Agent models are frequently evaluated one decision at a time, where the model predicts the next action based on the gold interaction history, which is scored against a reference. We investigate whether improvement under this protocol is predictive of improved autonomous workflow execution. We study pre-SFT and supervised fine-tuned (SFT) Qwen3 models at 4B and 14B parameters and Gemma 3 models at 4B and 12B parameters on multi-turn customer-support workflows. We find that SFT consistently improves text-turn success, and that overall next-turn success increases for every model under gold-history evaluation. However, these improvements do not transfer to autonomous workflow execution. Tool-specific gains also vary across metrics and models. None of the four SFT models succeeds under holistic workflow evaluation, with strict trajectory completion reaching at most 10.4% workflow success. Our results show that next-turn evaluation is not a reliable proxy for workflow success, motivating separate reporting of text quality, local action correctness, tool execution, and end-to-end task completion.

Large language models (LLMs) have achieved impressive performance in text summarization, yet their performance often falls short when applied to specialized domains that differ from their original pre-training distribution. While fine-tuning can improve summarization quality, it typically relies on costly and scarce high-quality labeled data. In this work, we explore continual pre-training as a scalable, self-supervised approach to adapt LLMs for downstream summarization tasks, particularly in the context of noisy real-world conversation transcripts. We conduct extensive experiments using large-scale, unlabeled business conversation data to investigate whether continual pre-training enhances model capabilities in conversational summarization. Our results demonstrate that continual pre-training yields substantial gains in both in-domain and out-of-domain summarization benchmarks, while maintaining strong generalization and robustness. We also analyze the effects of data selection strategies, providing practical guidelines for applying continual pre-training in summarization-focused industrial applications.

The rapid advancements in Large Language Models (LLMs) have enabled their adoption in real-world industrial scenarios for various natural language processing tasks. However, the high inference cost of large-scale LLMs makes their deployment impractical, necessitating the use of smaller models. Despite their efficiency, smaller LLMs lack robust zero-shot instruction-following capabilities across diverse domains, limiting their adaptability to dynamic user requirements. Traditional fine-tuning approaches exacerbate this issue by inducing catastrophic forgetting, reducing the model’s generalization ability for unseen tasks. In this paper, we propose Domain Adaptive Continual Instruction Pre-Training via Reading Comprehension (DACIP-RC), a continual pre-training technique that enhances smaller LLMs’ domain adaptability for business conversational tasks. Unlike conventional pre-training approaches that rely on next-token prediction, DACIP-RC generates diverse task instructions and responses via reading comprehension on conversation transcripts, enabling better instruction generalization. Our empirical evaluations demonstrate that DACIP-RC significantly improves zero-shot generalization across a wide range of business conversational tasks, including meeting summarization, action item generation, and call purpose identification. To the best of our knowledge, this is the first work to apply instruction pre-training on business conversational data, providing insights into how industries can leverage proprietary datasets for domain adaptation.

Large Language Models (LLMs) have demonstrated impressive capability to solve a wide range of tasks in recent years. This has inspired researchers and practitioners in the real-world industrial domain to build useful products via leveraging LLMs. However, extensive evaluations of LLMs, in terms of accuracy, memory management, and inference latency, while ensuring the reproducibility of the results are crucial before deploying LLM-based solutions for real-world usage. In addition, when evaluating LLMs on internal customer data, an on-premise evaluation system is necessary to protect customer privacy rather than sending customer data to third-party APIs for evaluation. In this paper, we demonstrate how we build an on-premise system for LLM evaluation to address the challenges in the evaluation of LLMs in real-world industrial settings. We demonstrate the complexities of consolidating various datasets, models, and inference-related artifacts in complex LLM inference pipelines. For this purpose, we also present a case study in a real-world industrial setting. The demonstration of the LLM evaluation tool development would help researchers and practitioners in building on-premise systems for LLM evaluation ensuring privacy, reliability, robustness, and reproducibility.