FrontierPhysics: Evaluating Agents for End-to-End Physics Research
cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/benchflow-ai/benchflow
Terminology
Sources
- Concrete Problems in AI Safety
- How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks
- HealthBench: Evaluating Large Language Models Towards Improved Human Health
- SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs
- Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
- Theoretical Physics Benchmark (TPBench) -- a Dataset and Study of AI Reasoning Capabilities in Theoretical Physics
- Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction
- Agentic LLM Reasoning in a Self-Driving Laboratory for Air-Sensitive Lithium Halide Spinel Conductors
- Harnessing X-ray Absorption Spectroscopy Data through Multimodal Mining of Battery Literature
- RealPDEBench: A Benchmark for Complex Physical Systems with Real-World Data
- CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution
- Deep Research in Physical Sciences: A Multi-Agent Framework and Comprehensive Benchmark
- ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
- Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- PRBench: End-to-end Paper Reproduction in Physics Research
- Agent Laboratory: Using LLM Agents as Research Assistants
- Agents' Last Exam
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents