Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce

In vibe coding, people describe software in natural language and delegate implementation to AI agents. By analogy, vibe commerce allows people to express buying or selling goals in natural language and delegate the corresponding tasks to agents. Commerce, however, requires independently controlled Buyer and Merchant agents to interact in a shared market while preserving their private objectives and distinct authority. We introduce Agentic Commerce World (ACWorld), an environment for evaluating such agents across ongoing transactions. Through its Vibe Commerce Protocol (VCP), ACWorld validates agent actions before updating shared transaction state and records the resulting interactions, making agent behavior auditable and evaluation reproducible. The ACWorld Benchmark contains a 200-task capability-coverage track and a 60-task large-catalog track that searches 785,022 transactable listings. Across ten models, mean scores range from 65.9% to 85.6% and from 56.1% to 91.4%, respectively. Our analysis shows that process-level evidence is necessary: final state alone can miss evaluated errors, incomplete trajectories still retain useful process signals, and large-catalog tasks expose bottlenecks across stages.

Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for LLM Marketplace Agents

LLM agents increasingly act as autonomous merchants that write their own product listings, and under competitive pressure, they fabricate attributes to win sales. Even under instructions to be honest, they fabricate attributes in a majority of listings across models. A platform's obvious remedy---verifying each claim against the truth---is unavailable, because it observes only a noisy, biased complaint signal, never the ground truth. We design CARP, a reputation-penalty mechanism with a deadband that forgives complaint noise and a state-dependent severity that counters reputation-driven detection erosion. CARP requires no product-level ground truth and is robust to strategic gaming. CARP protects consumers by suppressing the sales volume of low-rated liars while sparing honest sellers. Paired with SPARC, it closes most of the consumer-welfare gap relative to a perfect-information oracle, without ever accessing the truth. It also achieves the best welfare of the policies we compare. We further show that this felt penalty becomes behaviorally binding through SPARC, a byte-clean code-gated reflection mechanism: LLM merchants fabricate when lying is free but restrain themselves when fabrication costs them sales, a self-interested response rather than compliance. We trace this distinction to penalty-gated self-correction reasoning, and observe the binding across models, with supporting confidence intervals.

Personalized Recommendation Tool Learning via Autonomous Language Agents

Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive world knowledge, previous LLM-based agents suffer from hallucination and context-length limitations, and thus are not suitable for full-ranking recommendation tasks. To circumvent these limitations through architectural design rather than modifying the LLM itself, we propose an agent-based recommendation framework, memory-based $\textbf{P}$ersonalized $\textbf{R}$ecommendation $\textbf{T}$ool learning via autonomous language $\textbf{A}$gents (PRTA), in which an LLM acts as a central planner interacting with multiple recommendation models as tools. The LLM-based agent is responsible for high-level reasoning and personalized tool selection, while traditional recommendation models perform full-ranking scoring, leveraging their scalability in modeling behavioral patterns. To support personalized tool selection, we design reflection mechanisms that enable the agent to evaluate and compare tools for each user based on user profiles and candidate ranked lists. Extensive experiments across three public datasets demonstrate the superiority of \modelname over traditional recommendation and LLM-based baselines in improving full-ranking recommendation performance.

Automating Personalization: Prompt Optimization for Recommendation Reranking

Modern recommender systems increasingly leverage large language models (LLMs) for reranking to improve personalization. However, existing approaches face two key limitations: (1) heavy reliance on manually crafted prompts that are difficult to scale, and (2) inadequate handling of unstructured item metadata that complicates preference inference. We present AGP (Auto-Guided Prompt Refinement), a novel framework that automatically optimizes user profile generation prompts for personalized reranking. AGP introduces two key innovations: (1) position-aware feedback mechanisms for precise ranking correction, and (2) batched training with aggregated feedback to enhance generalization.

Training Large Recommendation Models via Graph-Language Token Alignment

Recommender systems (RS) have become essential tools for helping users efficiently navigate the overwhelming amount of information on e-commerce and social platforms. However, traditional RS relying on Collaborative Filtering (CF) struggles to integrate the rich semantic information from textual data. Meanwhile, large language models (LLMs) have shown promising results in natural language processing, but directly using LLMs for recommendation introduces challenges, such as ambiguity in generating item predictions and inefficiencies in scalability. In this paper, we propose a novel framework to train Large Recommendation models via Graph-Language Token Alignment. By aligning item and user nodes from the interaction graph with pretrained LLM tokens, GLTA effectively leverages the reasoning abilities of LLMs. Furthermore, we introduce Graph-Language Logits Matching (GLLM) to optimize token alignment for end-to-end item prediction, eliminating ambiguity in the free-form text as recommendation results. Extensive experiments on three benchmark datasets demonstrate the effectiveness of GLTA, with ablation studies validating each component.

