5 papers
Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks
Boxiu Li, Zimo Wen, Yijia Fan +24
Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and pivot when measurements reveal failure, hidden constraints, or a…
CineMobile: On-Device Image-to-Video Diffusion for Cinematic Camera Motion Generation
Xuyao Huang, Zelai Deng, Xu Wang +2
The growing demand for image-to-video creation on mobile devices has increasingly focused on cinematic motion effects like bullet time, dolly zoom, slow motion, etc. While Diffusio…
TPS-Bench: Evaluating AI Agents' Tool Planning \& Scheduling Abilities in Compounding Tasks
Hanwen Xu, Xuyao Huang, Yuzhe Liu +2
Large language model (LLM) agents have exhibited strong problem-solving competence across domains like research and coding. Yet, it remains underexplored whether LLM agents can tac…
Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition
Zihao Zeng, Xuyao Huang, Boxiu Li +2
Large Reasoning Models (LRMs) are criticized for the excessively lengthy Chain-of-Thought (CoT) to derive the final answer, suffering from high first-token and overall latency. Typ…
SIFT: Grounding LLM Reasoning in Contexts via Stickers
Zihao Zeng, Xuyao Huang, Boxiu Li +1
This paper identifies the misinterpretation of the context can be a significant issue during the reasoning process of large language models, spanning from smaller models like Llama…