paper-with-me

Papers

Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems

2025-05-22 · Song Jin, Juntian Zhang, YuHan Liu, Xun Zhang, Yufei Zhang, Guojun Yin, Fei Jiang, Wei Lin, Rui Yan

Evaluating and iterating upon recommender systems is crucial, yet traditional A/B testing is resource-intensive, and offline methods struggle with dynamic user-platform interactions. While agent-based simulation is promising, existing platforms often lack a mechanism for user actions to dynamically reshape the environment. To bridge this gap, we introduce RecInter, a novel agent-based simulation platform for recommender systems featuring a robust interaction mechanism. In RecInter platform, simulated user actions (e.g., likes, reviews, purchases) dynamically update item attributes in real-time, and introduced Merchant Agents can reply, fostering a more realistic and evolving ecosystem. High-fidelity simulation is ensured through Multidimensional User Profiling module, Advanced Agent Architecture, and LLM fine-tuned on Chain-of-Thought (CoT) enriched interaction data. Our platform achieves significantly improved simulation credibility and successfully replicates emergent phenomena like Brand Loyalty and the Matthew Effect. Experiments demonstrate that this interaction mechanism is pivotal for simulating realistic system evolution, establishing our platform as a credible testbed for recommender systems research.

📄 PDF Abstract BibTeX arXiv:2505.16429

Code (0)

등록된 구현이 없습니다.

Tasks

Recommendation Systems

Similar Papers 제목 키워드 기반

Beyond Static Evaluation: Rethinking the Assessment of Personalized Agent Adaptability in Information Retrieval

2025-10-05 · Kirandeep Kaur, Preetam Prabhu Srikar Dammu, Hideo Joho, Chirag Shah arxiv

Personalized AI agents are becoming central to modern information retrieval, yet most evaluation methodologies remain static, relying on fixed benchmarks and one-off metrics that fail to reflect how users' needs evolve o…

Information Retrieval

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning

2025-09-24 · Cheng Qian, Zuxin Liu, Akshara Prabhakar, Jielin Qiu 외 arxiv

Reinforcement learning (RL) has shown promise in training agentic models that move beyond static benchmarks to engage in dynamic, multi-turn interactions. Yet, the ultimate value of such agents lies in their ability to a…

Reinforcement Learning

LLMs Get Lost in Evolving User Intent

2026-07-22 · Jihoon Tack, Philippe Laban, Jennifer Neville hf

As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-delegated tasks through iterative interaction. Yet genuine interaction is inherently dynamic: users rarely specify their…

Quo Vadis, World Modeling?

2026-08-03 · Yu Yang, Xuemeng Yang, Licheng Wen, Lingdong Kong 외 hf

Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize. World modeling offers a natural inter…

Agent Skills Should Go Beyond Text: The Case for Visual Skills

2026-05-31 · Binxiao Xu, Ruichuan An, Bocheng Zou, Hang Hua arxiv

Reusable skills are a key mechanism for extending agent capabilities, allowing agents to accumulate experience and solve increasingly complex tasks. Yet most existing skill-learning methods store reusable experience as t…

Visual Grounding