The study investigates whether large language models (LLMs) have improved in screening systematic reviews (SRs) within software engineering. Using the SESR‑Eval benchmark and a new smaller dataset, the authors evaluated eight recent LLMs and found only marginal performance gains over older models (average MCC rose from 0.347 to 0.365). The research also examined prompt variations, inter‑model agreement, and the impact of refining inclusion/exclusion criteria, concluding that LLMs still fall short of replacing human reviewers and that future work should explore agent‑based methods, prompt engineering, and further criteria refinement.
By Aleksi Huotala, Miikka Kuutila, Mika M\"antyl\"a
The paper introduces a benchmark of 400 synthetic healthcare workflow episodes to evaluate large language model (LLM) agents’ reliability in escalating care when evidence is missing or conflicting. It finds that while clean decision accuracy is high (0.97), models miss a large proportion of necessary escalations (32–97%) under uncertainty, and even the largest 9.7B model’s performance drops to 0.78 in conflict scenarios. A workflow-aware controller improves utility and reduces missed escalations, but its effectiveness is limited by lexical generalization failures.
By Zihao Zheng (Washington University in St. Louis), Junyi Yao (Washington University in St. Louis), Baichuan Li (Southern Methodist University), Jiayu Long (Washington University in St. Louis)
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 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
The study evaluates how to reduce fabricated claims in multi‑stage large language model (LLM) hiring pipelines. Prompt guardrails alone cut fabrication density by 86 % but still left half of outputs containing false claims, while adding a human‑in‑the‑loop checkpoint after resume improvement eliminated all identity fabrications and significantly lowered overall fabrication rates. The results show that a layered approach—combining prompt guardrails with human checkpoints—provides stronger protection against severe failures without harming the quality of the final outputs.
By Hiroko Takano
TWIST is a new benchmark suite designed to evaluate the quality of interventions in conversational memory systems, focusing on how well these systems act correctly at belief change points. It includes four tracks—tension detection, draft vetting, belief-consistent answering, and sensitive recall governance—each paired with hard-negative controls to prevent gaming. The benchmark is rigorously validated through double annotation, adjudication, and a separability audit, revealing that current models face trade-offs between contradiction recall and false-positive rates.
By Subrat Panda
arXiv:2607. 14707v1 Announce Type: cross Abstract: Large language models routinely produce fluent answers to single-shot prompts, yet deploying them as reliable components of a domain decision system is substantially harder.
By Akash Raj
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
Operational reporting for high-performance computing (HPC) facilities requires combining information from monitoring services, schedulers, incident and maintenance records, storage measurements, perio...
The study compares single-agent and multi-agent large language model (LLM) setups for reviewing credit assessment memos against specified requirements. In a controlled experiment with 300 synthetic memos, a single agent examined six requirements in one call, while a team of three agents each checked two requirements. Results show the team identified 0.08 to 0.10 more defects on certain models but also produced more false alarms, used 2.2 to 2.4 times more tokens, and had mixed effects on balanced accuracy depending on instruction and model.
By Pei Liu
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
arXiv:2608. 14551v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for title-abstract screening in systematic reviews, but their decisions lack calibrated uncertainty.
By Arya Rahgozar, Pouria Mortezaagha