Deterministic vs. LLM-Controlled Orchestration for COBOL-to-Python Modernization

• URL: http://arxiv.org/abs/2605.09894v1
• Date: Mon, 11 May 2026 02:34:27 GMT
• Title: Deterministic vs. LLM-Controlled Orchestration for COBOL-to-Python Modernization
• Abstract summary: Modernizing legacy systems remains difficult due to scarce expertise, large and long-liveds, and strict correctness requirements.<n>Recent large language model (LLM)-based modernization systems increasingly rely on agentic correctness in which the model controls multi-step tool execution.
• Score: 2.3754840025365183
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modernizing legacy COBOL systems remains difficult due to scarce expertise, large and long-lived codebases, and strict correctness requirements. Recent large language model (LLM)-based modernization systems increasingly rely on agentic workflows in which the model controls multi-step tool execution. However, it remains unclear whether delegating execution control to the LLM improves correctness, robustness, or efficiency in structured software engineering workflows. We present a controlled empirical study of deterministic and LLM-controlled orchestration for COBOL-to-Python modernization. Using a unified experimental framework, we hold the language models, prompts, tools, configurations, and source programs constant while varying only the execution control strategy. This isolates orchestration as the sole experimental variable. We evaluate both approaches using functional correctness, robustness across repeated stochastic runs, and computational efficiency. Across multiple models, deterministic orchestration achieves comparable computational accuracy to LLM-controlled orchestration while improving worst-case robustness and reducing performance variability across runs. Deterministic execution also reduces token consumption by up to 3.5x, leading to substantially lower operational cost. These results suggest that, in structured modernization workflows with explicit validation stages, fixed execution policies provide more stable and cost-efficient behavior than fully agentic orchestration without reducing translation quality.

Related papers

• Chiseling Out Efficiency: Structured Skeleton Supervision for Efficient Code Generation [61.72280804975896]
  Large Language Models (LLMs) are capable of generating syntactically correct and functionally complete programs, greatly streamlining software development.<n>Existing approaches to bridging this efficiency gap typically involve either iteratively optimizing code after generation or fine-tuning models on corpora of efficient code.<n>EffiSkel is an efficiency skeleton-guided framework that explicitly extracts and learns efficiency skeletons-abstract, reusable structural patterns efficient code.
  arXiv  Detail & Related papers  (2026-06-05T01:49:20Z)
• Evaluating Prompting and Execution-Based Methods for Deterministic Computation in LLMs [1.2957535240267326]
  Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning.<n>We systematically evaluate multiple prompting strategies, including Chain-of-Thought (CoT), Least-to-Most decomposition, Program-of-Thought (PoT), and Self-Consistency (SC)<n>Our results show that standard prompting methods achieve only moderate accuracy on sequence-based tasks.
  arXiv  Detail & Related papers  (2026-05-04T23:32:37Z)
• Execution-Verified Reinforcement Learning for Optimization Modeling [49.171122807323634]
  Execution-verified learning framework treats a mathematical programming solver as a deterministic, interactive verifier.<n>Experiments on NL4OPT, MAMO, IndustryOR, and OptiBench across Gurobi, OR-Tools, and COPT show that EVOM matches or outperforms process-supervised SFT.
  arXiv  Detail & Related papers  (2026-04-01T03:39:11Z)
• Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards [76.49428173793386]
  LLMs must invoke multiple dependent APIs in the correct order while propagating intermediate outputs.<n>Training models to handle such faces two obstacles: existing environments focus on simple per-turn function calls with simulated data, and binary rewards.<n>We present a framework addressing both challenges. First, we construct a reinforcement learning environment backed by a large-scale cache of real API responses, enabling a data synthesis pipeline that samples valid multi-step orchestration traces.<n>Second, we propose a graduated reward design that decomposes correctness into atomic validity and orchestration.
  arXiv  Detail & Related papers  (2026-03-25T18:31:39Z)
• Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective Correction [55.13278005189741]
  We model tool orchestration as learning a layered execution structure that captures high-level tool dependencies.<n>We introduce a schema-aware reflective correction mechanism that detects and repairs errors locally.<n>This design confines errors to individual tool calls and avoids re-planning entire execution trajectories.
  arXiv  Detail & Related papers  (2026-02-21T22:20:01Z)
• SHERPA: A Model-Driven Framework for Large Language Model Execution [5.595920727790909]
  SHERPA is a model-driven framework to improve the performance of large language models (LLMs) on complex tasks.<n>By explicitly incorporating domain-specific best practices into hierarchical state machines, SHERPA enables more fine-grained control over their behavior.
  arXiv  Detail & Related papers  (2025-08-29T23:14:21Z)
• Dynamic Benchmark Construction for Evaluating Large Language Models on Real-World Codes [33.80591142965565]
  We present CODE2BENCH, a pipeline for dynamically constructing robust and contamination-resistant benchmarks from real-world GitHub repositories.<n>Specifically, CODE2BENCH introduces three key innovations: (1) Automated Dynamism, achieved through periodic ingestion of recent code to minimize training data contamination; (2) Scope Graph-based dependency analysis, which enables structured classification of functions into benchmark instances with controlled dependency levels; and (3) Property-Based Testing (PBT) for the automated synthesis of rigorous test suites.
  arXiv  Detail & Related papers  (2025-08-10T05:06:36Z)
• Flow: Modularized Agentic Workflow Automation [53.073598156915615]
  Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution.<n>However, the effective adjustment of agentic during execution has not been well studied.<n>In this paper, we define an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by agents.<n>Our proposed multi-agent framework achieves efficient concurrent execution of subtasks, effective goal achievement, and enhanced error tolerance.
  arXiv  Detail & Related papers  (2025-01-14T04:35:37Z)
• Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification [76.14641982122696]
  We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. We show that our approach leads to an LLM that produces fewer inappropriate responses while achieving competitive performance on benchmarks and a toxicity detection task.
  arXiv  Detail & Related papers  (2024-10-07T23:38:58Z)
• ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness? [12.862825053595934]
  ECCO is a benchmark for evaluating program efficiency via two paradigms: natural language (NL) based code generation and history-based code editing. We find that adding execution information often helps maintain functional correctness, and NL feedback enhances more on efficiency.
  arXiv  Detail & Related papers  (2024-07-19T05:47:40Z)

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.