SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension Paper โข 2508.01959 โข Published Aug 3 โข 58
Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following Paper โข 2508.02150 โข Published Aug 4 โข 36
Dynaword: From One-shot to Continuously Developed Datasets Paper โข 2508.02271 โข Published Aug 4 โข 14
Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction Paper โข 2508.02558 โข Published Aug 4 โข 10
view post Post 3596 I'm building a mmo-ish RPG with LLM agents that can (hopefully) complete player tasks, as an experiment. I've started documenting my progress here: https://huggingface.co/blog/neph1/rpg-llm-agentsLet me know if you want to see more of it. See translation 4 replies ยท ๐ฅ 11 11 ๐ 1 1 + Reply
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Paper โข 2507.19457 โข Published Jul 25 โข 28