Pith. sign in

REVIEW 8 cited by

An LLM Compiler for Parallel Function Calling

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.04511 v3 pith:HMKEVTED submitted 2023-12-07 cs.CL

Sehoon Kim , Suhong Moon , Ryan Tabrizi , Nicholas Lee , Michael W. Mahoney , Kurt Keutzer , Amir Gholami This is my paper · ORCID
classification cs.CL
keywords functioncallingllmcompilerparallelcallstaskscostfunctions
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The reasoning capabilities of the recent LLMs enable them to execute external function calls to overcome their inherent limitations, such as knowledge cutoffs, poor arithmetic skills, or lack of access to private data. This development has allowed LLMs to select and coordinate multiple functions based on the context to tackle more complex problems. However, current methods for function calling often require sequential reasoning and acting for each function which can result in high latency, cost, and sometimes inaccurate behavior. To address this, we introduce LLMCompiler, which executes functions in parallel to efficiently orchestrate multiple function calls. Drawing inspiration from the principles of classical compilers, LLMCompiler enables parallel function calling with three components: (i) a Function Calling Planner, formulating execution plans for function calling; (ii) a Task Fetching Unit, dispatching function calling tasks; and (iii) an Executor, executing these tasks in parallel. LLMCompiler automatically generates an optimized orchestration for the function calls and can be used with both open-source and closed-source models. We have benchmarked LLMCompiler on a range of tasks with different patterns of function calling. We observe consistent latency speedup of up to 3.7x, cost savings of up to 6.7x, and accuracy improvement of up to ~9% compared to ReAct. Our code is available at https://github.com/SqueezeAILab/LLMCompiler.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Auto: The AGI Compiler

    cs.LG 2026-07 conditional novelty 7.0 of 10

    AUTO compiles witnessed-deterministic LLM-agent spans into verified WASM cognition binaries and recompiles on deopt, cutting cost 6.4× at 96.9% parity on a 300-item shifted stream.

  2. TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows

    cs.SE 2026-08 conditional novelty 6.0 of 10

    TraceCompiler recovers producer-consumer dependencies from noisy agent traces by admitting only uniquely-justified data flow and abstaining on ambiguity, achieving 0.928 precision on T1 versus 0.711 F1 for adjacency.

  3. DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering

    cs.AI 2025-07 conditional novelty 6.0 of 10

    DrafterBench is a new benchmark of 1,920 PDF drawing-revision tasks; on it, the best model (OpenAI o1) averages about 80/100, and all tested models fail hard on incomplete instructions and plan execution.

  4. An Agentic AI Framework Overcomes Fundamental Limitations of Large Language Models for Glaucoma Detection from Fundus Photography

    cs.AI 2026-08 conditional novelty 5.0 of 10

    A three-step agentic workflow with LLM function calling and reflection improved glaucoma classification, CDR estimation, and repeatability over LLM-alone baselines, approaching specialist-level accuracy.

  5. What makes prompts a graph: necessary and sufficient conditions for prompt graph engineering

    cs.AI 2026-07 conditional novelty 5.0 of 10

    The paper defines prompt graph engineering via four necessary and sufficient conditions (explicit structure, structure/content separation, executable semantics, first-class artifact) and an inclusion/exclusion test th...

  6. TimelyLLM: Segmented LLM Serving System for Time-sensitive Robotic Applications

    cs.RO 2024-12 conditional novelty 5.0 of 10

    TimelyLLM segments LLM-generated robot plans into executable pieces and schedules those pieces by urgency, reducing response delays for time-critical robot tasks.

  7. Less is More: Optimizing Function Calling for LLM Execution on Edge Devices

    cs.PF 2024-11 conditional novelty 5.0 of 10

    Selectively reducing the number of tools presented to an LLM, using embedding similarity over individual tools or clusters, improves function-calling success and efficiency on edge devices.

  8. LLM Enabled Multi-Agent System for 6G Networks: Framework and Method of Dual-Loop Edge-Terminal Collaboration

    cs.MA 2025-09 conditional novelty 4.0 of 10

    A dual-loop edge-terminal multi-agent framework, combining task decomposition with parallel tool calling and offloading, is shown in a simulated 6G urban safety case study to outperform ReAct and LLMCompiler.

Pith tools