Related papers: An LLM Compiler for Parallel Function Calling

Code synthesis, which requires a deep understanding of complex natural language problem descriptions, generation of code instructions for complex algorithms and data structures, and the successful execution of comprehensive unit tests,…

Generative AI and LLMs in particular are heavily used nowadays for various document processing tasks such as question answering and summarization. However, different LLMs come with different capabilities for different tasks as well as with…

LLM-driven web agents operating through continuous inference loops -- repeatedly querying a model to evaluate browser state and select actions -- exhibit a fundamental scalability constraint for repetitive tasks. We characterize this as the…

Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action;…

Large language models (LLMs) are increasingly used for generating parallel scientific codes, with a primary focus on generating functionally correct code. Recent work has focused on generating performant code, with an emphasis on its…

Crary and Sullivan's Relaxed Memory Calculus (RMC) proposed a new declarative approach for writing low-level shared memory concurrent programs in the presence of modern relaxed-memory multi-processor architectures and optimizing compilers.…

While enabling large language models to implement function calling (known as APIs) can greatly enhance the performance of Large Language Models (LLMs), function calling is still a challenging task due to the complicated relations between…

LLMs are increasingly used as general-purpose reasoners, but long inputs remain bottlenecked by a fixed context window. Recursive Language Models (RLMs) address this by externalising the prompt and recursively solving subproblems. Yet…

In the era of diminishing returns from Moores Law, heterogeneous computing systems have emerged as a vital approach to enhance computational efficiency. This paper introduces a novel MLIR-based dialect, named hyper, designed to optimize…

Recent advanced LLM-powered agent systems have exhibited their remarkable capabilities in tackling complex, long-horizon tasks. Nevertheless, they still suffer from inherent limitations in resource efficiency, context management, and…

Compound AI applications, which compose calls to ML models using a general-purpose programming language like Python, are widely used for a variety of user-facing tasks, from software engineering to enterprise automation, making their…

Augmented Large Language Models (LLMs) enhance the capabilities of standalone LLMs by integrating external data sources through API calls. In interactive LLM applications, efficient scheduling is crucial for maintaining low request…

Lazy search algorithms have been developed to efficiently solve planning problems in domains where the computational effort is dominated by the cost of edge evaluation. The existing algorithms operate by intelligently balancing…

Large Language Models (LLMs) enable intelligent multi-robot collaboration but face fundamental trade-offs: open-loop methods that compile tasks into formal representations for external executors produce sound plans but lack adaptability in…

Neural algorithmic reasoners are parallel processors. Teaching them sequential algorithms contradicts this nature, rendering a significant share of their computations redundant. Parallel algorithms however may exploit their full…

Modern deployment of large language models (LLMs) frequently involves both inference serving and continuous retraining to stay aligned with evolving data and user feedback. Common practices separate these workloads onto distinct servers in…

With the development of LLMs as agents, there is a growing interest in connecting multiple agents into multi-agent systems to solve tasks concurrently, focusing on their role in task assignment and coordination. This paper explores how LLMs…

In the past few years, Large Language Models (LLMs) have exploded in usefulness and popularity for code generation tasks. However, LLMs still struggle with accuracy and are unsuitable for high-risk applications without additional oversight…

Reasoning-augmented search agents such as Search-R1, trained via reinforcement learning with verifiable rewards (RLVR), demonstrate remarkable capabilities in multi-step information retrieval from external knowledge sources. These agents…

Recent advances in Large Language Models (LLMs) demonstrate that chain-of-thought prompting and deep reasoning substantially enhance performance on complex tasks, and multi-agent systems can further improve accuracy by enabling model…