Large language models (LLMs) increasingly tackle complex real-world tasks in specialized domains. However, identifying and correctly applying domain-specific rules remains challenging when scenario information is distributed across multiple files. Existing rule-reasoning benchmarks typically represent scenarios using o...
Chen-Hao Yuan, Bo-Han Yu, Yin-Hao Xu et al.· 0 citations
LongCat-DeepResearch is presented, a deep research system that combines an enhanced LongCat model with a multi-agent workflow for producing comprehensive, evidence-grounded reports and improves average automatic readability preference across two benchmarks, with different trends on each.
He Zhu, Yue-Ya Xu, Wan-Li Wu et al.· arXiv.org· 0 citations
Diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. However, reasoning-oriented post-training for dLLMs remains challenging. Supervised fine-tuning (SFT) for dLLMs requires dense but often off-policy masked states, while reinforcement learning (RL) relies on sparse rewards...