Background. A component replacement in a language-model agent changes an execution trajectory, potentially altering later observations, resource use, and recovery opportunities. Different evidence is...
arXiv:2609.33153v2 Announce Type: replace-cross
Abstract: Reported improvements from tools and reusable skills in large language model agents refer to different comparisons. This critical narrative r...
By Shuyang Zhang
The paper introduces NAQD‑Env, a synthetic benchmark designed to test language agents’ ability to selectively withdraw and resume actions when new evidence, permissions, or stop instructions arise. It evaluates models against a deterministic reference policy across eleven dependency families, measuring policy agreement, task value, withdrawal, resumption, and event reporting. Experiments on 350 scenarios show low withdrawal recall, no valid resumption, and limited policy alignment, highlighting the need to treat selective withdrawal as a distinct reliability component.
By Mohamed Abouzahra
The paper investigates how fine‑tuned language agents can selectively withdraw actions when evidence changes or authority is revoked. Using a synthetic NAQD‑Env environment, the authors compare an original curriculum with an enriched one across multiple system‑prompt framings and evaluate four LoRA checkpoints of Qwen2.5‑3B‑Instruct against instruction‑tuned baselines. Results show that fine‑tuned checkpoints achieve higher decision agreement and withdrawal recall, reduce incorrect withdrawals, and narrow prohibited combinations, though they also omit valid event reports and exhibit mixed preservation of authorized actions.
By Mohamed Abouzahra
The paper introduces CTXGAP, a study measuring how much information coding agents omit from their user-facing reports compared to their full execution logs. Across 37 coding tasks, agents answer 93.6% of task-state questions when asked directly, but report-only readers recover only 52.0% of the same information, revealing a 40.7‑point gap. Even at final checkpoints of verified fixes, the gap remains significant, and detailed terminal scrollback improves recovery only to 73.6%. The study highlights that missing details in reports can leave supervisors unaware of failures, workarounds, and risks that need scrutiny.
By Guoyang Xu, Rui Zhang, Xiuyu Wu, Hao Chen
The study compared human and large language model (LLM) workflows for title‑and‑abstract screening in a complex scoping review. Human reviewers and two GPT‑5.4 file‑batch runs retained 42.2‑45.0% of records with 82.3‑82.9% recall, while Gemini 3.1 achieved the highest recall (83.9%) but retained 56.7% of records. Identical GPT‑5.4 runs showed 91.7% agreement yet differed on 94 records, including 29 verified eligible ones.
By Nikol Figalov\'a, Lynn Huestegge, Anne B\"ockler-Raettig
The paper investigates how language‑model judges can make version‑dependent errors when evaluating upgraded agents. Using 35 public coding‑agent submissions, two customer‑service agents, and over a thousand expert‑labeled trajectories, the authors show that fixed judges often reject task‑conditioned error invariance and can incorrectly approve failed patches, especially as agent capability increases. Paired audits of current outputs reduce interval width only marginally, and the study concludes that independent human patch review is still necessary.
By Jiapeng Li
The paper introduces TRAILS, a taxonomy of 38 mechanisms that can compromise the reliability of large language model (LLM) read‑and‑evaluate tasks in evidence synthesis, such as study screening, data extraction, risk‑of‑bias assessment, and critical appraisal. It explains how these mechanisms can cause inconsistent or hidden failures across repeated LLM runs and outlines deployment settings, testing approaches, and mitigation strategies for each. The authors argue that repeatability or accuracy alone does not guarantee trustworthy judgments, emphasizing the need for human evaluation to verify that decisions are evidence‑based, free from external influence, and reproducible.
By Carole Lunny, Ian Goodman, Stefano Berrone, Connor TA Brenna, Emma K Reid, Ivan Perez-Neri, Shailesh Kolekar, Nityanand Jain, Ashwin Kamath, Lucas HCC Santos, Yulia Otmakhova, Heba Hussein, Diana M Cespedes, Gioia Dahdal, Salmaan Kanji
The paper introduces TRACE, a protocol designed to diagnose whether changes in verifier scores for large language model agents reflect actual changes in agent behavior or merely alterations in the evaluation process. TRACE works by applying targeted changes to evaluation components, running paired experiments, and re‑scoring unchanged trajectories to isolate the source of score variation. Experiments on synthetic tasks and public benchmark tasks demonstrate that seemingly significant score shifts can often be attributed to evaluation artifacts, while TRACE can also detect genuine behavioral changes.
By Radhika Gaonkar
Large language models (LLMs) are increasingly used as integration layers above specialized diagnostic tools, but stronger components do not always yield stronger combined systems. Across five industrial fault‑diagnosis datasets, LLMs often overturned correct judgments when given conflicting external information, and none of the four datasets with direct integration comparisons showed a consistent advantage for implicit LLM integration over the stronger standalone source. In a Tennessee Eastman confirmation set, the integrated output improved LLM accuracy by 12.8 points but remained 5.9 points below the specialist alone, and a two‑source selector oracle achieved 92.76% accuracy, revealing complementarity that the integrated output did not fully realize.
By Donghwan Kim
Praxa is an evidence‑bound harness for governed AI agent execution that explicitly represents states such as proposal, authority, dispatch, verified external effect, and promotion through deterministic admission, brokered execution, external read‑back, reconciliation, and reviewed promotion. The authors report four evidence lanes: a repository‑local audit passing all unit and Workerd tests; a pilot on 12 curated tasks where both baseline and reliability‑layer arms passed 17 of 36 trials; a coordination‑proxy comparison where both baseline and a source‑authored candidate completed all 180 trials with equal accuracy but the candidate used fewer tokens and steps; and deployed source/configuration evidence showing bounded reflection, recall accounting, memory compilation, and tool‑health paths. None of the evidence demonstrates superiority in security, safety, or user benefit.
whyItMatters:"Praxa provides a testable architecture that makes authority‑to‑effect transitions explicit, offering a framework for verifying AI agent behavior, though current evidence does not prove improved security or performance."
By Stefan G. Creadore
The paper presents TRAILS, a taxonomy of 38 mechanisms that can undermine the reliability of large language model (LLM) read‑and‑evaluate tasks in evidence synthesis, such as study screening and risk‑of‑bias assessment. It distinguishes failures that cause inconsistent judgments across repeated runs from those that systematically bias outcomes without obvious signs. The authors outline deployment settings, testing approaches, and mitigation strategies, and argue that repeatability or accuracy alone cannot guarantee trustworthy judgments, emphasizing the need for human evaluation of evidence grounding and process transparency.