6 papers
MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts
Peiwen Li, Shiyang Zhang, Yangtian Zhang +3
Large language model-based multi-agent systems have recently shown strong potential for complex, long-horizon tasks. However, existing methods mainly rely on coarse prompt-level di…
STRIDE: Post-Training LLMs to Reason and Refine Bio-Sequences via Edit Trajectories
Daiheng Zhang, Shiyang Zhang, Sizhuang He +3
Discrete biological sequence optimization often requires goal-directed, parser-valid edits to an existing protein or molecule. Diffusion models support iterative refinement but do…
Learning Permutation Distributions via Reflected Diffusion on Ranks
Sizhuang He, Yangtian Zhang, Shiyang Zhang +1
The finite symmetric group S_n provides a natural domain for permutations, yet learning probability distributions on S_n is challenging due to its factorially growing size and disc…
Variational Learning for Insertion-based Generation
Yangtian Zhang, Zhe Wang, Arthur Gretton +4
Non-monotonic sequence generation methods, such as masked diffusion models, provide a flexible alternative to left-to-right autoregressive modeling by allowing tokens to be generat…
FederatedSkill: Federated Learning for Agentic Skill Evolution
Jingbo Yang, Guanyu Yao, Yang Zhang +3
Modern LLM agents increasingly rely on skill libraries to handle complex tasks, making skill evolution a primary driver of self-improvement. However, isolated single-user task stre…
Non-Markovian Discrete Diffusion with Causal Language Models
Yangtian Zhang, Sizhuang He, Daniel Levine +7
Discrete diffusion models offer a flexible, controllable approach to structured sequence generation, yet they still lag behind causal language models in expressive power. A key lim…