evaluate four frontier models. The top-performing model achieves 21%, demonstrating that COMPOSITE-STEM captures capabilities beyond current agent reach. All tasks are open-sourced with contributor permission to support reproducibility and to promote additional research towards AI's acceleration of scientific progress in these domains.

Related papers

• Benchmarking AI Agents for Addressing Scientific Challenges Across Scales [118.2204632627895]
  SciAgentArena is a systematic benchmark for evaluating AI agents in real-world scientific research scenarios.<n>It comprises approximately 200 tasks with stepwise verification and an interactive, agent-agnostic environment for assessing diverse AI agents.<n>We find that current agents can contribute effectively to well-specified data-analysis, particularly when the task structure and evaluation criteria are clear.
  arXiv  Detail & Related papers  (2026-06-10T22:55:30Z)
• AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents [49.67355440164857]
  We introduce AIRS-Bench, a suite of 20 tasks sourced from state-of-the-art machine learning papers.<n>Airs-Bench tasks assess agentic capabilities over the full research lifecycle.<n>We open-source the AIRS-Bench task definitions and evaluation code to catalyze further development in autonomous scientific research.
  arXiv  Detail & Related papers  (2026-02-06T16:45:02Z)
• FIRE-Bench: Evaluating Agents on the Rediscovery of Scientific Insights [63.32178443510396]
  We introduce FIRE-Bench (Full-cycle Insight Rediscovery Evaluation), a benchmark that evaluates agents through the rediscovery of established findings.<n>Even the strongest agents achieve limited rediscovery success (50 F1), exhibit high variance across runs, and display recurring failure modes in experimental design, execution, and evidence-based reasoning.
  arXiv  Detail & Related papers  (2026-02-02T23:21:13Z)
• HeurekaBench: A Benchmarking Framework for AI Co-scientist [2.206319727896241]
  HeurekaBench is a framework to create benchmarks with exploratory, open-ended research questions for experimental datasets.<n>We instantiate the framework in single-cell biology to obtain sc-HeurekaBench benchmark and use it to compare state-of-the-art single-cell agents.<n>We find that the addition of a critic module can improve ill-formed responses for open-source LLM-based agents by up to 22% and close the gap with their closed-source counterparts.
  arXiv  Detail & Related papers  (2026-01-04T22:16:42Z)
• Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows [203.3527268311731]
  We present an operational SGI definition grounded in the Practical Inquiry Model (PIM)<n>We operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning.<n>Our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery.
  arXiv  Detail & Related papers  (2025-12-18T12:44:36Z)
• From Task Executors to Research Partners: Evaluating AI Co-Pilots Through Workflow Integration in Biomedical Research [0.16174969956296248]
  This rapid review examines benchmarking practices for AI systems in preclinical biomedical research.<n>A process-oriented evaluation framework is proposed that addresses four critical dimensions absent from current benchmarks.<n>These dimensions are essential for evaluating AI systems as research co-pilots rather than as isolated task executors.
  arXiv  Detail & Related papers  (2025-12-04T14:37:46Z)
• Dr.Mi-Bench: A Modular-integrated Benchmark for Scientific Deep Research Agent [52.876617746453995]
  Dr.Mi-Bench is a Modular-integrated benchmark for scientific deep research (DR) agents.<n>Dr.Mi-Eval is a novel modular-integrated evaluation paradigm.
  arXiv  Detail & Related papers  (2025-11-30T17:16:47Z)
• SelfAI: Building a Self-Training AI System with LLM Agents [79.10991818561907]
  SelfAI is a general multi-agent platform that combines a User Agent for translating high-level research objectives into standardized experimental configurations.<n>An Experiment Manager orchestrates parallel, fault-tolerant training across heterogeneous hardware while maintaining a structured knowledge base for continuous feedback.<n>Across regression, computer vision, scientific computing, medical imaging, and drug discovery benchmarks, SelfAI consistently achieves strong performance and reduces redundant trials.
  arXiv  Detail & Related papers  (2025-11-29T09:18:39Z)
• InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research [36.46396692622759]
  We introduce InnovatorBench, a benchmark-platform pair for realistic, end-to-end assessment of agents performing Large Language Model (LLM) research.<n>It comprises 20 tasks spanning Data Construction, Filtering, Augmentation, Loss Design, Reward Design, and Scaffold Construction.<n>We also develop ResearchGym, a research environment offering rich action spaces, distributed and long-horizon execution, asynchronous monitoring, and snapshot saving.
  arXiv  Detail & Related papers  (2025-10-31T16:22:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.