3 papers
cs.CL2026
CAPO: Constraint-Aware Prompt Optimization for LLM Agents
Victor Ye Dong, Reid Pryzant, Yi Liu +1
Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks. Such deployments impose distinct operational requireme…
cs.LG2026
Greedy Information Projection for LLM Data Selection
Victor Ye Dong, Kuan-Yun Lee, Jiamei Shuai +3
We present \emph{Greedy Information Projection} (\textsc{GIP}), a principled framework for choosing training examples for large language model fine-tuning. \textsc{GIP} casts selec…
cs.CL2025
DeepThink: Aligning Language Models with Domain-Specific User Intents
Yang Li, Mingxuan Luo, Yeyun Gong +4
Supervised fine-tuning with synthesized instructions has been a common practice for adapting LLMs to domain-specific QA tasks. However, the synthesized instructions deviate from re…