FermiLink is a unified AI agent framework that automates multidomain scientific simulations via separated package knowledge bases and a four-layer progressive disclosure mechanism, reproducing 56% of target figures in benchmarks and generating research-grade results on unpublished problems.
Vibe physics: the AI grad student
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
years
2026 7representative citing papers
Structured critic-actor loops improve AI performance on theoretical physics reasoning tasks, with benefits strongest in asymmetric model pairings using constructive feedback.
KS uncolorability in 3D occurs only with modulus-2 or phase cancellation in the coordinate generators, producing new graph types in the Heegner-7 ring and golden ratio field.
SHARP is a human-AI collaboration pipeline for reproducing scientific analyses, demonstrated by recreating a jet classification task from a particle physics paper.
VLM ensembles with Bayesian weighting classify galaxy mergers at human-expert accuracy on 41 mock images and recover the merger fraction within 0.66 sigma.
pAI/MSc is a customizable multi-agent system that reduces human steering by orders of magnitude when turning a hypothesis into a literature-grounded, mathematically established, experimentally supported manuscript draft in ML theory.
AI agents exploring Platonic mathematical structures via proof hypergraphs may reveal the overall architecture of formal mathematics and what makes parts of it human-accessible.
citing papers explorer
-
FermiLink: A Unified Agent Framework for Multidomain Autonomous Scientific Simulations
FermiLink is a unified AI agent framework that automates multidomain scientific simulations via separated package knowledge bases and a four-layer progressive disclosure mechanism, reproducing 56% of target figures in benchmarks and generating research-grade results on unpublished problems.
-
When Does Critique Improve AI-Assisted Theoretical Physics? SCALAR: Structured Critic--Actor Loop for Agentic Reasoning
Structured critic-actor loops improve AI performance on theoretical physics reasoning tasks, with benefits strongest in asymmetric model pairings using constructive feedback.
-
The Algebraic Landscape of Kochen-Specker Sets in Dimension Three
KS uncolorability in 3D occurs only with modulus-2 or phase cancellation in the coordinate generators, producing new graph types in the Heegner-7 ring and golden ratio field.
-
A Scientific Human-Agent Reproduction Pipeline
SHARP is a human-AI collaboration pipeline for reproducing scientific analyses, demonstrated by recreating a jet classification task from a particle physics paper.
-
Vision-Language Model Ensembles Achieve Human-Expert Accuracy for Galaxy Merger Classification
VLM ensembles with Bayesian weighting classify galaxy mergers at human-expert accuracy on 41 mock images and recover the merger fraction within 0.66 sigma.
-
pAI/MSc: ML Theory Research with Humans on the Loop
pAI/MSc is a customizable multi-agent system that reduces human steering by orders of magnitude when turning a hypothesis into a literature-grounded, mathematically established, experimentally supported manuscript draft in ML theory.
-
Artificial Intelligence and the Structure of Mathematics
AI agents exploring Platonic mathematical structures via proof hypergraphs may reveal the overall architecture of formal mathematics and what makes parts of it human-accessible.