Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Beyond the Performance Illusion: Structure-Aware Stratified Partitioning and Curriculum Distributionally Robust Optimization for Spatially Correlated Domains
Prathamesh Patil, Arpit Jain, Aswanth Krishnan
Performance evaluation in AI systems commonly assumes that random dataset splits produce independent and identically distributed (i.i.d.) subsets. We show that this assumption ofte…
cs.LG2025
ReflexGrad: Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process Routing
Ankush Kadu, Aswanth Krishnan
We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commit to a wrong approach early and exhaus…
cs.LG2024
Are large language models superhuman chemists?
Adrian Mirza, Nawaf Alampara, Sreekanth Kunchapu +32
Large language models (LLMs) have gained widespread interest due to their ability to process human language and perform tasks on which they have not been explicitly trained. Howeve…