SPL: Orchestrating Workflows with Declarative Deterministic-Probabilistic Composition
Not on the map. Why?
Abstract (arXiv)
We present SPL (Structured Prompt Language), a declarative language that composes deterministic and probabilistic computation modes in a single specification. While existing frameworks separate these -- orchestration systems (AutoGen, CrewAI, LangGraph) for LLM calls, symbolic tools (SymPy, SageMath, Lean) for computation -- SPL unifies them. It provides GENERATE/EVALUATE for probabilistic computation and SOLVE/ASSERT for deterministic computation, sharing syntax, variable bindings, and runtime routing. A .spl specification runs unchanged across local nodes (Ollama), cloud APIs (OpenRouter, Anthropic), and distributed grids (Momagrid), with model and verifier selection deferred to invocation time. We validate SPL through an extensive 78-recipe cookbook and a controlled 1,200-run experiment (10 models x 20 problems x 2 arms x 3 repetitions; the 20 problems span 6 difficulty tiers). The solver arm achieves 82-93% machine-verified correctness (sonnet-4-6: 85%, gemma4:e2b: 93%) while the LLM-only arm measures output production without mathematical verification, making the comparison one of verified correctness against unverified fluency. A backend difficulty gradient emerges (SymPy 78%, Sage 54%), and the dominant failure mode is solver_error (kernel-rejected expressions), not format non-compliance.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 18 references that are in the map. First posted on arXiv 6 Jul 2026.
Builds on
11 of 18 references.
References · 11
- 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
- 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
- 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
- 2023LeanDojo: Theorem Proving with Retrieval-Augmented Language Modelscited by 414
- 2022HyperTree Proof Search for Neural Theorem Provingcited by 192
- 2025Blueprint First, Model Second: A Framework for Deterministic LLM Workflowcited by 11
- 2024MCP-Solver: Integrating Language Models with Constraint Programming Systemscited by 9
- 2025Open Agent Specification (Agent Spec): A Unified Representation for AI Agentscited by 5
- 2026Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automationcited by 3
- 2026Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflowscited by 2
- 2026DUPLEX: Agentic Dual-System Planning via LLM-Driven Information Extractioncited by 1
Built on by
Not cited yet.