…Results show that explicit evidence organization improves traceability and factual support, but gains depend strongly on the decision family. Diagnostics reveal a recurring evidence-decision decoupling: agents may cite relevant evidence while…
…To provide learning signals for curation, we design composite rewards and train on grouped task streams based on skill-relevant task dependencies, where earlier trajectories update the SkillRepo, and later related tasks…
…We propose a general multi-agent setup in which a manager model decomposes computer use tasks as a directed acyclic graph (DAG), encoding relevant dependencies and goals for subagents. At each iteration…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Retrieval-augmented generation is moving beyond text into long, egocentric video , where systems must select query-relevant chunks across multiple modalities and temporal granularities…
…Empirically, despite the lightweight reward, our RL-trained models effectively extract and apply relevant linguistic information from the provided context, leading to better translations on completely unseen languages than in-context learning…
…Specifically, for the e dit ing region specified by the user mask, we retain all tokens within a dilated mask to preserve strong locality and contextual relevance. Outside the e dit ing…
…a small frozen LLM reads the decision-time state and dialogue; its answer is discarded, and its hidden state becomes a decision-oriented feature, making the LLM an encoder rather than a…
…Across this sweep, it reduces answer-time visual-token load by up to 1,500x and query TTFT by 6-80x, while preserving video-faithful outputs. We also find that independently generated…
…To disentangle long-range subject evidence from short-range cues, Memento introduces a dual-query memory mechanism , where one query retrieves identity-relevant memory and the other selects short-context keyframes for…
…the art for fine-grained inference-time sparse attention by introducing a learned token-wise indexer that scores every prefix token and selects the most relevant ones for the main attention. To…