Topic
case study
Agent Rosetta: How an LLM Agent Masters Protein Design for Specialized Scientific Tasks
Researchers introduce Agent Rosetta, an LLM-based agent integrated with the Rosetta software environment to automate complex protein design tasks. The agent achieves performance comparable to specialized ML models and human experts on canonical amino acids, and excels on non-canonical residues where standard ML fails. The study highlights the critical role of environment design in enabling LLM agents to operate specialized scientific software.
Imperfect Visual Verifiers Boost LLM Code Customization, Study on TikZ Finds
A new study explores using imperfect visual verifiers for iterative refinement in LLM-based code customization of TikZ graphics. Despite the lack of a deterministic oracle, imperfect verifiers achieved F1-scores up to 0.815, significantly improving customization success for weaker models and providing stable gains for stronger ones.