Large Language Model (LLM) based multiagent systems (MAS) show strong potential for tackling complex tasks through collaborative intelligence.Monte Carlo Tree Search (MCTS) based methods provide promising approaches for enhancing MAS self-training by generating synthetic data, using Q-values to estimate agent contributions.However, relying solely on Q-values may misalign with the goal of selecting data most beneficial for MAS improvement.To address this discrepancy, we propose Data Influence-oriented Tree Search (DITS), a novel framework that incorporates influence scores to guide both tree search and data selection in data synthesis.By leveraging influence scores, we effectively identify the most impactful data for MAS improvement, thereby enhancing model performance.Furthermore, we derive a novel influence score estimation method tailored for non-differentiable metrics, significantly reducing computational overhead by calculating performance changes on the validation set.Extensive experiments on three different multi-agent tasks demonstrate the robustness and effectiveness of the proposed methods.Notably, our findings reveal that allocating more resources to estimate influence scores, rather than Q-values, during data synthesis can more effectively and efficiently enhance model training.The code is available at https://github.com/swt-user/DITS.

Xiqiao Xiong, Ouxiang Li, Zhuo Liu, Moxin Li, Wentao Shi, Fengbin Zhu, Qifan Wang, Fuli Feng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

The powerful reasoning and generative capabilities of large language models (LLMs) have inspired researchers to apply them to reasoning-based recommendation tasks, which require in-depth reasoning about user interests and the generation of recommended items. However, previous reasoning-based recommendation methods have typically performed inference within the language space alone, without incorporating the actual item space. This has led to over-interpreting user interests and deviating from real items. Towards this research gap, we propose performing multiple rounds of grounding during inference to help the LLM better understand the actual item space, which could ensure that its reasoning remains aligned with real items. Furthermore, we introduce a user agent that provides feedback during each grounding step, enabling the LLM to better recognize and adapt to user interests. Comprehensive experiments conducted on three Amazon review datasets demonstrate the effectiveness of incorporating multiple groundings and feedback. These findings underscore the critical importance of reasoning within the actual item space, rather than being confined to the language space, for recommendation tasks.

Conventional recommendation systems frequently fail to fully exploit the high-dimensional semantic signals inherent in multimedia content, thereby limiting the fidelity of user preference modeling. While Multimodal Large Language Models (MM-LLMs) offer robust mechanisms for interpreting such complex data, their integration into latency-constrained, industrial-scale architectures remains a significant challenge. To address this, we propose a generalized framework for MM-LLM-driven multimedia understanding. Our methodology employs a tripartite architecture encompassing content interpretation, representation extraction, and systematic pipeline integration, instantiated via a LLaMA2-based model that generates descriptive captions subsequently ingested as tokenized categorical features. Empirical evaluation demonstrates the efficacy of this approach, yielding a 0.35% increase in offline AUC and a 0.02% improvement in online metrics at scale, substantiating the practical viability of leveraging MM-LLMs to enhance large-scale recommendation performance.

Large Language Models for Recommendation (LLM4Rec) have shown great potential. Many LLM4Rec approaches technically leverage a learnable tokenizer to assign item identifiers and then enable a Recommender LLM (RecLLM) to process tokenized items and user interactions for recommendation. However, a key challenge in their real-world deployment is the need for continuous retraining over time to accommodate new items and evolving user interests. While existing retraining methods can be applied to RecLLMs, learnable tokenizers introduce additional retraining challenges. We conduct a comprehensive investigation into the joint retraining of RecLLMs and learnable tokenizers, identifying key issues such as identifier collision and identifier shifts across periods. To address these, we propose Reformer, an incremental learning framework to fine-tune RecLLMs and learnable tokenizers at each period. Reformer employs a dynamic codebook to mitigate identifier collision by appending new codes and enforcing a diversity-oriented code assignment constraint. Additionally, Reformer adopts an identifier freezing strategy to ensure the invariance of previously assigned item identifiers across retraining periods. We instantiate Reformer on two representative RecLLMs and conduct extensive experiments on three real-world datasets. Substantial results demonstrate its superior retraining performance, facilitating the real-world deployment of LLM4Rec.

