← Search

Haosi Mo

2 accepted papers

2026

AgentVocab: Structure-Aware Vocabulary Adaptation for Efficient LLM Agents

ICML 2026poster

Recent large language models (LLMs) have demonstrated strong capabilities across challenging tasks, enabling their widespread adoption in agentic systems that interact with external tools. In such deployments, however, LLMs are typically trained with general-purpose tokenizers designed for broad lan…

Cited by 0SourceScholar
2025

CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task

EMNLP 2025

Recent advances in Large Language Models (LLMs) have significantly enhanced their capabilities, highlighting the need for comprehensive evaluation frameworks that extend beyond task-specific benchmarks.However, existing benchmarks often focus on isolated abilities, lacking a holistic framework for a