Research
Research by Vikas Goel
India-origin Sovereign AI research, published under the ThinkerWave programme. Focused on AI Agent Architecture, self-evolving agent systems, evaluation frameworks for Enterprise AI Agents, and the engineering reality of LLM-based AI at production scale.
Current focus
Active research at ThinkerWave addresses the gap between what an AI agent can do and what it should be optimising for — a structural limitation in production deployments where the system's capabilities can evolve but its definition of success usually can't. The work explores mechanisms for evolving evaluation criteria alongside agent identity, with knowledge persistence across generations.
Patent application 202611044024 filed at the Indian Patent Office, April 2026.
Ongoing & upcoming work
The ThinkerWave research line continues. Areas under active investigation include cross-domain criteria transfer between agent lineages, the boundary conditions of identity replacement in safety-critical deployments, and the relationship between evaluation evolution and verbal calibration in LLM-as-judge architectures.
Full research outputs and pre-prints are available to qualifying parties on request, following patent grant.
For research collaboration enquiries, get in touch.
Find Vikas Goel's full body of work at Work & Research, or read more on the blog.