Large language model (LLM)-based agents have demonstrated remarkable capabilities in addressing complex tasks, thereby enabling more advanced information retrieval and supporting deeper, more sophisticated human information-seeking behaviors. However, most existing agents operate in a purely reactive manner, responding passively to user instructions, which significantly constrains their effectiveness and efficiency as general-purpose platforms for information acquisition. To overcome this limitation, this paper proposes AppAgent-Pro, a proactive GUI agent system that actively integrates multi-domain information based on user instructions. This approach enables the system to proactively anticipate users' underlying needs and conduct in-depth multi-domain information mining, thereby facilitating the acquisition of more comprehensive and intelligent information. AppAgent-Pro has the potential to fundamentally redefine information acquisition in daily life, leading to a profound impact on human society. Our code is available at: https://github.com/LaoKuiZe/AppAgent-Pro. The demonstration video could be found at: https://www.dropbox.com/scl/fi/hvzqo5vnusg66srydzixo/AppAgent-Pro-demo-video.mp4?rlkey=o2nlfqgq6ihl125mcqg7bpgqu&st=d29vrzii&dl=0.

Accurate and safe medication recommendations are critical for effective clinical decision-making, especially in multimorbidity cases. However, existing systems rely on point-wise prediction paradigms that overlook synergistic drug effects and potential adverse drug-drug interactions (DDIs). We propose FLAME, a fine-grained list-wise alignment framework for large language models (LLMs), enabling drug-by-drug generation of drug lists. FLAME formulates recommendation as a sequential decision process, where each step adds or removes a single drug. To provide fine-grained learning signals, we devise step-wise Group Relative Policy Optimization (GRPO) with potential-based reward shaping, which explicitly models DDIs and optimizes the contribution of each drug to the overall prescription. Furthermore, FLAME enhances patient modeling by integrating structured clinical knowledge and collaborative information into the representation space of LLMs. Experiments on benchmark datasets demonstrate that FLAME achieves state-of-the-art performance, delivering superior accuracy, controllable safety–accuracy trade-offs, and strong generalization across diverse clinical scenarios. Our code is available at https://github.com/cxfann/Flame.

While large language models (LLMs) are increasingly adapted for recommendation systems via supervised fine-tuning (SFT), this approach amplifies popularity bias due to its likelihood maximization objective, compromising recommendation diversity and fairness.To address this, we present Flow-guided fine-tuning recommender (Flower), which replaces SFT with a Generative Flow Network (GFlowNet) [6] framework that enacts process supervision through token-level reward propagation.Flower's key innovation lies in decomposing item-level rewards into constituent token rewards, enabling direct alignment between token generation probabilities and their reward signals.This mechanism achieves three critical advancements: (1) popularity bias mitigation and fairness enhancement through empirical distribution matching, (2) preservation of diversity through GFlowNet's proportional sampling, and (3) flexible integration of personalized preferences via adaptable token rewards.Experiments demonstrate Flower's superior distribution-fitting capability and its significant advantages over traditional SFT in terms of accuracy, fairness, and diversity, highlighting its potential to improve LLM-based recommendation systems.The implementation is available via https://github.com/Mr- Peach0301/Flower.

Adapting Large Language Models (LLMs) for agent tasks is critical in developing language agents.Direct Preference Optimization (DPO) is a promising technique for this adaptation with the alleviation of compounding errors, offering a means to directly optimize Reinforcement Learning (RL) objectives.However, applying DPO to multi-turn tasks presents challenges due to the inability to cancel the partition function.Overcoming this obstacle involves making the partition function independent of the current state and addressing length disparities between preferred and dis-preferred trajectories.In this light, we replace the policy constraint with the state-action occupancy measure constraint in the RL objective and add length normalization to the Bradley-Terry model, yielding a novel loss function named DMPO for multi-turn agent tasks with theoretical explanations.Extensive experiments on three multi-turn agent task datasets confirm the effectiveness and superiority of the DMPO loss.

