Large language models (LLMs) are used as post hoc explainers of sequential decision-making policies, producing natural-language explanations of why an action was chosen. However, LLMs often generate p...
The paper introduces SWE-Flux, a repository‑level benchmark designed to test large language models’ ability to reason about runtime behavior. It contains 480 execution‑grounded instances from 12 real Python repositories, with gold answers automatically harvested from instrumented test executions. Evaluation of five LLMs shows the task remains difficult, with the best model achieving only 37% accuracy, and the benchmark can generate challenging variants through input perturbation.
By Hamed Taherkhani, Mohammad Abdollahi, Melika Sepidband, Hridya Dhulipala, Tien N. Nguyen, Hadi Hemmati
arXiv:2605. 23965v2 Announce Type: replace Abstract: Large Language Models (LLMs) achieve strong performance on logical reasoning benchmarks, yet their reliability remains uncertain.
By Zenghui Zhou, Man Li, Xiaoke Fang, Xinyi Zhou, Weibin Lin, Zheng Zheng
arXiv:2608.17795v2 Announce Type: replace
Abstract: Text-to-SQL systems are commonly evaluated using ground-truth SQL queries or reference execution results, but such supervision is unavailable at in...
By Neelesh Kumar Shukla, Debasmita Panda, Srutanik Bhaduri, Aditya Banerjee, Vasu Rangarajan, Viji Krishnamurthy
The paper introduces "code explanations"—programs that describe how large language models (LLMs) generate outputs across a dataset, enabling automatic verification through execution. It defines a Consistency metric to assess how often a program reproduces the LLM’s outputs and evaluates this approach on three open‑source code‑capable LLMs across eight tasks, finding that code explanations are significantly shorter than chain‑of‑thought explanations and often better align with model behavior. However, consistency drops on tasks with complex linguistic components, and even with consistency feedback and execution, LLMs struggle to produce reliable explanations for these harder tasks.
By Nhi Nguyen, Shauli Ravfogel, Rajesh Ranganath
arXiv:2607. 11342v1 Announce Type: cross Abstract: Despite their central role in fault detection, test oracles remain challenging to construct effectively.
By Yue Zhao, Binish Tanveer, Jelena Zdravkovic
The paper introduces VERA, an automated framework that audits large language model (LLM) reasoning in software vulnerability analysis. Instead of relying on free‑form explanations, VERA requires models to produce a Structured Reasoning Record (SRR) that captures pointers, memory operations, and state transitions in machine‑readable fields. A multi‑stage judge then checks each SRR against eight reasoning failure modes, revealing that reasoning flaws are as common in correct verdicts as in incorrect ones and that VERA detects 87% of errors missed by free‑form LLM‑as‑judge evaluations.
arXiv:2606. 19588v1 Announce Type: new Abstract: Formal tools such as SAT and SMT solvers are increasingly embedded in language model reasoning pipelines when a safety or security critical question can be formulated in logic.
By Zunchen Huang, Songgaojun Deng
arXiv:2606. 03601v1 Announce Type: cross Abstract: While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.
By Qinyan Zhou, Peixin Zhang, Jun Sun, Haonan Zhang, Dongxia Wang
Detecting Inconsistencies in Model Specifications with LLM-as-Verifier Reasoning introduces VeriSpec, a method that audits natural‑language model specifications directly using an LLM as a verifier. VeriSpec extracts structured rules, builds a topic‑guided graph to cluster related rules, and applies LLM‑based reasoning to find inconsistencies. In a case study on the OpenAI Model Spec, it identified 405 rules, validated five inconsistencies, and outperformed five baselines with the highest precision and lowest cost per validated inconsistency.
By Zichen Xie, Mrigank Pawagi, Lize Shao, Yang Hu, Wenxi Wang
arXiv:2605. 15229v3 Announce Type: replace-cross Abstract: Existing code benchmarks measure whether an agent can produce any test that reproduces a known bug, or whether it can produce a patch that fixes a described issue.
By Lucas Jing, Xinqi Wang, Liao Zhang, Simon S. Du
LGMT is an open‑source tool that tests logical reasoning reliability in large language models by generating logically equivalent follow‑up test cases from a source premise‑conclusion pair and checking for consistency in the model’s entailment predictions. It includes 20 built‑in metamorphic relations, allows custom relations verified by the Z3 theorem prover, and can be run via CLI or a web studio, even offline without an API key. In experiments on six popular LLMs across 3,091 metamorphic groups, LGMT uncovered inconsistency rates between 20.84% and 29.44%.
By Zenghui Zhou, Xiaoke Fang, Zheng Zheng