30 papers
EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents
Dongwook Choi, Taeyoon Kwon, Bogyung Jeong +6
MLLM-powered embodied agents deployed in real-world environments encounter physical hazards. However, existing approaches lack explicit mechanisms for identifying hazards and reaso…
Towards Direct Evaluation of Harness Optimizers via Priority Ranking
Kai Tzu-iunn Ong, Minseok Kang, Dongwook Choi +9
Harness optimization enables automated agent creation by having an optimizer agent iteratively update the harness of target agents. Despite its success, current studies evaluate op…
On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
Sunghwan Kim, Junhee Cho, Beong-woo Kwak +6
Large language models (LLMs) have shown promise as interactive agents that solve tasks through extended sequences of environment interactions. While prior work has primarily focuse…
MVIGER: Multi-View Variational Integration of Complementary Knowledge for Generative Recommender
Tongyoung Kim, Soojin Yoon, SeongKu Kang +2
Language Models (LMs) have been widely used in recommender systems to incorporate textual information of items into item IDs, leveraging their advanced language understanding and g…
PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints
Minjun Park, Donghyun Kim, Hyeonjong Ju +5
We are entering an era in which individuals and organizations increasingly deploy dedicated AI agents that interact and collaborate with other agents. However, the dynamics of mult…
Why These Documents? Explainable Generative Retrieval with Hierarchical Category Paths
Sangam Lee, Ryang Heo, SeongKu Kang +3
Generative retrieval directly decode a document identifier (i.e., docid) in response to a query, making it impossible to provide users with explanations as an answer for ``why is t…