Yuchen Li

Winning the IROS 2026 Indoor Exploration Competition, this solution integrates pre-trained map completion and time-aware homing for single-robot exploration, and a utility-driven, data-sharing approach for multi-robot coordination.

Results show that the effectiveness of TabPFN is highly problem dependent, and it cannot replace conventional surrogates universally, and it should be adopted selectively according to data availability, landscape complexity, search space characteristics, and its role within the algorithm.

This paper proposes SWRouter, a Similarity-Contractive Window Router for multi-turn large language model routing that combines a similarity-based context segmentation mechanism for prompt construction with a dual-metric evaluation framework that decouples construction accuracy from router performance.

Deleting obsolete memories breaks historical recall, but keeping them poisons current reasoning—a trade-off solved by permanently storing raw history while dynamically masking superseded facts using query-conditioned semantic slots.

Real-world complexities expose significant performance gaps in autonomous agents, revealing that even advanced LLMs struggle with task completion in dynamic environments.