·4 mins
AI agents that automatically improve through prompt evolution and dynamic tool creation.
Research
2025
NLP Interpretability - Mechanistic Analysis of LLMs
·3 mins
Research investigating LLM interpretability for financial prediction using attention analysis and causal attribution.
·2 mins
Research using LLMs to evolve agent behaviors through automated code generation. Accepted at GECCO ‘25.
·3 mins
Extension bridging NetLogo and LLMs for intelligent agent behaviors and decision-making.
QD-LEAR - Quality-Diversity in LLM-Evolved Agents
·2 mins
Extension of LEAR research exploring quality-diversity tradeoffs in agent evolution.