Papers by Narimawa Watanabe

5 papers
Generative Reviewer Agents: Scalable Simulacra of Peer Review (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing peer review mechanisms are limited by the small fraction of researchers with established networks.
Approach: They propose a system that extends a large language model and equips agents with reviewer personas derived from historical data to enable generative reviewers.
Outcome: The proposed architecture performs comparable to human reviewers in providing detailed feedback and predicting paper outcomes.
AlignUSER: Human-Aligned LLM Agents via World Models for Recommender System Evaluation (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluation practices for recommender systems rely on few-shot prompting and offline metrics are often misaligned with online behavior.
Approach: They propose a framework that learns world-model-driven agents from human interactions.
Outcome: The proposed framework enables agents to express rich preferences and feedback in natural language and interact with recommender systems in a simulation.
SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation (2025.acl-industry)

Copied to clipboard

Challenge: Recommender systems are a key component of our day-to-day lives, but evaluation remains a challenge due to the gap between offline metrics and online behaviors.
Approach: They propose a framework that enables users to build believable human proxies from historical data.
Outcome: The proposed framework exhibits closer alignment with real humans than previous work, both at micro and macro levels.
MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulation (2026.eacl-industry)

Copied to clipboard

Challenge: Existing methods for simulating realistic urban behaviors rely on static profiles and synchronous inference pipelines that hinder scalability.
Approach: They propose a lightweight generative agent framework for city-scale simulation powered by cognitively-grounded generative agents.
Outcome: Experiments with 4,000 agents show that MobileCity generates more human-like urban dynamics than baselines while maintaining high computational efficiency.
CitySim: Modeling Urban Behaviors and City Dynamics with Large-Scale LLM-Driven Agent Simulation (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing models rely on rigid, hand-crafted rules to model nuanced behavior in urban environments.
Approach: They propose an urban simulator that generates realistic daily schedules using a recursive value-driven approach that balances mandatory activities, personal habits, and situational factors.
Outcome: The proposed urban simulator exhibits closer alignment with real humans than previous work.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations