The article reviews how replacing components in language‑model agents affects execution trajectories and downstream outcomes. It maps 348 studies, analyzes 90 comparison records, and finds that while many studies report both local decision metrics and task endpoints, they rarely demonstrate matched comparisons or prove that improved local decisions drive task‑level gains. The review identifies three potential mechanisms—recovery and disruption, intervention timing, and downstream use—and proposes eight claim‑specific reporting items to clarify evidence quality.
By Shuyang Zhang (The Hong Kong Polytechnic University), Jianshuo Chang (The Hong Kong Polytechnic University)
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 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 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
arXiv:2609.36138v1 Announce Type: new
Abstract: Before invoking external tools, an agentic LLM must select among a K-way action space: executing a call, seeking clarification, answering directly, or...
By Jiayi Li, Ruizhe Li
arXiv:2608. 05235v1 Announce Type: cross Abstract: Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings and retain the resulting trajectories to guide later decisions.
By Zijie Zhuang, Changxin Lao, Pengbo Xu, Hanwen Xu, Ruochen Yang, Yingzhi He, Peng Zhang, Jiangxia Cao, Yusheng Huang, Guohong Mu, Jian Liang, Ruiming Tang, Shuang Yang, Zhaojie Liu, Wenwu Ou, Kun Gai
The paper presents a layered framework for evaluating conversational AI by aligning offline proxy signals with online A/B experiment outcomes. It introduces a three‑step alignment chain—behavioral label to product outcome, classifier to candidate behavior, and offline signal to experiment effect—alongside an audit protocol that compares confidence intervals and rankings. In a real‑world deployment, the composite proxy achieved 81.1% F1 versus 34.3% for the raw classifier, correctly predicting direction on all 113 contrasts and enabling efficient prioritization of candidate models before costly online testing.
By Xuanyi Li, Vaskar Nath, Hossein Amirkhani, Jay Li, Alex Deng
The paper introduces RAISE, a diagnostic framework that tests whether a costly large language model (LLM) signal provides enough pre-call information to justify selective use. It identifies the failure mode of acquisition collapse, where an LLM appears useful overall but lacks actionable evidence for individual decisions. The authors demonstrate RAISE with Structured Hypothesis Embeddings (SHE) and evaluate it across multiple study designs, showing that predictable incremental benefit, rather than average lift, indicates recoverable selective value.
By Ying Yuan, Yu Wang, Yize Cheng, Xuyang Wu
The paper introduces a framework for diagnosing and recovering from hidden dynamics changes in deployed control policies, focusing on the problem of task readiness under dormant dynamics drift. It proposes an intervention-based Bayesian method called Evidence‑Gated Matched‑Pulse Transport that localizes faults and estimates actuator effectiveness, enabling agents to certify readiness for future tasks with limited, task‑agnostic interactions. The approach is evaluated on diverse benchmarks, measuring readiness coverage, selective risk, interaction cost, and return, and identifies regimes where transported evidence is decisive.
By Nguyen Viet Tuan Kiet, Huynh Thi Thanh Binh
arXiv:2608. 13867v1 Announce Type: cross Abstract: AI coding agents are commonly evaluated as models but deployed as systems.
By Stephanie Jarmak
Online A/B experiments are the decision standard for user engagement, but traffic and readout time limit how many conversational-AI changes can be tested. We ask whether an offline signal designed to...
arXiv:2607. 28871v1 Announce Type: cross Abstract: When a repair agent runs a test and sees it pass, the result is treated as evidence about the reported defect.
By Xiaonan Xu, Wenjing Wu