REVIEW 14 cited by
An LLM Compiler for Parallel Function Calling
Not yet reviewed by Pith; the record is open.
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
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.
Forward citations
Cited by 14 Pith papers
-
Auto: The AGI Compiler
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.
-
OctoT2I: A Self-Evolving Agentic Text-to-Image Router
OctoT2I uses a no-supervision PSEL loop to discover model capability frontiers and route T2I tasks, reaching 0.96 GenEval score with 90.3% speedup over Flow-GRPO.
-
SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
SkCC compiles LLM skills via SkIR to achieve portability across agent frameworks, reduce adaptation effort from O(m×n) to O(m+n), and enforce security with reported gains in task success rates and token efficiency.
-
SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
SkCC introduces a typed intermediate representation and compiler pipeline to make LLM agent skills portable across frameworks and enforce security constraints before deployment.
-
Recursive Agent Harnesses
RAH improves coding performance on Oolong-Synthetic from 71.75% to 81.36% with fixed GPT-5 backbone by spawning subagent harnesses via executable scripts.
-
SCALE: Scalable Cross-Attention Learning with Extrapolation for Agentic Workflow Scheduling
SCALE is a DRL scheduler using cross-attention and SRR regularization that generalizes from 16 to 48 nodes without retraining and reduces response time by 8.9% at N=48 versus the unregularized version.
-
Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents
Slipstream uses asynchronous compaction with trajectory-grounded judge validation to improve long-horizon agent accuracy by up to 8.8 percentage points and reduce latency by up to 39.7%.
-
SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
SkCC compiles LLM agent skills through a strongly-typed IR and static security checks, cutting adaptation complexity from O(m×n) to O(m+n) and raising pass rates by 12-13 points on tested platforms.
-
PlanCompiler: A Deterministic Compilation Architecture for Structured Multi-Step LLM Pipelines
PlanCompiler uses a typed node registry, static validation, and deterministic compilation to reach 278/300 successes on structured LLM pipeline benchmarks, outperforming GPT-4.1 and Claude Sonnet baselines at lower cost.
-
Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse
Tree Training serializes tree trajectories via DFS and uses redundancy-free partitioning to compute weighted per-token losses exactly once per token, achieving up to 6.2x training speedup on dense and MoE models.
-
SGLang: Efficient Execution of Structured Language Model Programs
SGLang is a new system that speeds up structured LLM programs by up to 6.4x using RadixAttention for KV cache reuse and compressed finite state machines for output decoding.
-
What makes prompts a graph: necessary and sufficient conditions for prompt graph engineering
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...
-
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
Plan-and-Act trains a dedicated Planner on synthetic plan-annotated trajectories to generate high-level plans that an Executor follows, reaching 57.58% success on WebArena-Lite and 81.36% on WebVoyager.
-
LLM Enabled Multi-Agent System for 6G Networks: Framework and Method of Dual-Loop Edge-Terminal Collaboration
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.
Discussion (0). Sign in to comment.