Loss functions steer the optimization direction of recommendation models and are critical to model performance, but have received relatively little attention in recent recommendation research. Among various losses, we find Softmax loss (SL) stands out for not only achieving remarkable accuracy but also better robustness and fairness. Nevertheless, the current literature lacks a comprehensive explanation for the efficacy of SL. Toward addressing this research gap, we conduct theoretical analyses on SL and uncover three insights: 1) Optimizing SL is equivalent to performing Distributionally Robust Optimization (DRO) on the negative data, thereby learning against perturbations on the negative distribution and yielding robustness to noisy negatives. 2) Comparing with other loss functions, SL implicitly penalizes the prediction variance, resulting in a smaller gap between predicted values and and thus producing fairer results. Building on these insights, we further propose a novel loss function Bilateral SoftMax Loss (BSL) that extends the advantage of SL to both positive and negative sides. BSL augments SL by applying the same Log-Expectation-Exp structure to positive examples as is used for negatives, making the model robust to the noisy positives as well. Remarkably, BSL is simple and easy-to-implement - requiring just one additional line of code compared to SL. Experiments on four real-world datasets and three representative backbones demonstrate the effectiveness of our proposal. The code is available at https://github.com/junkangwu/BSL.

Planning for both immediate and long-term benefits becomes increasingly important in recommendation. Existing methods apply Reinforcement Learning (RL) to learn planning capacity by maximizing cumulative reward for long-term recommendation. However, the scarcity of recommendation data presents challenges such as instability and susceptibility to overfitting when training RL models from scratch, resulting in sub-optimal performance. In this light, we propose to leverage the remarkable planning capabilities over sparse data of Large Language Models (LLMs) for long-term recommendation. The key to achieving the target lies in formulating a guidance plan following principles of enhancing long-term engagement and grounding the plan to effective and executable actions in a personalized manner. To this end, we propose a Bi-level Learnable LLM Planner framework, which consists of a set of LLM instances and breaks down the learning process into macro-learning and micro-learning to learn macro-level guidance and micro-level personalized recommendation policies, respectively. Extensive experiments validate that the framework facilitates the planning ability of LLMs for long-term recommendation. Our code and data can be found at https://github.com/jizhi-zhang/BiLLP.

Optimization metrics are crucial for building recommendation systems at scale. However, an effective and efficient metric for practical use remains elusive. While Top-K ranking metrics are the gold standard for optimization, they suffer from significant computational overhead. Alternatively, the more efficient accuracy and AUC metrics often fall short of capturing the true targets of recommendation tasks, leading to suboptimal performance. To overcome this dilemma, we propose a new optimization metric, Lower-Left Partial AUC (LLPAUC), which is computationally efficient like AUC but strongly correlates with Top-K ranking metrics. Compared to AUC, LLPAUC considers only the partial area under the ROC curve in the Lower-Left corner to push the optimization focus on Top-K. We provide theoretical validation of the correlation between LLPAUC and Top-K ranking metrics and demonstrate its robustness to noisy user feedback. We further design an efficient point-wise recommendation loss to maximize LLPAUC and evaluate it on three datasets, validating its effectiveness and robustness.

Recommender systems are vulnerable to injective attacks, which inject limited fake users into the platforms to manipulate the exposure of target items to all users. In this work, we identify that conventional injective attackers overlook the fact that each item has its unique potential audience, and meanwhile, the attack difficulty across different users varies. Blindly attacking all users will result in a waste of fake user budgets and inferior attack performance. To address these issues, we focus on an under-explored attack task called target user attacks, aiming at promoting target items to a particular user group. In addition, we formulate the varying attack difficulty as heterogeneous treatment effects through a causal lens and propose an Uplift-guided Budget Allocation (UBA) framework. UBA estimates the treatment effect on each target user and optimizes the allocation of fake user budgets to maximize the attack performance. Theoretical and empirical analysis demonstrates the rationality of treatment effect estimation methods of UBA. By instantiating UBA on multiple attackers, we conduct extensive experiments on three datasets under various settings with different target items, target users, fake user budgets, victim models, and defense models, validating the effectiveness and robustness of UBA.

