Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse
Ling-Qi Zhang, Kristin Branson
Neuroscience data are highly fragmented across labs, formats, and experimental paradigms, and reuse often requires substantial manual effort. A persistent roadblock to data reuse a…
cs.LG2026
GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
Sijia Li, Yuchen Huang, Zifan Liu +7
Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision.…