Showing 2026Show all
3 papers · 1 filter
cs.AI2026
Asynchrony Is Nearly Free for Evolution Strategies on Long-Horizon LLM Agentic Tasks
William Hoy, Jingxuan Fan, Nurcin Celik +1
Synchronous policy updates can limit the efficiency of post-training for long-horizon LLM agents. When trajectories span multiple interaction turns, completion times can vary subst…
cs.LG2026
Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training
William Hoy, Binxu Wang, Xu Pan
Evolution Strategies (ES) have emerged as a scalable gradient-free alternative to reinforcement learning based LLM fine-tuning, but it remains unclear whether comparable task perfo…
cs.AI2026
Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers
Binxu Wang, Jingxuan Fan, Xu Pan
Diffusion Transformers (DiTs) have greatly advanced text-to-image generation, but models still struggle to generate the correct spatial relations between objects as specified in th…