LLMs show promise in code generation, yet their effectiveness for IT automation tasks, particularly for tools like Ansible, remains understudied. Existing benchmarks rely primarily on synthetic tasks that fail to capture the needs of practitioners who use IT automation tools. We present ExITBench (Execution-based IT Automation Benchmark), a benchmark of 126 diverse tasks (e.g., configuring servers and managing files) in which each task captures state reconciliation - a core property of IT automation tools. ExITBench evaluates LLMs’ ability to generate functional Ansible automation scripts via dynamic execution in controlled environments. We evaluate 14 open-source and 3 proprietary LLMs and find that GPT-4.1-Mini achieves the best pass@10 rate of 23.9%, while Claude-3.5-Sonnet achieves the best pass@1 performance. To explain the low performance, we analyze 1,517 execution failures across the evaluated LLMs and identify two prevalent semantic error categories: failures in state-reconciliation reasoning (42.117% combined from variable (12.287%), host (10.363%), path (10.511%), and template (8.956%) issues) and deficiencies in module-specific execution knowledge (26.203% combined from attribute & parameter (17.617%) and module (8.586%) errors). Our findings reveal key limitations in LLMs’ ability to address state reconciliation and apply specialized module knowledge, indicating that reliable IT automation with LLM-based agents need major advances in state reasoning and domain-specific execution.

One of the most important yet onerous tasks in the academic peer-reviewing process is composing meta-reviews, which involves assimilating diverse opinions from multiple expert peers, formulating one’s self-judgment as a senior expert, and then summarizing all these perspectives into a concise holistic overview to make an overall recommendation. This process is time-consuming and can be compromised by human factors like fatigue, inconsistency, missing tiny details, etc. Given the latest major developments in Large Language Models (LLMs), it is very compelling to rigorously study whether LLMs can help meta-reviewers perform this important task better. In this paper, we perform a case study with three popular LLMs, i.e., GPT-3.5, LLaMA2, and PaLM2, to assist meta-reviewers in better comprehending multiple experts’ perspectives by generating a controlled multi-perspective-summary (MPS) of their opinions. To achieve this, we prompt three LLMs with different types/levels of prompts based on the recently proposed TELeR taxonomy. Finally, we perform a detailed qualitative study of the MPSs generated by the LLMs and report our findings.

Semantic Overlap Summarization (SOS) is a multi-document summarization task focused on extracting the common information shared cross alternative narratives which is a capability that is critical for trustworthy generation in domains such as news, law, and healthcare. We benchmark popular Large Language Models (LLMs) on SOS and introduce PrivacyPolicyPairs (3P), a new dataset of 135 high-quality samples from privacy policy documents, which complements existing resources and broadens domain coverage. Using the TELeR prompting taxonomy, we evaluate nearly one million LLM-generated summaries across two SOS datasets and conduct human evaluation on a curated subset. Our analysis reveals strong prompt sensitivity, identifies which automatic metrics align most closely with human judgments, and provides new baselines for future SOS research