Author

Yuval Kansal

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Mar 2026

An Alternative Trajectory for Generative AI

This work argues for first constructing explicit symbolic abstractions (knowledge graphs, ontologies, and formal logic) to underpin synthetic curricula enabling small language models to master domain-specific reasoning without the model collapse problem typical of LLM-based synthetic data methods.

Margarita Belova, Yuval Kansal, Yihao Liang et al. · arXiv.org · 2 citations

#artificial intelligence Preprint Oct 2026

Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons

Self-Direction is introduced, a mechanism for agents to learn from mistakes that combines the benefits of temporary in-context retries and policy updates and reduces repeated mistakes across future encounters of a task, nearly doubling the reliability of an agent's corrections.

Yuval Kansal, Karen Ullrich, Polina Kirichenko et al. · 0 citations