About
Ujwal is a researcher working on AI safety and governance.
Selected Work
Evolving Interpretable Constitutions for Multi-Agent Coordination
arXiv2026
Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design
arXiv2026
Gender Bias in LLM Hiring Decisions: Evidence from a Japanese Context and Evaluation of Mitigation Strategies
BIAS 2026 (ECML PKDD)2026
Constitutional Arms Races in the Public Goods Game: Co-Evolving LLM Constitutions Under Cooperation-Defection Pressure
arXiv2026