Recent advancements in Large Language Models (LLMs) have enabled autonomous agents to decompose complex tasks, select appropriate tools, and execute structured workflows. However, a key challenge in this field is the lack of a universal, large-scale, and cross-domain benchmark to systematically evaluate LLMs’ ability to reason over and utilize interconnected tools for automation. Existing benchmarks, such as TaskBench, focus on manually curated tool graphs for benchmark generation, which lack scalability and diversity across domains. To address this, we propose UniToolBench, a benchmark that incorporates automated tool graph construction by formulating link prediction as a probabilistic task, instead of relying on categorical LLM outputs. Furthermore, we introduce a confidence-based beam search sampling strategy to select high-confidence tool dependencies, ensuring more structured and semantically coherent subgraphs for evaluation. Through extensive experiments on multiple datasets, we demonstrate that while LLMs show promise in tool selection, significant challenges remain in parameter prediction and handling complex tool dependencies.

Conversational recommendation systems (CRS) have gained popularity in e-commerce as they can recommend items during user interactions. However, current open-ended CRS have limited recommendation performance due to their short-sighted training process, which only predicts one utterance at a time without considering its future impact. To address this, we propose a User Simulator (US) that communicates with the CRS using natural language based on given user preferences, enabling long-term reinforcement learning. We also introduce a framework that uses reinforcement learning (RL) with two novel rewards, i.e., recommendation and conversation rewards, to train the CRS. This approach considers the long-term goals and improves both the conversation and recommendation performance of the CRS. Our experiments show that our proposed framework improves the recall of recommendations by almost 100%. Moreover, human evaluation demonstrates the superiority of our framework in enhancing the informativeness of generated utterances.