https://arulmurugan.me/research/ Recent content in Research on Arul Murugan https://arulmurugan.me/images/arul.jpg https://arulmurugan.me/images/arul.jpg Hugo -- 0.167.0 en Mon, 14 Sep 2026 00:00:00 +0000 https://arulmurugan.me/research/interpreting-steering-llm-agents/ Mon, 14 Sep 2026 00:00:00 +0000 https://arulmurugan.me/research/interpreting-steering-llm-agents/ We compare prompting, sparse autoencoders, and linear probes for interpreting and steering LLM agents in social simulations. SAEs help inspect internal features, probes offer calibrated control, and stronger prompting is competitive or better on some tasks. https://arulmurugan.me/research/theorizing-with-llms/ Wed, 29 Jul 2026 00:00:00 +0000 https://arulmurugan.me/research/theorizing-with-llms/ Published open access in Strategic Management Journal, this paper introduces a framework for using LLM-based AI agents as synthetic subjects in strategy research. https://arulmurugan.me/research/jagged-global-economy/ Mon, 06 Jul 2026 00:00:00 +0000 https://arulmurugan.me/research/jagged-global-economy/ We estimate how labor markets in 141 countries are exposed to frontier AI, showing large cross-country variation, gender gaps, adoption correlations, and remittance-linked indirect exposure.