6 papers
Continual Test-Time Learning with Evolution Strategies
Guangya Hao, Yiting Duan, Longyan Tan +5
Large language models increasingly operate in open-ended environments, where they are expected to continually adapt to evolving tasks and distributions, often without access to ext…
How Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-Distillation
Yunbo Long, Guangya Hao, Yuhan Liu +4
Execution feedback lets coding agents revise programs and learn from their own corrections. A correction's learning weight should reflect both the transitions supported by its exec…
SPECTRUM: Proximal Spectral Modulation for Looped Self-Distillation
Yunbo Long, WenJie Chen, Jiaquan Zhang +4
A model that learns from its own outputs inherits more than their correctness: it inherits which solutions it produces. We formulate Looped Self-Distillation, a self-evolution fram…
Self-Evolving Multi-Agent Systems via Decentralized Memory
Guangya Hao, Yunbo Long, Zhuokai Zhao
Self-evolving multi-agent systems (MAS) have emerged as a promising route to LLM agents that continually improve from experience, with persistent memory at their foundation. Howeve…
Self-Policy Distillation via Capability-Selective Subspace Projection
Guangya Hao, Yitong Shang, Yunbo Long +2
Self-distillation bootstraps large language models (LLMs) by training on their own generations. However, existing methods either rely on external signals to curate self-generated o…
Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training
Yunbo Long, Tejumade Afonja, Guangya Hao +2
Tabular language models can generate synthetic tables by modeling rows as token sequences, but they are typically trained once with supervised fine-tuning and then used as static s…