PCL: Prompt-based Continual Learning for User Modeling in Recommender Systems

User modeling in large e-commerce platforms aims to optimize user experiences by incorporating various customer activities. Traditional models targeting a single task often focus on specific business metrics, neglecting the comprehensive user behavior, and thus limiting their effectiveness. To develop more generalized user representations, some existing work adopts Multi-task Learning (MTL)approaches. But they all face the challenges of optimization imbalance and inefficiency in adapting to new tasks. Continual Learning (CL), which allows models to learn new tasks incrementally and independently, has emerged as a solution to MTL's limitations. However, CL faces the challenge of catastrophic forgetting, where previously learned knowledge is lost when the model is learning the new task. Inspired by the success of prompt tuning in Pretrained Language Models (PLMs), we propose PCL, a Prompt-based Continual Learning framework for user modeling, which utilizes position-wise prompts as external memory for each task, preserving knowledge and mitigating catastrophic forgetting. Additionally, we design contextual prompts to capture and leverage inter-task relationships during prompt tuning. We conduct extensive experiments on real-world datasets to demonstrate PCL's effectiveness.

Instruction-based Hypergraph Pretraining

Pretraining has been widely explored to augment the adaptability of graph learning models to transfer knowledge from large datasets to a downstream task, such as link prediction or classification. However, the gap between training objectives and the discrepancy between data distributions in pretraining and downstream tasks hinders the transfer of the pretrained knowledge. Inspired by instruction-based prompts widely used in pretrained language models, we introduce instructions into graph pretraining. In this paper, we propose a novel pretraining framework named Instruction-based Hypergraph Pretraining. To overcome the discrepancy between pretraining and downstream tasks, text-based instructions are applied to provide explicit guidance on specific tasks for representation learning. Compared to learnable prompts, whose effectiveness depends on the quality and the diversity of training data, text-based instructions intrinsically encapsulate task information and support the model to generalize beyond the structure seen during pretraining. To capture high-order relations with task information in a context-aware manner, a novel prompting hypergraph convolution layer is devised to integrate instructions into information propagation in hypergraphs. Extensive experiments conducted on three public datasets verify the superiority of IHP in various scenarios.

Multi-view Graph Convolution for Participant Recommendation

Social networks have become essential for people's lives. The proliferation of web services further expands social networks at an unprecedented scale, leading to immeasurable commercial value for online platforms. Recently, the group buying (GB) business mode is prevalent and also becoming more popular in E-commerce. GB explicitly forms groups of users with similar interests to secure better discounts from the merchants, often operating within social networks. It is a novel way to further unlock the commercial value by explicitly utilizing the online social network in E-commerce. Participant recommendation, a fundamental problem emerging together with GB, aims to find the participants for a launched group buying process with an initiator and a target item to increase the GB success rate. This paper proposes Multi-View Graph Convolution for Participant Recommendation (MVPRec) to tackle this problem. To differentiate the roles of users (Initiator/Participant) within the GB process, we explicitly reconstruct historical GB data into initiator-view and participant-view graphs. Together with the social graph, we obtain a multi-view user representation with graph encoders. Then MVPRec fuses the GB and social representation with an attention module to obtain the user representation and learns a matching score with the initiator's social friends via a multi-head attention mechanism. Social friends with the Top-k matching score are recommended for the corresponding GB process. Experiments on three datasets justify the effectiveness of MVPRec in the emerging participant recommendation problem.

Group-Aware Interest Disentangled Dual-Training for Personalized Recommendation

Personalized recommender systems aim to predict users' preferences for items. It has become an indispensable part of online services. Online social platforms enable users to form groups based on their common interests. The users' group participation on social platforms reveals their interests and can be utilized as side information to mitigate the data sparsity and cold-start problem in recommender systems. Users join different groups out of different interests. In this paper, we generate group representation from the user's interests and propose IGRec (Interest-based Group enhanced Recommendation) to utilize the group information accurately. It consists of four modules. (1) Interest disentangler via self-gating that disentangles users' interests from their initial embedding representation. (2) Interest aggregator that generates the interest-based group representation by Gumbel-Softmax aggregation on the group members' interests. (3) Interest-based group aggregation that fuses user's representation with the participated group representation. (4) A dual-trained rating prediction module to utilize both user-item and group-item interactions. We conduct extensive experiments on three publicly available datasets. Results show IGRec can effectively alleviate the data sparsity problem and enhance the recommender system with interest-based group representation. Experiments on the group recommendation task further show the informativeness of interest-based group representation.

Unified Pretraining for Recommendation via Task Hypergraphs

Although pretraining has garnered significant attention and popularity in recent years, its application in graph-based recommender systems is relatively limited. It is challenging to exploit prior knowledge by pretraining in widely used ID-dependent datasets. On one hand, user-item interaction history in one dataset can hardly be transferred to other datasets through pretraining, where IDs are different. On the other hand, pretraining and finetuning on the same dataset leads to a high risk of overfitting. In this paper, we propose a novel multitask pretraining framework named Unified Pretraining for Recommendation via Task Hypergraphs. For a unified learning pattern to handle diverse requirements and nuances of various pretext tasks, we design task hypergraphs to generalize pretext tasks to hyperedge prediction. A novel transitional attention layer is devised to discriminatively learn the relevance between each pretext task and recommendation. Experimental results on three benchmark datasets verify the superiority of UPRTH. Additional detailed investigations are conducted to demonstrate the effectiveness of the proposed framework.