4 papers · 1 filter
VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?
Yansong Ning, Jingwen Ye, Zhongkai Wu +5
Constructing an interactive 3D open world from a user query is important. However, existing methods are primarily evaluated on idealized, simple queries, making it difficult to sys…
HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs
Yansong Ning, Mianpeng Liu, Jingwen Ye +2
Hybrid-reasoning large language models (LLMs) expose explicit controls over reasoning effort, allowing users or systems to trade off answer quality against inference cost. However,…
Agent-Omit: Adaptive Context Omission for Efficient LLM Agents
Yansong Ning, Jun Fang, Naiqiang Tan +1
Managing agent context (e.g., thought and observation) during multi-turn agent-environment interactions is an emerging strategy to improve agent efficiency. However, existing studi…
DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents
Yansong Ning, Rui Liu, Jun Wang +6
Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools/resources for travel itinerary generation, ensuring an enjoyable user e…