Tootfinder

Efficient Manipulation-Enhanced Semantic Mapping With Uncertainty-Informed Action Selection
Nils Dengler, Jesper M\"ucke, Rohit Menon, Maren Bennewitz
https://arxiv.org/abs/2506.02286

Efficient Manipulation-Enhanced Semantic Mapping With Uncertainty-Informed Action Selection
Service robots operating in cluttered human environments such as homes, offices, and schools cannot rely on predefined object arrangements and must continuously update their semantic and spatial estimates while dealing with possible frequent rearrangements. Efficient and accurate mapping under such conditions demands selecting informative viewpoints and targeted manipulations to reduce occlusions and uncertainty. In this work, we present a manipulation-enhanced semantic mapping framework for oc…

1/N Teemapäiviä riittää. Tänään on näköjään Maailman ympäristöpäivä. "Ympäristö" on sana, joka laimenee joka hetki, kun se saa eteensä aina uusia, vahvoja täsmenteitä: turvallisuuusympäristö, poliittinen ympäristö, toimintaympäristö, psyykkinen ympäristö, kulttuuriympäristö, tietotekninen ympäristö. "Ympäristö" on silloin yhä enemmän vain sana ilman sisältöä, ellei selvästi joka kerta sanota millaisista ympärillämme olevista asioista ja asioiden luokista on tällä kertaa k…

WHEN TO ACT, WHEN TO WAIT: Modeling Structural Trajectories for Intent Triggerability in Task-Oriented Dialogue
Yaoyao Qian, Jindan Huang, Yuanli Wang, Simon Yu, Kyrie Zhixuan Zhou, Jiayuan Mao, Mingfu Liang, Hanhan Zhou
https://arxiv.org/abs/2506.01881

WHEN TO ACT, WHEN TO WAIT: Modeling Structural Trajectories for Intent Triggerability in Task-Oriented Dialogue
Task-oriented dialogue systems often face difficulties when user utterances seem semantically complete but lack necessary structural information for appropriate system action. This arises because users frequently do not fully understand their own needs, while systems require precise intent definitions. Current LLM-based agents cannot effectively distinguish between linguistically complete and contextually triggerable expressions, lacking frameworks for collaborative intent formation. We present…

From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval
Dohyeon Lee, Yeonseok Jeong, Seung-won Hwang
https://arxiv.org/abs/2505.23059

From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval
Chain-of-Thought (CoT) prompting enables complex reasoning in large language models (LLMs), including applications in information retrieval (IR). However, it often leads to overthinking, where models produce excessively long and semantically redundant traces with little or no benefit. We identify two key challenges in IR: redundant trajectories that revisit similar states and misguided reasoning that diverges from user intent. To address these, we propose State Machine Reasoning (SMR), a transi…