Selection bias hinders recommendation models from learning unbiased user preference. Recent works empirically reveal that pursuing invariant user and item representation across biased and unbiased data is crucial for counteracting selection bias. However, our theoretical analysis reveals that simply optimizing representation invariance is insufficient for addressing the selection bias — recommendation performance is bounded by both representation invariance and discriminability. Worse still, current invariant representation learning methods in recommendation neglect even hurt the representation discriminability due to data sparsity and label shift. In this light, we propose a new Discriminative-Invariant Representation Learning framework for unbiased recommendation, which incorporates label-conditional clustering and prior-guided contrasting into conventional invariant representation learning to mitigate the impact of data sparsity and label shift, respectively. We conduct extensive experiments on three real-world datasets, validating the rationality and effectiveness of the proposed framework. Code and supplementary materials are available at: https://github.com/HungPaan/DIRL.

This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias, wherein negative samples may encompass similar semantics (\eg labels). However, existing theories fall short in providing explanations for this phenomenon. We bridge this research gap by analyzing CL through the lens of distributionally robust optimization (DRO), yielding several key insights: (1) CL essentially conducts DRO over the negative sampling distribution, thus enabling robust performance across a variety of potential distributions and demonstrating robustness to sampling bias; (2) The design of the temperature $\tau$ is not merely heuristic but acts as a Lagrange Coefficient, regulating the size of the potential distribution set; (3) A theoretical connection is established between DRO and mutual information, thus presenting fresh evidence for ``InfoNCE as an estimate of MI'' and a new estimation approach for $\phi$-divergence-based generalized mutual information. We also identify CL's potential shortcomings, including over-conservatism and sensitivity to outliers, and introduce a novel Adjusted InfoNCE loss (ADNCE) to mitigate these issues. It refines potential distribution, improving performance and accelerating convergence. Extensive experiments on various domains (image, sentence, and graph) validate the effectiveness of the proposal.

Negative sampling has been heavily used to train recommender models on large-scale data, wherein sampling hard examples usually not only accelerates the convergence but also improves the model accuracy. Nevertheless, the reasons for the effectiveness of Hard Negative Sampling (HNS) have not been revealed yet. In this work, we fill the research gap by conducting thorough theoretical analyses on HNS. Firstly, we prove that employing HNS on the Bayesian Personalized Ranking (BPR) learner is equivalent to optimizing One-way Partial AUC (OPAUC). Concretely, the BPR equipped with Dynamic Negative Sampling (DNS) is an exact estimator, while with softmax-based sampling is a soft estimator. Secondly, we prove that OPAUC has a stronger connection with Top-K evaluation metrics than AUC and verify it with simulation experiments. These analyses establish the theoretical foundation of HNS in optimizing Top-K recommendation performance for the first time. On these bases, we offer two insightful guidelines for effective usage of HNS: 1) the sampling hardness should be controllable, e.g., via pre-defined hyper-parameters, to adapt to different Top-K metrics and datasets; 2) the smaller the K we emphasize in Top-K evaluation metrics, the harder the negative samples we should draw. Extensive experiments on three real-world benchmarks verify the two guidelines.

Knowledge graph completion (KGC) has become a focus of attention across deep learning community owing to its excellent contribution to numerous downstream tasks. Although recently have witnessed a surge of work on KGC, they are still insufficient to accurately capture complex relations, since they adopt the single and static representations. In this work, we propose a novel Disentangled Knowledge Graph Attention Network (DisenKGAT) for KGC, which leverages both micro-disentanglement and macro-disentanglement to exploit representations behind Knowledge graphs (KGs). To achieve micro-disentanglement, we put forward a novel relation-aware aggregation to learn diverse component representation. For macro-disentanglement, we leverage mutual information as a regularization to enhance independence. With the assistance of disentanglement, our model is able to generate adaptive representations in terms of the given scenario. Besides, our work has strong robustness and flexibility to adapt to various score functions. Extensive experiments on public benchmark datasets have been conducted to validate the superiority of DisenKGAT over existing methods in terms of both accuracy and explainability.