5 papers
PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement
Tuo Zhang, Alin-Ionut Popa, Yan Xu +2
Large language model (LLM)-based agents frequently generate seemingly coherent plans that fail upon execution due to infeasible actions, constraint violations, and compounding erro…
MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents
Peizhou Huang, Zixuan Zhong, Zhongwei Wan +12
Deep Research Agents (DRAs) generate citation-rich reports via multi-step search and synthesis, yet existing benchmarks mainly target text-only settings or short-form multimodal QA…
Stratos: An End-to-End Distillation Pipeline for Customized LLMs under Distributed Cloud Environments
Ziming Dai, Tuo Zhang, Fei Gao +5
The growing industrial demand for customized and cost-efficient large language models (LLMs) is fueled by the rise of vertical, domain-specific tasks and the need to optimize perfo…
Provenance Analysis of Archaeological Artifacts via Multimodal RAG Systems
Tuo Zhang, Yuechun Sun, Ruiliang Liu
In this work, we present a retrieval-augmented generation (RAG)-based system for provenance analysis of archaeological artifacts, designed to support expert reasoning by integratin…
Revisiting OPRO: The Limitations of Small-Scale LLMs as Optimizers
Tuo Zhang, Jinyue Yuan, Salman Avestimehr
Numerous recent works aim to enhance the efficacy of Large Language Models (LLMs) through strategic prompting. In particular, the Optimization by PROmpting (OPRO) approach provides…