AI Tour Meeting: Group Travel Planning by LLM Agents
This paper proposes AI Tour Meeting, a group travel planning framework powered by multiple Large Language Model (LLM)-based agents. The agents are instantiated with distinct personas…
Latest
Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation
Role-playing agents (RPAs) have become one of the most important consumer applications of large language models. Users engage in multi-turn conversations with RPAs for experiences such…
MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing
Text-to-image and personalized editing models now synthesize high-fidelity single-subject images with ease. Yet placing multiple named people into shared contact actions such as embrace, carry, or…
Can Large Language Models Execute Parent Orders?
Parent-order execution is a core problem in algorithmic trading, where the goal is to split a large order into smaller orders while reducing execution costs. Existing…
Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory
Decoder-only language models entangle long-term memory and reasoning in a single parameter set, making it difficult to scale memory capacity independently. Memory Decoder introduces a parametric…
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
GUI agents have the potential to become a general purpose executor over existing digital devices. To advance them toward real-world use, we envision agents that operate…
RefCaptioner: Multi-Reference Image-Grounded Video Captioning
Existing video captioning models generate natural descriptions of video content but cannot explicitly ground local visual elements to multiple reference images. We introduce multi-reference image-grounded video…
Beacon: Knowing When and How to Perform Agentic Visual Reasoning
The fundamental goal of agentic visual reasoning is to improve the success rate of multimodal large language models (MLLMs) on complex tasks, rather than merely equipping…
BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms
Retrieval-augmented generation (RAG) spans lexical and dense retrieval, graph-based indexing, and agentic search, but these paradigms are usually evaluated on different benchmarks at one corpus size,…
Flux-OPD: On-Policy Distillation with Evolving Contexts
Large language model training in open-ended domains lacks verifiable rewards, making task preferences difficult to formalize as effective supervision. Contexts can convey such preferences, yet provide…