Related papers: Seer: Online Context Learning for Fast Synchronous…

In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent sequences. However, we discover a counterintuitive…

While Reinforcement Learning ( RL) has made great strides towards solving increasingly complicated problems, many algorithms are still brittle to even slight environmental changes. Contextual Reinforcement Learning (cRL) provides a…

Retrieval Augmented Generation (RAG) has emerged as a crucial technique for enhancing the accuracy of Large Language Models (LLMs) by incorporating external information. With the advent of LLMs that support increasingly longer context…

User queries in e-commerce search are often vague, short, and underspecified, making it difficult for retrieval systems to match them accurately against structured product catalogs. This challenge is amplified by the one-to-many nature of…

The context window of large language models (LLMs) has been extended significantly in recent years. However, while the context length that the LLM can process has grown, the capability of the model to accurately reason over that context…

In the last decade, Reinforcement Learning (RL) has achieved remarkable success in the control and decision-making of complex dynamical systems. However, most RL algorithms rely on the Markov Decision Process assumption, which is violated…

Collaborative edge computing uses edge nodes in different locations to execute tasks, necessitating dynamic task offloading decisions to maintain low latency and high reliability, especially under unpredictable node failures. Although deep…

Recent advancements in Large Language Models (LLMs) have significantly enhanced their capacity to process long contexts. However, effectively utilizing this long context remains a challenge due to the issue of distraction, where irrelevant…

Evaluating production LLM responses and routing requests across providers in LLM gateways requires fine-grained quality signals and operationally grounded decisions. To address this gap, we present SEAR, a schema-based evaluation and…

In real-world applications, automatic speech recognition (ASR) systems must handle overlapping speech from multiple speakers and recognize rare words like technical terms. Traditional methods address multi-talker ASR and contextual biasing…

Reinforcement Learning (RL) has emerged as a transformative approach for aligning and enhancing Large Language Models (LLMs), addressing critical challenges in instruction following, ethical alignment, and reasoning capabilities. This…

Large Language Models (LLMs) can perform zero-shot learning on unseen tasks and few-shot learning on complex reasoning tasks. However, resource-limited mobile edge networks struggle to support long-context LLM serving for LLM agents during…

Test-time scaling improves the inference performance of Large Language Models (LLMs) but also incurs substantial computational costs. Although recent studies have reduced token consumption through dynamic self-consistency, they remain…

Reinforcement Learning (RL) has become a cornerstone for improving the performance of Large Language Models (LLMs). However, its rollout phase constitutes a significant efficiency bottleneck, mainly arising from the long-tail bubbles across…

Reinforcement learning (RL) is a framework for solving sequential decision-making problems. In this work, we demonstrate that, surprisingly, RL emerges during the inference time of large language models (LLMs), a phenomenon we term…

In this work, we review research studies that combine Reinforcement Learning (RL) and Large Language Models (LLMs), two areas that owe their momentum to the development of deep neural networks. We propose a novel taxonomy of three main…

Though significant advancements have been achieved in developing long-context large language models (LLMs), the compromised quality of LLM-synthesized data for supervised fine-tuning (SFT) often affects the long-context performance of SFT…

Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue histories grow in length and accumulate noise, current…

Large Language Model (LLM) agents tackle data-intensive tasks such as deep research and code generation. However, their effectiveness depends on frequent interactions with knowledge sources across remote clouds or regions. Such interactions…

In the training process of Deep Reinforcement Learning (DRL), agents require repetitive interactions with the environment. With an increase in training volume and model complexity, it is still a challenging problem to enhance data…