Related papers: SimpleTool: Parallel Decoding for Real-Time LLM Fu…

Large language model (LLM)-based multi-agent systems have demonstrated remarkable promise for tackling complex tasks by breaking them down into subtasks that are iteratively planned, executed, observed, and refined. Despite their…

As text generation has become a core capability of modern Large Language Models (LLMs), it underpins a wide range of downstream applications. However, most existing LLMs rely on autoregressive (AR) generation, producing one token at a time…

Diffusion large language models (dLLMs) represent a significant advancement in text generation, offering parallel token decoding capabilities. However, existing open-source implementations suffer from quality-speed trade-offs that impede…

Large Language Models (LLMs) are widely adopted for assisting in software development tasks, yet their performance evaluations have narrowly focused on the functional correctness of generated code. Human programmers, however, require…

As large language models gain widespread adoption, running them efficiently becomes crucial. Recent works on LLM inference use speculative decoding to achieve extreme speedups. However, most of these works implicitly design their algorithms…

How do LLMs compare with symbolic tools on program synthesis tasks? We investigate this question on several synthesis domains: LTL reactive synthesis, syntax-guided synthesis, distributed protocol synthesis, and recursive function…

Evaluating the performance of LLMs in multi-turn human-agent interactions presents significant challenges, particularly due to the complexity and variability of user behavior. In this paper, we introduce HammerBench, a novel benchmark…

Decoder-only large language models (LLMs) have recently demonstrated impressive capabilities in text generation and reasoning. Nonetheless, they have limited applications in simultaneous machine translation (SiMT), currently dominated by…

Breakthroughs in the generative AI domain have fueled an explosion of large language model (LLM)-powered applications, whose workloads fundamentally consist of sequences of inferences through transformer architectures. Within this rapidly…

Recent advancements in large language models (LLMs) have significantly enhanced their reasoning capabilities. However, they continue to struggle with basic character-level tasks, such as counting letters in words, a problem rooted in their…

Large Language Models (LLMs) have excelled in various tasks but perform better in high-resource scenarios, which presents challenges in low-resource scenarios. Data scarcity and the inherent difficulty of adapting LLMs to specific tasks…

Inference accounts for the majority of latency and energy consumption in large language model (LLM) deployments, often exceeding 90% of total cost. While training-time efficiency has seen extensive progress, runtime optimization remains a…

Code large language models (LLMs) face limitations in repository-level code generation due to their lack of awareness of repository-level dependencies (e.g., user-defined attributes), resulting in dependency errors such as…

Large Language Models (LLMs) have demonstrated remarkable capabilities in software engineering, yet comprehensive benchmarks covering diverse SE activities remain limited. We present a multi-task evaluation of 11 state-of-the-art LLMs…

In robotic task planning, symbolic planners using rule-based representations like PDDL are effective but struggle with long-sequential tasks in complicated environments due to exponentially increasing search space. Meanwhile, LLM-based…

Real-time LLM interactions demand streamed token generations, where text tokens are progressively generated and delivered to users while balancing two objectives: responsiveness (i.e., low time-to-first-token) and steady generation…

Deploying Large Language Models (LLMs) on resource-constrained devices remains challenging due to limited memory, lack of GPUs, and the complexity of existing runtimes. In this paper, we introduce TranSQL+, a template-based code generator…

The widespread application of Large Language Models (LLMs) has motivated a growing interest in their capacity for processing dynamic graphs. Temporal motifs, as an elementary unit and important local property of dynamic graphs which can…

Multi-turn tool calling is essential for LLMs to function as autonomous agents, yet synthesizing the training data required for these capabilities remains a fundamental challenge. Existing synthetic data generation pipelines often produce…

To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to…