Tag
This article explains why cancellation of Windows Runtime asynchronous activities is asynchronous, using code examples to illustrate how it avoids deadlocks, especially when progress callbacks trigger cancellation.
CONCORD is an asynchronous sparse aggregation framework for retrieval-augmented generation (RAG) under document isolation in device-cloud setups. It improves throughput and reduces communication by orders of magnitude by treating the cloud as an asynchronously arriving evidence source rather than a continuously synchronized co-generator.
A tweet highlights the potential of hillclimb RLMs to incentivize code block launching, referencing a new decentralized language model (DeLM) approach where agents coordinate asynchronously through shared context.
This paper introduces RACE-Sched, an asynchronous agentic framework that decouples real-time reactive scheduling from deliberative LLM-based reasoning to handle dynamic job shop scheduling problems, achieving superior performance over DRL and other baselines.
This paper presents PushCen-ADFL, a communication-efficient asynchronous decentralized federated learning framework that uses centroid-based messaging and bias-correction to improve accuracy and reduce communication overhead under heterogeneous conditions.
This paper introduces AsyncTool, a benchmark for evaluating LLM-based agents' asynchronous function calling abilities in multi-task scenarios with delayed tool responses. It proposes efficiency-oriented metrics and identifies key failure modes of current tool-using agents.
D-VLA proposes a high-concurrency distributed asynchronous reinforcement learning framework for Vision-Language-Action models, using plane decoupling and a swimlane pipeline to improve throughput and efficiency in large-scale embodied AI training.
AReaL is a fully asynchronous reinforcement learning system for LLM reasoning, achieving up to 2.57x training speedup over synchronous systems while maintaining or improving performance. It decouples generation and training to improve GPU utilization and includes optimizations like staleness-enhanced PPO.