Dynamic Stability of LLM-Generated Code

• URL: http://arxiv.org/abs/2511.07463v1
• Date: Wed, 12 Nov 2025 01:00:59 GMT
• Title: Dynamic Stability of LLM-Generated Code
• Authors: Prateek Rajput, Abdoul Aziz Bonkoungou, Yewei Song, Abdoul Kader Kabore, Iyiola E. Olatunji, Jacques Klein, Tegewende Bissyande,
• Abstract summary: Current evaluations of LLMs for code generation overlook the fact that functionally correct solutions can differ significantly in algorithmic complexity.<n>We introduce a principled framework for evaluating the dynamic stability of generated code.<n>Our findings call for stability-aware objectives in code generation and new benchmarks with test cases for robust, real-world evaluation.
• Score: 6.120340803716395
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Current evaluations of LLMs for code generation emphasize functional correctness, overlooking the fact that functionally correct solutions can differ significantly in algorithmic complexity. For instance, an $(O(n^2))$ versus $(O(n \log n))$ sorting algorithm may yield similar output but incur vastly different performance costs in production. This discrepancy reveals a critical limitation in current evaluation methods: they fail to capture the behavioral and performance diversity among correct solutions. To address this, we introduce a principled framework for evaluating the dynamic stability of generated code. We propose two metrics derived from opcode distributions: Static Canonical Trace Divergence (SCTD), which captures algorithmic structure diversity across generated solutions, and Dynamic Canonical Trace Divergence (DCTD), which quantifies runtime behavioral variance. Their ratio, the Behavioral Expression Factor (BEF), serves as a diagnostic signal: it indicates critical runtime instability when BEF $\ll$ 1 and functional redundancy when BEF $\gg$ 1. Empirical results on BigOBench and CodeContests show that state-of-the-art LLMs exhibit significant algorithmic variance even among functionally correct outputs. Notably, increasing sampling temperature improves pass@1 rates but degrades stability, revealing an unrecognized trade-off: searching for correct solutions in diverse output spaces introduces a "penalty of instability" between correctness and behavioral consistency. Our findings call for stability-aware objectives in code generation and new benchmarks with asymptotic test cases for robust, real-world LLM evaluation.

Related papers

• SOLVAR: Fast covariance-based heterogeneity analysis with pose refinement for cryo-EM [1.739627424017212]
  Cryo-electron microscopy (cryo-EM) has emerged as a powerful technique for resolving the three-dimensional structures of macromolecules.<n>A key challenge in cryo-EM is characterizing continuous heterogeneity, where molecules adopt a continuum of conformational states.<n>Covariance-based methods offer a principled approach to modeling structural variability.
  arXiv  Detail & Related papers  (2026-02-19T18:28:46Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• Correctness isnt Efficiency: Runtime Memory Divergence in LLM-Generated Code [10.464512010462789]
  Large language models (LLMs) can generate programs that pass unit tests, but passing tests does not guarantee reliable runtime behavior.<n>We find that different correct solutions to the same task can show very different memory and performance patterns, which can lead to hidden operational risks.<n>We present a framework to measure execution-time memory stability across multiple correct generations.
  arXiv  Detail & Related papers  (2026-01-03T15:42:21Z)
• Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective [85.06838178922791]
  Reinforcement Learning (RL) has proven highly effective for autoregressive language models.<n>But adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges.<n>We propose a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy.
  arXiv  Detail & Related papers  (2025-12-03T13:05:32Z)
• Iterative Refinement of Flow Policies in Probability Space for Online Reinforcement Learning [56.47948583452555]
  We introduce the Stepwise Flow Policy (SWFP) framework, founded on the key insight that discretizing the flow matching inference process via a fixed-step Euler scheme aligns it with the variational Jordan-Kinderlehrer-Otto principle from optimal transport.<n>SWFP decomposes the global flow into a sequence of small, incremental transformations between proximate distributions.<n>This decomposition yields an efficient algorithm that fine-tunes pre-trained flows via a cascade of small flow blocks, offering significant advantages.
  arXiv  Detail & Related papers  (2025-10-17T07:43:51Z)
• Measuring LLM Code Generation Stability via Structural Entropy [4.812266013066678]
  We extend "structural-entropy concepts" to the program domain by pairing entropy with abstract syntax tree (AST) analysis.<n>We measure stability in two complementary ways: (i) Jensen-Shannon divergence, a symmetric, bounded indicator of structural overlap, and (ii) a Structural Cross-Entropy ratio that highlights missing high-probability patterns.<n>Unlike pass@k, BLEU, or CodeBLEU, our metrics are reference-free, language-agnostic, and execution-independent.
  arXiv  Detail & Related papers  (2025-08-19T22:07:12Z)
• Assessing Correctness in LLM-Based Code Generation via Uncertainty Estimation [0.0]
  We explore uncertainty estimation as a proxy for correctness in LLM-generated code.<n>We adapt two state-of-the-art techniques from natural language generation to the domain of code generation.<n>Our findings indicate a strong correlation between the uncertainty computed through these techniques and correctness.
  arXiv  Detail & Related papers  (2025-02-17T10:03:01Z)
• COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
  Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
  arXiv  Detail & Related papers  (2024-10-12T23:56:19Z)
• A Scale-Invariant Sorting Criterion to Find a Causal Order in Additive Noise Models [49.038420266408586]
  We show that sorting variables by increasing variance often yields an ordering close to a causal order. We propose an efficient baseline algorithm termed $R2$-SortnRegress that exploits high $R2$-sortability. Our findings reveal high $R2$-sortability as an assumption about the data generating process relevant to causal discovery.
  arXiv  Detail & Related papers  (2023-03-31T17:05:46Z)
• Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability [67.8426046908398]
  Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world. This paper presents MetaPG, an evolutionary method for automated design of actor-critic loss functions.
  arXiv  Detail & Related papers  (2022-04-08T20:46:16Z)
• Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning [99.34907092347733]
  We analyze the problem of estimating optimal $Q$-value functions for a discounted Markov decision process with discrete states and actions. Using a local minimax framework, we show that this functional arises in lower bounds on the accuracy on any estimation procedure. In the other direction, we establish the sharpness of our lower bounds, up to factors logarithmic in the state and action spaces, by analyzing a variance-reduced version of $Q$-learning.
  arXiv  Detail & Related papers  (2021-06-28T00:38:54Z)
• Convergence Analysis of the Hessian Estimation Evolution Strategy [3.756550107432323]
  Hessian Estimation Evolution Strategies (HE-ESs) update the covariance matrix of their sampling distribution by directly estimating the curvature of the objective function. We prove two strong guarantees for the (1+4)-HE-ES, a minimal elitist member of the family.
  arXiv  Detail & Related papers  (2020-09-06T13:34:25Z)
• Distributional Robustness and Regularization in Reinforcement Learning [62.23012916708608]
  We introduce a new regularizer for empirical value functions and show that it lower bounds the Wasserstein distributionally robust value function. It suggests using regularization as a practical tool for dealing with $textitexternal uncertainty$ in reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-05T19:56:23Z)

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.