10 papers
SpanNorm: Reconciling Training Stability and Performance in Deep Transformers
Chao Wang, Bei Li, Jiaqi Zhang +8
The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, lead…
CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM
Son Nguyen, Xinyuan Liu, Ransalu Senanayake
Users increasingly face the challenge of selecting an appropriate LLM for a given task from a rapidly growing pool of LLMs, each with distinct but often opaque latent properties. C…
MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition
Yifan Bao, Xinyu Xi, Xinyu Liu +8
Automated data science is a structured model-selection problem. A solution must choose data transformations, feature representations, architecture, training procedure, evaluation p…
TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents
Dawei Wang, Chengming Zhou, Di Zhao +4
Recent breakthroughs in Large Language Models (LLMs) have positioned them as a promising paradigm for agents, with long-term planning and decision-making emerging as core general-p…
On Safety Risks in Experience-Driven Self-Evolving Agents
Weixiang Zhao, Yichen Zhang, Yingshuo Wang +8
Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduc…
LLM Routing as Reasoning: A MaxSAT View
Son Nguyen, Xinyuan Liu, Ransalu Senanayake
Routing a query through an appropriate LLM is challenging, particularly when user preferences are expressed in natural language and model attributes are only partially observable.…