8 papers
FlowCompile: An Optimizing Compiler for Structured LLM Workflows
Junyan Li, Zhang-Wei Hong, Maohao Shen +2
Structured LLM workflows, where specialized LLM sub-agents execute according to a predefined graph, have become a powerful abstraction for solving complex tasks. Optimizing such wo…
SkillOS: Learning Skill Curation for Self-Evolving Agents
Siru Ouyang, Jun Yan, Yanfei Chen +13
LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills disti…
Decocted Experience Improves Test-Time Inference in LLM Agents
Maohao Shen, Kaiwen Zha, Zexue He +6
There is growing interest in improving LLMs without updating model parameters. One well-established direction is test-time scaling, where increased inference-time computation (e.g.…
PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory
Bowen Jiang, Yuan Yuan, Maohao Shen +13
Personalization is one of the next milestones in advancing AI capability and alignment. We introduce PersonaMem-v2, the state-of-the-art dataset for LLM personalization that simula…
RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
Kaiwen Zha, Zhengqi Gao, Maohao Shen +3
Reinforcement learning (RL) has recently emerged as a compelling approach for enhancing the reasoning capabilities of large language models (LLMs), where an LLM generator serves as…
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
Maohao Shen, Guangtao Zeng, Zhenting Qi +7
Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains. Recent studies have shown that increasing test-time computation enhances LL…