Namyoung So
Author directoryAlso published as: Namyeong So
2026
Superficial Success vs. Internal Breakdown: An Empirical Study of Generalization in Adaptive Multi-Agent Systems
Namyeong So | Seokgyu Jang | Taeuk Kim
Findings of the Association for Computational Linguistics: ACL 2026
Namyeong So | Seokgyu Jang | Taeuk Kim
Findings of the Association for Computational Linguistics: ACL 2026
Adaptive multi-agent systems (MAS) are increasingly adopted as solutions to complex problems. However, their optimization for narrow task ranges leaves it unclear whether they can function as general-purpose systems. To fill this gap, we conduct an extensive empirical study on adaptive MAS, revealing two key findings: (1) they are prone to topological overfitting, defined as failures in domain transfer; and (2) they exhibit illusory coordination, where surface-level accuracy is high but underlying agent coordination deviates from ideal MAS behavior, raising concerns about their practical effectiveness. These observations highlight the urgent need to prioritize generalization in MAS development and motivate more thorough evaluation beyond correctness of the final answer.
2025
Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents
Yejin Yoon | Yuri Son | Namyoung So | Minseo Kim | Minsoo Cho | Chanhee Park | Seungshin Lee | Taeuk Kim
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Yejin Yoon | Yuri Son | Namyoung So | Minseo Kim | Minsoo Cho | Chanhee Park | Seungshin Lee | Taeuk Kim
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Conversational agents have traditionally been developed for either task-oriented dialogue (TOD) or open-ended chitchat, with limited progress in unifying the two. Yet, real-world conversations naturally involve fluid transitions between these modes. To address this gap, we introduce TACT (TOD-And-Chitchat Transition), a dataset designed for transition-aware dialogue modeling that incorporates structurally diverse and integrated mode flows. TACT supports both user- and agent-driven mode switches, enabling robust modeling of complex conversational dynamics.To evaluate an agent’s ability to initiate and recover from mode transitions, we propose two new metrics—Switch and Recovery.Models trained on TACT outperform baselines in both intent detection and mode transition handling. Moreover, applying Direct Preference Optimization (DPO) to TACT-trained models yields additionalgains, achieving 75.74% joint mode-intent accuracy and a 70.1% win rate against GPT-4o in human evaluation.These results demonstrate that pairing structurally diverse data with DPO enhances response quality and transition control, paving the way for more proactive and transition-aware conversational agents.
Search