Tootfinder

🎲 TextBandit: Evaluating Probabilistic Reasoning in LLMs Through Language-Only Decision Tasks
#llm

TextBandit: Evaluating Probabilistic Reasoning in LLMs Through Language-Only Decision Tasks
Large language models (LLMs) have shown to be increasingly capable of performing reasoning tasks, but their ability to make sequential decisions under uncertainty only using natural language remains underexplored. We introduce a novel benchmark in which LLMs interact with multi-armed bandit environments using purely textual feedback, "you earned a token", without access to numerical cues or explicit probabilities, resulting in the model to infer latent reward structures purely off linguistic cu…

JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation
Shuang Zeng, Dekang Qi, Xinyuan Chang, Feng Xiong, Shichao Xie, Xiaolong Wu, Shiyi Liang, Mu Xu, Xing Wei
https://arxiv.org/abs/2509.22548

JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation
Vision-and-Language Navigation requires an embodied agent to navigate through unseen environments, guided by natural language instructions and a continuous video stream. Recent advances in VLN have been driven by the powerful semantic understanding of Multimodal Large Language Models. However, these methods typically rely on explicit semantic memory, such as building textual cognitive maps or storing historical visual frames. This type of method suffers from spatial information loss, computatio…