…Xiangyuan Xue , Yifan Zhou , , , , , , Abstract Strategic Trajectory Abstraction framework enhances long-horizon decision making in large language models by introducing trajectory-level strategies that improve sample efficiency and performance across interactive environments…
…State of the art approaches are either too costly, e.g., they require retraining, or fail to satisfy both performance and quality objectives in a scalable manner. To this end, we introduce…
…However, the performance of consistency-distilled models often degrades as more sampling steps are allocated at test time, limiting their effectiveness for any-step video diffusion. This limitation arises because consistency distillation…
…increasing the amount of PhoneWorld supervision strongly improves PhoneWorld performance, and under a fixed PhoneWorld budget, expanding app coverage yields even larger gains. Overall, PhoneWorld shifts the focus from building one mobile…
…stages to improve performance in complex agentic environments. AI-generated summary Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which…
…noise diffusion for domain harmonization from residual diffusion for semantic mapping, enhancing data efficiency and performance. Generated by Qwen/Qwen2.5-Coder-32B-Instruct We propose Decoupled Residual Denoising Diffusion models (DRDD…
…a parallel visual memory path that retrieves from a fixed visual token bank and gates it back into the main stream, so perception doesn't fade as text length grows. i’ve…
…Yet, recent progress in LLM coding has focused on well-defined tasks such as feature implementation, bug fixing, and competitive programming . Open-ended coding remains a weak spot for LLMs, largely because…
…Minbeom Kim , , , , , , , , Abstract LiSA enables adaptive safety guardrails for AI agents by converting occasional failures into reusable policy abstractions and using evidence-aware confidence gating to improve performance under sparse and noisy…
…A per-query oracle on the frozen base model exceeds contrastive fine-tuning at the same fixed budget, pointing to adaptive budget selection as future work. Code is available at https://github…