2 papers
cs.LG2026
Dynamic K-Head: Difficulty-Supervised Budget Selection for Continuous Latent Reasoning
Ying Li, Yuqi Chen, Sixuan Li +1
Chain-of-thought (CoT) improves reasoning but incurs substantial autoregressive rationale cost. Continuous CoT moves intermediate computation into recurrent hidden states, yet typi…
cs.CL2026
When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations
Yuqi Chen, Sixuan Li, Yunfeng Cai +3
Large language models can write fluent stories, but open-ended storytelling requires more than local fluency. In evolving world simulations and AI-native games, models must preserv…