5 papers
Towards Precise Intent-Aligned VLA Aerial Navigation via Expert-Guided GRPO
Tianyang Chen, Wenjun Li, Xin zhou +2
Vision-Language-Action (VLA) models offer a promising end-to-end paradigm for unmanned aerial vehicles (UAVs) to accomplish complex tasks specified by fine-grained instructions. Ho…
HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained Travel
The Viet Bui, Wenjun Li, Yong Liu
Sequential LLM agents fail on long-horizon planning with hard constraints like budgets and diversity requirements. As planning progresses and context grows, these agents drift from…
Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement
Yuxiao Lu, Lin Xu, Yang Sun +2
Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behav…
Doc-Researcher: A Unified System for Multimodal Document Parsing and Deep Research
Kuicai Dong, Shurui Huang, Fangda Ye +9
Deep Research systems have revolutionized how LLMs solve complex questions through iterative reasoning and evidence gathering. However, current systems remain fundamentally constra…
Unlocking Large Language Model's Planning Capabilities with Maximum Diversity Fine-tuning
Wenjun Li, Changyu Chen, Pradeep Varakantham
Large language models (LLMs) have demonstrated impressive task-solving capabilities through prompting techniques and system designs, including solving planning tasks (e.g., math pr…