The paper investigates when a language‑model judge can truly ground its verdicts in code correctness. It shows that current multi‑agent verification methods rely on evidence that is both independent of the answer and distinct between candidates—conditions that fail in code judging. By analyzing two label‑free measurements from the judge’s logs, the authors demonstrate that gating on one measurement allows the system to decline uncertain comparisons, improving accuracy from 20.7% to 36.9% while still answering half of all cases.
By Salma Roshdy Aly, Hussein Assaf, Ziad Kobti
arXiv:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.
By Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu, Pratinav Seth
arXiv:2605.06161v2 Announce Type: replace
Abstract: LLM-as-a-Judge pipelines have become the de facto evaluator for agent safety, yet existing benchmarks treat their verdicts as ground-truth proxies...
By Shihao Weng, Yang Feng, Xiaofei Xie
The paper investigates how personalized agents decide to use, ignore, update, or query retrieved user memory before acting on a task. An empirical audit protocol is developed to test structured intermediate outputs, revealing that while exposing state definitions improves accuracy, an explicit state-output field does not significantly enhance policy accuracy for large language models. The study also shows that example-level accuracy overstates consistency, with full four‑way family success being rare, and that providing benchmark‑associated state labels merely conditions predictions rather than proving internal fidelity.
By Yihang Chen, Pin Qian, Su Wang, Chong Peng, Huan Xu, Shuaiting Li, Yiqi Sun
arXiv:2609.13174v1 Announce Type: cross
Abstract: California recently required all prosecutors in the state to conduct a "race-blind charging" decision by reviewing case documents in which selected r...
By Muskan Walia, Joe Nudell, Alex Chohlas-Wood
The paper investigates whether the object selected in a grounded language‑model pipeline actually reaches the reader, a failure that can break the handoff between stages. By auditing 600 HybridQA questions across three selector families, the authors find that exact key lookup and title matching recover the selected object in all 1,463 resolvable records, but body‑only BM25 omits it in 26.6% of cases at cutoff five, while hybrid retrieval with reranking omits it only 1.0%. The study also shows that misalignment between selected and retrieved objects can reduce exact match scores by up to 31 points, and introduces the Returned‑Object Profile (ROP) as a tool for reproducible auditing.
By Siddharth Vohra, Runmin Jiang, Xiaomo Li, Min Xu
Operational reporting for high-performance computing (HPC) facilities requires combining information from monitoring services, schedulers, incident and maintenance records, storage measurements, perio...
The paper proposes a new reporting standard for attributing agent failures to their history, insisting on intervention‑verified evidence rather than post‑hoc taxonomies. It outlines a method to freeze an executable mid‑trajectory state, alter only the agent’s perceived history, and continue execution to obtain a measured replay certificate. The authors review existing manipulation classes and highlight that while several methods perform interventions, none currently report a quantified replay certificate, and they provide two cautionary examples illustrating the pitfalls of lacking such verification.
By Egor Pakhomov, Erik Nijkamp
The paper reports that a model can pass fidelity checks—verifying that extracted values match the source—without actually opening a datasheet, due to a hidden constraint that disables tool use. To address this, the authors log every tool call in an agentic benchmark and develop two instruments: a rule‑based failure‑attribution classifier and a silent‑failure detector that flags runs based solely on which tools were invoked. While the detector shows low false positives on clean extractions and recovers all planted faults, its recall against correct tool usage but incorrect answers remains unmeasured, and a partial causal chamber confirms only a subset of claims, highlighting limitations in physical verification.
By Qing Ye, Meng-Hsuan Lin
arXiv:2607. 16019v1 Announce Type: new Abstract: AI systems increasingly retrieve from records that revise themselves: issue threads, encyclopedic histories, policy logs, and long conversations.
By Zhaoyang Jiang, Zhizhong Fu, Zicheng Li, Yunsoo Kim, Jiacong Mi, Xuanqi Peng, Fei Teng, Honghan Wu
The paper introduces the twin‑prefix framework to evaluate how the size of the verification unit—i.e., how many actions a pre‑execution LLM monitor reviews in one call—affects its performance. By pairing each gold plan with a twin that differs by a single write and injecting a controlled error, the authors isolate the impact of review length on catch rates and false rejections. Their findings show that longer review windows increase rejection rates but do not improve discrimination, with the highest informedness occurring at one or two actions across all judges and domains.
By Yuchen Han, Cheng Yan, Wuyang Zhang
The paper audits the reproducibility of knowledge‑graph extraction from threat reports by re‑implementing matching rules for only five of twelve systems and re‑scoring ten system outputs under eight protocols. The audit shows that different matching protocols can reverse most pairwise system rankings and that a fixed prediction set can vary from 0.16 to 0.70 F1. The authors also build CTIForge to isolate validation effects, finding that validation changes precision across backbones and increases entity‑type disputes, and they release the full pipeline, protocol suite, and audit records.
By Safayat Bin Hakim, Houbing Herbert Song