arXiv:2606. 03331v1 Announce Type: cross Abstract: Consumer device repair is an important but underexplored testbed for large language models (LLMs).
Consumer device repair is an important but underexplored testbed for large language models (LLMs). Repair tasks require reasoning over incomplete problem descriptions, hardware-specific diagnostics, actionable troubleshooting, and safety-critical decisions, where incorrect advice can cause device damage, battery hazards, or permanent data loss.
arXiv:2606. 16262v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as UX judges that inspect interfaces, diagnose usability problems, and propose repairs.
arXiv:2606. 29377v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) improves the factuality of large language models by grounding responses in external evidence, yet real-world deployments remain fragile.
The paper introduces a roundtrip verification method for ensuring that large language models (LLMs) produce faithful formalizations of natural language statements. By formalizing a statement, translating it back to natural language, re-formalizing, and checking logical equivalence with a formal tool, the approach detects inconsistencies without needing ground-truth annotations. When inconsistencies are found, a diagnosis localizes the error to a specific translation step, and a scoped repair operator attempts to correct it. The framework is evaluated on the Texas Transportation Code and Texas Parks and Wildlife Code using Claude Opus and GPT-5, showing that diagnosis-guided scoped repair is most effective and that rules failing the equivalence check exhibit significantly more natural language inference drift.
arXiv:2601. 05366v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed as agents that invoke external tools through structured function calls.
The paper evaluates how well open-weight large language models can repair Planning Domain Definition Language (PDDL) models using only LLMs. Experiments show that while the best LLM achieves an F1 score of 0.87—an improvement of 0.38 over a symbolic baseline—it still fails to reliably satisfy test constraints, with a mean test pass rate of only 0.82 and as low as 0.06 on the Thoughtful domain. The study concludes that current open-weight models cannot guarantee the necessary test constraint satisfaction for dependable automated model repair.
arXiv:2609.15684v1 Announce Type: new Abstract: Language agents increasingly rely on reusable skills, but post-failure repair is often handled by opaque one-shot reflection: a model generates a skill...
arXiv:2607. 25873v1 Announce Type: cross Abstract: Large Language Model (LLM)-based Automated Program Repair systems are advancing rapidly, yet their performance remains inconsistent.
arXiv:2609.34879v2 Announce Type: replace Abstract: Tool agents use large language models to act through external tools, yet successfully executed calls can still leave user requests unfulfilled. Too...
The paper evaluates lightweight, edge‑deployable large language models—Claude‑Haiku‑4.5, GPT‑5.4‑Mini, and Gemini‑3.1‑Flash‑Lite—on free‑text 5G domain knowledge and fault‑analysis tasks using three benchmarks (TeleQNA ORAN FT, 5G‑Faults FT, TeleInter FT). All models achieve at least 90% accuracy on fault diagnosis, but zero‑shot recall of 3GPP and O‑RAN specifications remains below 60%. Multi‑judge scoring yields a mean inter‑judge agreement of at least 0.90, and Gemini‑3.1‑Flash‑Lite emerges as the most efficient model for production telecom deployments.
The paper presents an end‑to‑end pipeline for translating natural language planning descriptions into PDDL problem instances using large language models. It incorporates multiple checks—syntactic parsing, planner success, domain conformance, an LLM critic, and iterative repair—to ensure faithfulness to the original task. Experiments on Planetarium, AutoPlanBench, and curated PDDL~2.1 problems reveal that operational success can diverge from benchmark‑reference reconstruction, and that structured repair improves outcomes while PDDL~2.1 remains challenging for reference reconstruction.
SafeTune is a source‑available library that consolidates four safety‑intervention paradigms—post‑hoc weight recovery, safety‑constrained fine‑tuning, gradient‑based unlearning, and inference‑time steering—into a single, configuration‑driven workflow. It offers shared interpretability, evaluation, and deployment tools, and its modular registry allows easy addition of new methods, benchmarks, judges, models, and fine‑tuning domains. The authors demonstrate SafeTune with controlled comparisons and case studies in finance and medical deployments, showing how it characterizes safety drift, evaluates interventions on refusal‑behavior and capability metrics, and supports calibrated or layered mitigation.