PlanCompiler: A Deterministic Compilation Architecture for Structured Multi-Step LLM Pipelines

• URL: http://arxiv.org/abs/2604.13092v1
• Date: Wed, 08 Apr 2026 00:54:41 GMT
• Title: PlanCompiler: A Deterministic Compilation Architecture for Structured Multi-Step LLM Pipelines
• Abstract summary: We present PlanCompiler, a compilation architecture for structured pipelines that separates planning from execution through a typed node registry registry.<n>PlanCompiler produces a typed plan over a fixed registry of primitives, validates that plan against explicit structural and type constraints, and compiles only validated plans into executable Python.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) remain brittle in multi-step structured workflows, where errors compound across sequential transformations, validation stages, and stateful operations such as SQL persistence. We present PlanCompiler, a compilation architecture for structured LLM pipelines that separates planning from execution through a typed node registry, static graph validation, and deterministic compilation. Instead of relying on autoregressive chaining at runtime, the system first produces a typed JSON plan over a fixed registry of primitives, validates that plan against explicit structural and type constraints, and compiles only validated plans into executable Python. We evaluate the approach on a 300-task benchmark covering increasing workflow depth, SQL roundtrip persistence, and schema-themed stress tests. In this setting, PlanCompiler achieves 100% first-pass success on Sets A and B, 88% on Set C, 96% on Set D, 88% on schema-trap tasks, and 84% on SQL roundtrip tasks, outperforming direct free-form code-generation baselines from GPT-4.1 and Claude Sonnet on five of six benchmark sets and achieving 278/300 successes overall versus 202/300 and 187/300 for the two baselines, respectively. Across the full suite, planning cost is approximately \$0.356, compared with \$2.140 for GPT-4.1 and \$18.391 for Claude, while maintaining competitive end-to-end latency. These results suggest that, for registry-constrained structured data workflows, deterministic compilation can improve first-pass reliability and cost efficiency relative to free-form code generation. Residual failures are concentrated in two narrow classes: late output-contract errors on aggregation tasks and early type mismatches at the SQLite persistence boundary, clarifying both the benefits and the current limits of the approach.

Related papers

• SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams [55.90739575113059]
  We argue the missing unit of reuse is the solving procedure shared by a cluster of related tasks, and build SkillGLoW around it.<n>Across four benchmarks (mathematical reasoning, terminal automation, software repair, and embodied control) and three models, the priors gain 17.2 points (hard) over the no-skill baseline on average.
  arXiv  Detail & Related papers  (2026-09-02T07:31:18Z)
• P$^{3}$: Joint Program-and-Proof Planning for Verified Code Generation [19.3449645807529]
  Verified code generation asks a large language model (LLM) to generate both an executable program and a machine-checkable proof that the program meets a formal specification.<n>We observe that this sequential pipeline can be both ineffective and inefficient in practice.<n>Inspired by Dijkstra's view that a program and its correctness argument should be developed hand in hand, we propose $P3$.
  arXiv  Detail & Related papers  (2026-08-10T08:33:18Z)
• Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata [57.27430779838529]
  We present an exact and tractable algorithm for sampling from the constrained mean-field posterior under any constraint expressible as a finite automaton.<n>The approach guarantees constraint satisfaction by construction, supports both greedy and sampling-based decoding, and is compatible with parallel and block-wise decoding.<n> Empirical evaluations on Dream-7B and LLaDA-8 show substantial accuracy gains across various tasks.
  arXiv  Detail & Related papers  (2026-07-08T05:48:57Z)
• ZAS-SQL: Distilling Rules from Failures for Zero-Shot Text-to-SQL [4.477529152940812]
  Few-shot in-context learning methods built upon large language models (LLMs) achieve strong performance, yet their reliance on demonstrations limits cross-domain generalization.<n>We propose a fully zero-shot Text-to-Guided framework that distills core generation rules from failure cases through a Map-Reduce-based rule distillation pipeline.<n>The proposed framework achieves up to 87.2% and 88.6% execution accuracy on the Dev and Test sets, respectively, establishing a new zero-shot state-of-the-art.
  arXiv  Detail & Related papers  (2026-06-06T16:08:40Z)
• SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks [1.496156904825668]
  We propose textttSPIN, a planning wrapper that combines validated Directed Acyclic Graph (DAG) planning with prefix based execution control.<n>textttSPIN enforces a strict DAG contract through texttt_validate_plan_text and repair prompting.<n>On AssetOpsBench, across 261 scenarios, textttSPIN reduces tasks executed from 1061 to 623 and improves emphAccomplished from 0.638 to 0.706, while reducing tool calls from 11.81 to
  arXiv  Detail & Related papers  (2026-05-13T19:12:24Z)
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• BatchDAG: LLM-Planned Execution Graphs for Scalable Ad-Hoc Analysis Over Enterprise Data [0.0]
  BatchDAG is a system in which an LLM generates a typed acyclic graph (DAG) of operations.<n> BatchDAG processes queries over 50,000+ meetings in under 60 seconds.<n>In production at Brevian, BatchDAG processes queries over 50,000+ meetings in under 60 seconds.
  arXiv  Detail & Related papers  (2026-04-17T19:22:34Z)
• APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay [7.370176470430802]
  LLM-based autonomous agents lack persistent procedural memory.<n>We present APEX-EM, a non-parametric online learning framework that accumulates, retrieves, and reuses structured procedural plans.
  arXiv  Detail & Related papers  (2026-03-31T00:24:56Z)
• MagicAgent: Towards Generalized Agent Planning [73.21129030631421]
  We present textbfMagicAgent, a series of foundation models specifically designed for generalized agent planning.<n>We introduce a lightweight and scalable synthetic data framework that generates high-quality trajectories across diverse planning tasks.<n>We show that MagicAgent-32B and MagicAgent-30B-A3B achieve superior performance across diverse open-source benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T01:39:16Z)
• Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems [72.3575737073235]
  Multi-Agent Systems (MAS) solve complex tasks by coordinating multiple agents through.<n>Existing approaches generates either at task level or query level, but their relative costs and benefits remain unclear.<n>We show that query-level workflow generation is not always necessary, since a small set of top-K best task-level together already covers equivalent or even more queries.
  arXiv  Detail & Related papers  (2026-01-16T10:05:51Z)
• Programming over Thinking: Efficient and Robust Multi-Constraint Planning [54.77940831026738]
  SCOPE is a framework that disentangles query-specific reasoning from generic code execution.<n>SCOPE achieves state-of-the-art performance while lowering cost and latency.
  arXiv  Detail & Related papers  (2026-01-14T02:58:07Z)
• Thinkquel: A Model Dedicated to Text-to-dbt Using Synthetic Data and a Span-Aware Objective [2.5297878656953605]
  Thinkquel is a fine-tuned model for producing robust, portable, execution-validated queries.<n>TS-GRPO bridges the gap between token-level training signals and sequence-level execution rewards.
  arXiv  Detail & Related papers  (2025-09-30T19:04:53Z)
• Tree-Planner: Efficient Close-loop Task Planning with Large Language Models [63.06270302774049]
  Tree-Planner reframes task planning with Large Language Models into three distinct phases. Tree-Planner achieves state-of-the-art performance while maintaining high efficiency.
  arXiv  Detail & Related papers  (2023-10-12T17:59:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.