TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments

• URL: http://arxiv.org/abs/2605.04107v1
• Date: Mon, 04 May 2026 15:35:45 GMT
• Title: TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments
• Abstract summary: Production agent frameworks transmit tool schemas as MCP, a format designed for machine parsing, not for interpretation by language models.<n>For small models (4B-14B), this protocol mismatch accounts for the majority of tool-use failure at production sizes.<n>We present TSCG, a deterministic tool-schema compiler that resolves this mismatch at the API boundary.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, not for interpretation by language models. For small models (4B-14B), this protocol mismatch accounts for the majority of tool-use failure at production catalog sizes. We present TSCG, a deterministic tool-schema compiler that resolves this mismatch at the API boundary, converting JSON schemas into token-efficient structured text without model access, fine-tuning, or runtime search. TSCG combines eight composable operators with a formal compression bound (>=51% on well-formed schemas). On TSCG-Agentic-Bench (about 19,000 calls, 12 models, 5 scenarios), TSCG restores Phi-4 14B from 0% to 84.4% accuracy at 20 tools (90.3% at 50 tools) and achieves 108-181% accuracy-retained ratio across three models on BFCL. Format-versus-compression decomposition (R^2=0.88 -> 0.03) establishes representation change as the dominant mechanism. Per-operator isolation across three frontier models reveals three distinct operator-response profiles: operator-hungry (Opus 4.7), operator-sensitive (GPT-5.2), and operator-robust (Sonnet 4), providing per-model deployment guidance. Scaling experiments show accuracy advantages persisting on heavy production MCP schemas (+5.0 pp at about 10,500 input tokens) despite saturation on light synthetic catalogs, with 52-57% token savings throughout. The synthetic benchmark generalizes to real MCP schemas within 0.1 accuracy points. TSCG ships as a 1,200-line zero-dependency TypeScript package.

