LLM

Execution-Grounded Agents: Enforcing Physical Constraints in AI Code Generation via Oracle Search

Workshop paper on oracle-search procedures that enforce physical constraints on LLM-generated scientific code, with an execution-grounded evaluation protocol.

Jul 6, 2026

Future-Ready Restoration: A Case Study on AI RAG-Enhanced Agentic Revival of a Run-2 2016 Λb → Λγ Analysis

A RAG and agentic-LLM tool (Claude, GPT-family models with a vector database over analysis scripts, notes, and documentation plus the LHCb software stack) to reproduce and accelerate a legacy LHCb analysis.

May 25, 2026

rag-ai-scientist

Open-source PyPI package for benchmarking LLM reasoning over scientific literature, with hybrid retrieval, evaluation harnesses, and agentic research pipelines.

Jan 1, 2026