Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models

Xianliang Zeng; Zhanzhan Zhao

Home/Archive/arXiv

arXiv · 2609.22243

Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models

Xianliang Zeng·Zhanzhan Zhao

View original source ↗Read source document ↗Export metadata ↓

Abstract

Input-conditioned neural interventions raise a runtime question: what persists when one behavioral specification admits multiple actions whose validity depends on execution state? We introduce replay-gated neural execution, separating five objects: a persistent behavioral predicate, its state-indexed certified realization set, a transient action witness, a budget-limited finder, and execution authorization. Candidates undergo isolated FP32/BF16 replay of the frozen model; commitment additionally requires a valid run audit. Experiments on Qwen3-0.6B and SmolLM2-360M-Instruct establish distinct failure modes for these objects. Independent initializations yield distinct certified actions in all 24 tested fixed-state cells. Unchanged SmolLM2 witnesses remain certified in all 128 native states but only 66 of 384 off-diagonal transfers. All 767 archived Qwen witnesses replay successfully, yet a budget-limited finder misses one known-realizable cell in all three prespecified runs. Of 1,141 replay-submitted candidates, 174 fail item certification. A frozen three-tier cascade uses these boundaries to reject uncertified proposals and escalate audit-valid search misses. On 256 previously sealed Qwen Fresh requests, 221 first certify at the lowest-cost tier and all 256 receive audited authorization, with no observed bypass. Relative to frozen full search, the median singleton search-and-certification cost ratio is 0.1055 and P95 is 1.3485, including failed tiers. Within the studied behavioral family on two small models, these results support state-indexed, set-valued execution semantics: specifications persist, search proposes witnesses, and replay certification plus run audit grants execution authority.

Explore related subjects

cs.CL cs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Xianliang Zeng, Zhanzhan Zhao. 2026-09-05. Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models. https://arxiv.org/abs/2609.22243

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

What is the Role of Small Models in the LLM Era: A Survey

Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning tasks, which leads to the development of increasingly large models. However, scaling up model sizes results in significantly higher computational costs and energy consumption, which makes these models impractical for academic researchers and businesses with limited resources. At the same time, Small Models (SMs) are frequently used in practical settings, although their significance is currently underestimated. This raises important questions about the role of small models in the era of LLMs, a topic that has received limited attention in prior surveys. In this work, we systematically examine the relationship between LLMs and SMs from two key perspectives: Collaboration and Competition (or Complementarity). We hope this survey provides valuable insights for practitioners, fostering a deeper understanding of the contribution of small models and promoting more efficient use of computational resources.

cs.CL↗

arXiv2026

SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine

Large Language Models with chain-of-thought prompting, such as OpenAI-o1, have shown impressive capabilities in natural language inference tasks. However, Multi-hop Question Answering (MHQA) remains challenging for many existing models due to issues like hallucination, error propagation, and limited context length. To address these challenges and enhance LLMs' performance on MHQA, we propose the Self-Guiding prompting Finite State Machine (SG-FSM), designed to strengthen multi-hop reasoning abilities. Unlike traditional chain-of-thought methods, SG-FSM tackles MHQA by iteratively breaking down complex questions into sub-questions, correcting itself to improve accuracy. It processes one sub-question at a time, dynamically deciding the next step based on the current context and results, functioning much like an automaton. Experiments across various benchmarks demonstrate the effectiveness of our approach, outperforming strong baselines on challenging datasets such as Musique. SG-FSM reduces hallucination, enabling recovery of the correct final answer despite intermediate errors. It also improves adherence to specified output formats, simplifying evaluation significantly.

cs.CL↗

arXiv2026

A Course Intelligence Platform for Higher Education: Lessons from AI-Assisted Course Evaluation

The rapid adoption of generative AI has created new opportunities for teaching, learning, and quality assurance. Existing applications, however, remain largely student-facing, with comparatively limited attention to institution-level needs. This paper presents a course intelligence platform deployed across more than 100 universities and serving over 10,000 instructors in China. By linking competency requirements, knowledge structures, teaching activities, and assessment evidence, it establishes a shared foundation for knowledge organization, instructional design, learning assessment, and quality evaluation. The course evaluation module is examined as a representative institution-facing application of the platform, which integrates national evaluation standards, structured educational evidence, customized prompting strategies, and domain-adapted LLMs to generate quantitative scores and qualitative feedback. A case study involving 100 authentic university courses is conducted to evaluate its alignment with expert judgments and the interpretability of its outputs. Statistical analyses show substantial agreement between AI-generated assessments and expert ratings, while qualitative results highlight the credibility of the feedback. The findings further suggest that AI-assisted evaluation requires not only capable models but also structured domain knowledge and transparent criteria. In this context, human ratings should be treated as an informative reference rather than an error-free gold standard, and the objective is to achieve consistent, interpretable, and defensible judgments instead of merely replicating expert scores.

cs.CL↗