Related papers

• Joint Optimization of Tool Creation and Use for Large Language Model Agents [69.07066297088187]
  SMITH (-grounded Multi-task Iterative Tool Honing) trains tool creation and tool use inside a single policy.<n>A 4B Qwen3 trained with SMITH on 13 procedural reasoning tasks with exact verifiers reaches 79.8 macro-average accuracy on held-out tasks.<n>It also reaches 40.4 on TabMWP-Hard and 42.6 on out-of-domain GQA (+7.6 over the best same-backbone inference-time baseline)
  arXiv  Detail & Related papers  (2026-08-25T13:59:34Z)
• Notation Matters: A Benchmark Study of Token-Optimized Formats in Agentic AI Systems [0.0]
  Large language models in Agentic AI systems consume tool schemas and execution results as structured data.<n>Recent work proposes token-optimized alternatives such as TOON (Token-Oriented Object Notation) and TRON (Token Reduced Object Notation) as more compact replacements.<n>We evaluate TOON and TRON on four agentic benchmarks (BFCL, MCPBenchPP, MCP-Universe, StableTool) and five open-weight LLMs.
  arXiv  Detail & Related papers  (2026-05-28T09:38:13Z)
• Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets [0.0]
  Agentic RAG systems that equip language models with dozens to hundreds of tool definitions face a critical resource conflict.<n>We present the first systematic study of this tool-context trade-off, evaluating 14 models spanning 1.5B-32B local models plus one frontier model across 6,566 controlled API calls.
  arXiv  Detail & Related papers  (2026-05-24T20:52:54Z)
• Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization [54.749573452394664]
  We find that accuracy collapses as instance data grows, even when the formulation itself is simple.<n>We address this via a simple inference-time approach, BIND, which externalizes numeric data to structured files so the model binds data rather than from prompt prompt.<n>We validate our hypothesis by finetuning a model exclusively on binding and show that it outperforms end-to-end SFT and RL across three structurally distinct optimization categories.
  arXiv  Detail & Related papers  (2026-05-20T21:25:41Z)
• Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs [46.60041435990374]
  We present FireFly, a pipeline for generating verified tool-call data from real-world MCP servers.<n>To handle the scale of real-world tool spaces, we build a pairwise tool graph and sample sub-DAGs.<n>Applying this pipeline yields 5,144 verified tasks spanning 240 servers and 993 tools.
  arXiv  Detail & Related papers  (2026-05-17T17:38:17Z)
• Template-as-Ontology: Configurable Synthetic Data Infrastructure for Cross-Domain Manufacturing AI Validation [0.0]
  A single Python configuration module serves as the specification for a time-stepped manufacturing simulator.<n>A five-layer pipeline--simulation, CDC/Iceberg lakehouse, star schema, and 12 parameterized AI tools--generates causally coherent, MES-shaped data.<n>The framework provides a reusable data layer for discrete manufacturing AI validation.
  arXiv  Detail & Related papers  (2026-05-11T21:36:05Z)
• When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models [2.064923532131528]
  Deployed language models must produce outputs that are both correct and format-compliant.<n>We study this structured-output reliability gap using two mathematical benchmarks -- GSM8K and MATH.<n>We develop AloLab, an iterative system-prompt requiring only black-box API access to the target model.
  arXiv  Detail & Related papers  (2026-05-04T09:07:44Z)
• VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents [1.06378109904813]
  VAREX is a benchmark for evaluating structured data extraction from government forms.<n>The benchmark comprises 1,777 documents with 1,771 unique documents with validated ground truth through three-phase quality assurance.<n>Results reveal that below 4B parameters, compliance output -- not extraction capability -- is a dominant bottleneck.
  arXiv  Detail & Related papers  (2026-03-16T11:15:56Z)
• Structured Context Engineering for File-Native Agentic Systems: Evaluating Schema Accuracy, Format Effectiveness, and Multi-File Navigation at Scale [0.0]
  Large Language Model agents increasingly operate systems through programmatic interfaces.<n>Yet practitioners lack empirical guidance on how to structure the context these agents consume.<n>We study 9,649 experiments across 11 models, 4 formats, and schemas ranging from 10 to 10,000 tables.
  arXiv  Detail & Related papers  (2026-02-05T08:39:05Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• HuggingR$^{4}$: A Progressive Reasoning Framework for Discovering Optimal Model Companions [50.61510609116118]
  HuggingR$4$ is a novel framework that combines Reasoning, Retrieval, Refinement, and Reflection to efficiently select models.<n>It attains a workability rate of 92.03% and a reasonability rate of 82.46%, surpassing existing method by 26.51% and 33.25% respectively.
  arXiv  Detail & Related papers  (2025-11-24T03:13:45Z)
• Schema Lineage Extraction at Scale: Multilingual Pipelines, Composite Evaluation, and Language-Model Benchmarks [3.3705400036304205]
  "Semantic drift" compromises data and governance, and impairs the utility of services like text-to-RAG.<n>This paper proposes a novel framework for the automated extraction of fine-grained schema lineage from multilingual enterprise pipeline scripts.<n>Result: A 32B open-source model, using a single reasoning trace, can achieve performance comparable to the GPT series under standard prompting.
  arXiv  Detail & Related papers  (2025-08-10T05:04:32Z)
• CoRT: Code-integrated Reasoning within Thinking [44.778344623138025]
  Large Reasoning Models (LRMs) like o1 and DeepSeek-R1 have shown remarkable progress in natural language reasoning with long chain-of-thought (CoT)<n>Addressing these limitations through computational tools is promising, but it introduces a technical challenge: Code Interpreter (CI) brings external knowledge beyond the model's internal text representations.<n>This paper introduces CoRT, a post-training framework for teaching LRMs to leverage CI effectively and efficiently.
  arXiv  Detail & Related papers  (2025-06-11T14:59:02Z)
• MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm [60.14048367611333]
  MonkeyOCR is a vision-language model for document parsing.<n>It advances the state of the art by leveraging a Structure-Recognition-Relation (SRR) triplet paradigm.
  arXiv  Detail & Related papers  (2025-06-05T16:34:57Z)
• SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints [59.645885492637845]
  SOPBench is an evaluation pipeline that transforms each service-specific SOP code program into a directed graph of executable functions.<n>Our approach transforms each service-specific SOP code program into a directed graph of executable functions and requires agents to call these functions based on natural language SOP descriptions.<n>We evaluate 18 leading models, and results show the task is challenging even for top-tier models.
  arXiv  Detail & Related papers  (2025-03-11T17:53:02Z)
• ToolACE: Winning the Points of LLM Function Calling [139.07157814653638]
  ToolACE is an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data.<n>We demonstrate that models trained on our synthesized data, even with only 8B parameters, achieve state-of-the-art performance on the Berkeley Function-Calling Leaderboard.
  arXiv  Detail & Related papers  (2024-09-02T03:19:56Z)

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.