14 papers · 1 filter
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…
Coupled Harness--Model Evolution for Scientific Equation Discovery
Pengze Li, Jiaquan Zhang, Encheng Su +8
Large language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that must work together: a library…
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…
ParaGeo: Decomposing Paralinguistic Variation into a Shared Latent Geometry
Yuhan Liu, Yuxuan Ou, Ruoxi Su +2
Speech delivery varies with both the requested paralinguistic attribute and the linguistic content. We introduce ParaGeo, a matched-content decomposition of paralinguistic variatio…
Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs
Yunbo Long, Haolang Zhao, Ge Zheng +1
LLM-based multi-agent systems have been widely adopted for knowledge retrieval and report generation, synthesizing known information through web search and textual reasoning. Howev…
Generating Logically Consistent Synthetic Supply Chain Data with LLM-Driven Knowledge Graph Reasoning
Yunbo Long, Ge Zheng, Liming Xu +1
Synthetic data offers a promising solution to two persistent barriers in supply chain analytics: data scarcity and data privacy. However, for synthetic data to support operational…
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…
EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation
Yunbo Long, Haolang Zhao, Lukas Beckenbauer +2
Post-trained LLMs are often optimized to produce helpful, polite, and accommodating responses. In adversarial negotiation, however, such behavior can become a vulnerability: emotio…
VeriTrace: Evolving Mental Models for Deep Research Agents
Haolang Zhao, Yunbo Long, Lukas Beckenbauer +1
Deep research agents face vast, interdependent, and pervasively uncertain information. Existing systems explore what evolving intermediate representations should look like, but lea…
EmoMAS: Emotion-Aware Multi-Agent System for High-Stakes Edge-Deployable Negotiation with Bayesian Orchestration
Yunbo Long, Yuhan Liu, Liming Xu
Large language models (LLMs) has been widely used for automated negotiation, but their high computational cost and privacy risks limit deployment in privacy-sensitive, on-device se…
AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model
Yunbo Long
Existing automated research systems operate as stateless, linear pipelines -- generating outputs without maintaining any persistent understanding of the research landscape they nav…