LeWRON is a new agentic framework that automates construction, auditing, and exploration of finite-temperature effective potentials and gravitational-wave predictions for electroweak phase transitions starting from an input Lagrangian.
An End-to-end Architecture for Collider Physics and Beyond
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8representative citing papers
Collider-Bench is a new benchmark showing that current LLM agents cannot reliably reproduce LHC analyses at the level of a physicist-in-the-loop.
Quantity-grounded multi-agent decomposition makes LLM-generated collider analysis code inspectable and reliable with 14B-scale models, outperforming prior single-prompt approaches.
An open-source framework that automates BSM Lagrangian construction, anomaly checks, and mass-matrix derivation from natural-language field specifications by using an LLM only as an orchestration layer over a deterministic symbolic backend.
A multi-agent LLM framework that runs and audits an astroparticle physics pipeline, reproducing human results for NANOGrav phase-transition fits and flagging limitations.
PRL-Bench evaluates frontier LLMs on 100 real physics research tasks and finds the best models score below 50, exposing a gap to autonomous discovery.
AutoResearchClaw introduces a multi-agent research pipeline with debate, self-healing, verifiable outputs, human collaboration modes, and cross-run evolution that outperforms AI Scientist v2 by 54.7% on ARC-Bench.
EasyScan_HEP 2 adds AI-agent interfaces to a HEP parameter scan framework for natural-language to .ini config translation and new sampler integration.
citing papers explorer
-
LeWRON: Agentic Analysis of Electroweak Phase Transitions
LeWRON is a new agentic framework that automates construction, auditing, and exploration of finite-temperature effective potentials and gravitational-wave predictions for electroweak phase transitions starting from an input Lagrangian.
-
Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction
Collider-Bench is a new benchmark showing that current LLM agents cannot reliably reproduce LHC analyses at the level of a physicist-in-the-loop.
-
Articulating Assumptions in AI-Generated Scientific Analyses through Task Decomposition
Quantity-grounded multi-agent decomposition makes LLM-generated collider analysis code inspectable and reliable with 14B-scale models, outperforming prior single-prompt approaches.
-
Large Language Model-Assisted Framework for BSM Model Building
An open-source framework that automates BSM Lagrangian construction, anomaly checks, and mass-matrix derivation from natural-language field specifications by using an LLM only as an orchestration layer over a deterministic symbolic backend.
-
DarkAgents
A multi-agent LLM framework that runs and audits an astroparticle physics pipeline, reproducing human results for NANOGrav phase-transition fits and flagging limitations.
-
PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research
PRL-Bench evaluates frontier LLMs on 100 real physics research tasks and finds the best models score below 50, exposing a gap to autonomous discovery.
-
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
AutoResearchClaw introduces a multi-agent research pipeline with debate, self-healing, verifiable outputs, human collaboration modes, and cross-run evolution that outperforms AI Scientist v2 by 54.7% on ARC-Bench.
-
EasyScan_HEP 2: Agent-Ready Parameter Scans for High-Energy Physics
EasyScan_HEP 2 adds AI-agent interfaces to a HEP parameter scan framework for natural-language to .ini config translation and new sampler integration.