Despite their powerful text generation capabilities, large language models (LLMs) still struggle to effectively utilize external tools to solve complex tasks, a challenge known as tool learning. Existing methods primarily rely on supervised fine-tuning, treating tool learning as a text generation problem while overlooking the decision-making complexities inherent in multi-step contexts. In this work, we propose modeling tool learning as a dynamic decision-making process and introduce StepTool, a novel step-grained reinforcement learning framework that enhances LLMs' capabilities in multi-step tool use. StepTool comprises two key components: Step-grained Reward Shaping, which assigns rewards to each tool interaction based on its invocation success and contribution to task completion; and Step-grained Optimization, which applies policy gradient methods to optimize the model across multiple decision steps. Extensive experiments across diverse benchmarks show that StepTool consistently outperforms both SFT-based and RL-based baselines in terms of task Pass Rate and Recall of relevant tools. Furthermore, our analysis suggests that StepTool helps models discover new tool-use strategies rather than merely re-weighting prior knowledge. These results highlight the importance of fine-grained decision modeling in tool learning and establish StepTool as a general and robust solution for enhancing multi-step tool use in LLMs. Code and data are available at https://github.com/yuyq18/StepTool.

Large language models (LLMs) have attracted significant attention in recommendation systems.Current work primarily applies supervised fine-tuning (SFT) to adapt the model for recommendation tasks.However, SFT on positive examples only limits the model's ability to align with user preference.To address this, researchers recently introduced Direct Preference Optimization (DPO), which explicitly aligns LLMs with user preferences using offline preference ranking data.However, we found that DPO inherently biases the model towards a few items, exacerbating the filter bubble issue and ultimately degrading user experience.In this paper, we propose SPRec, a novel self-play framework designed to mitigate over-recommendation and improve fairness without requiring additional data or manual intervention.In each self-play iteration, the model undergoes an SFT step followed by a DPO step, treating offline interaction data as positive samples and the predicted outputs from the previous iteration as negative samples.This effectively re-weights the DPO loss function using the model's logits, adaptively suppressing biased items.Extensive experiments on multiple real-world datasets demonstrate SPRec's effectiveness in enhancing recommendation accuracy and fairness.The code is available via https://github.com/RegionCh/SPRec.

LLM-based agents have gained considerable attention for their decision-making skills and ability to handle complex tasks.Recognizing the current gap in leveraging agent capabilities for multiagent collaboration in recommendation systems, we introduce MACRec, a novel framework designed to enhance recommendation systems through multi-agent collaboration.Unlike existing work on using agents for user/item simulation, we aim to deploy multiagents to tackle recommendation tasks directly.In our framework, recommendation tasks are addressed through the collaborative efforts of various specialized agents, including Manager, User/Item Analyst, Reflector, Searcher, and Task Interpreter, with different working flows.Furthermore, we provide application examples of how developers can easily use MACRec on various recommendation tasks, including rating prediction, sequential recommendation, conversational recommendation, and explanation generation of recommendation results.The framework and demonstration video are publicly available at https://github.com/wzf2000/MACRec.

Reinforcement Learning (RL)-Based Recommender Systems (RSs) have gained rising attention for their potential to enhance long-term user engagement. However, research in this field faces challenges, including the lack of user-friendly frameworks, inconsistent evaluation metrics, and difficulties in reproducing existing studies. To tackle these issues, we introduce EasyRL4Rec, an easy-to-use code library designed specifically for RL-based RSs. This library provides lightweight and diverse RL environments based on five public datasets and includes core modules with rich options, simplifying model development. It provides unified evaluation standards focusing on long-term outcomes and offers tailored designs for state modeling and action representation for recommendation scenarios. Furthermore, we share our findings from insightful experiments with current methods. EasyRL4Rec seeks to facilitate the model development and experimental process in the domain of RL-based RSs. The library is available for public use.

Calibration in recommender systems ensures that the user’s interests distribution over groups of items is reflected with their corresponding proportions in the recommendation, which has gained increasing attention recently. For example, a user who watched 80 entertainment videos and 20 knowledge videos is expected to receive recommendations comprising about 80% entertainment and 20% knowledge videos as well. However, with the increasing calls for responsible recommendation, it has become inadequate to just match users’ historical behaviors especially when items are grouped by their qualities, which could result in undesired effects at the system level (e.g., overwhelming clickbaits). In this paper, we envision the two-sided calibration task that not only matches the users’ past interests distribution (user-level calibration) but also guarantees an overall target exposure distribution of different item groups (system-level calibration). The target group exposure distribution can be explicitly pursued by users, platform owners, and even the law (e.g., the platform owners expect about 50% knowledge video recommendation on the whole). To support this scenario, we propose a post-processing method named PCT. PCT first solves personalized calibration targets that minimize the changes in users’ historical interest distributions while ensuring the overall target group exposure distribution. Then, PCT reranks the original recommendation lists according to personalized calibration targets to generate both relevant and two-sided calibrated recommendations. Extensive experiments demonstrate the superior performance of the proposed method compared to calibrated and fairness-aware recommendation approaches.

Collaborative filtering (CF) plays a critical role in the development of recommender systems. Most CF methods utilize an encoder to embed users and items into the same representation space, and the Bayesian personalized ranking (BPR) loss is usually adopted as the objective function to learn informative encoders. Existing studies mainly focus on designing more powerful encoders (e.g., graph neural network) to learn better representations. However, few efforts have been devoted to investigating the desired properties of representations in CF, which is important to understand the rationale of existing CF methods and design new learning objectives. In this paper, we measure the representation quality in CF from the perspective of alignment and uniformity on the hypersphere. We first theoretically reveal the connection between the BPR loss and these two properties. Then, we empirically analyze the learning dynamics of typical CF methods in terms of quantified alignment and uniformity, which shows that better alignment or uniformity both contribute to higher recommendation performance. Based on the analyses results, a learning objective that directly optimizes these two properties is proposed, named DirectAU. We conduct extensive experiments on three public datasets, and the proposed learning framework with a simple matrix factorization model leads to significant performance improvements compared to state-of-the-art CF methods.