arXiv Machine Learning August 7, 2026 By Hamed Damirchi, Ignacio Meza De la Jara, Damith Ranasinghe, Yuhang Liu, Javen Shi

Reasoning Errors Have a Region and a Direction in the Residual-Stream Trajectory of LLMs

Read the original on arXiv Machine Learning →

arXiv:2608. 05660v1 Announce Type: new Abstract: As language models are increasingly used for tasks that require verifiable reasoning, reliably distinguishing sound reasoning from flawed reasoning has become an important practical problem.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 1

Are Video Reasoning Models Ready to Go Outside?

arXiv:2603. 10652v3 Announce Type: replace-cross Abstract: In real-world deployment, vision-language models often encounter disturbances such as weather, occlusion, and camera motion.

By Yangfan He, Changgyu Boo, Jaehong Yoon

llms robotics multimodal benchmarks

arXiv Machine Learning

Aug 4

TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding

arXiv:2608. 00200v1 Announce Type: cross Abstract: Wearable sensors capture fine-grained motion patterns that support rich behavioral understanding, yet most existing methods reduce these signals to activity labels.

By Sparsh Rastogi, Tanmay Kumar, Baiyu Chen, Jatin Bedi, Zechen Li, Flora D. Salim

llms benchmarks

arXiv AI

Jun 30

Invariant Reasoning Directions in Latent Trajectories of Language Models

arXiv:2606. 29164v1 Announce Type: cross Abstract: Latent reasoning models perform multi-step inference directly in hidden-state space, yet the structure of these latent reasoning trajectories remains poorly understood.

By Arun Vignesh Malarkkan, Manan Roy Choudhury, Utkarsh Byahut, Yash Ravindra Charde, Vivek Gupta, Yanjie Fu

llms diffusion benchmarks safety

arXiv AI

Aug 7

Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models

arXiv:2605. 12519v2 Announce Type: replace-cross Abstract: Training language models to produce both correct answers and sound reasoning remains an open challenge.

By Kyuyoung Kim, Kevin Wang, Yunfei Xie, Peiyang Xu, Peiyao Sheng, Chen Wei, Zhangyang Wang, Jinwoo Shin, Pramod Viswanath, Sewoong Oh

llms reinforcement-learning fine-tuning

arXiv AI

Aug 11

Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models

arXiv:2608. 09435v1 Announce Type: new Abstract: Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time.

By Zhi Zeng, Cheng Zhang, Zesheng Yang, Rendong Pi, Jiaying Wu, Di Zhang, Zihan Ma, Guodong Li, Zhou Yang, Yu Xiang, Yifei Zheng, Minnan Luo

llms reinforcement-learning multimodal benchmarks

arXiv AI

1d ago

Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models

arXiv:2605. 08974v2 Announce Type: replace-cross Abstract: While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes.

By Tri Cao, Khoi Le, Thong Nguyen, Cong-Duy Nguyen, Quynh Vo, Anh Tuan Luu, Chunyan Miao, See-Kiong Ng, Shuicheng Yan, Bryan Hooi

llms multimodal benchmarks safety

Related stories

Are Video Reasoning Models Ready to Go Outside?

TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding

Invariant Reasoning Directions in Latent Trajectories of Language Models

Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models

Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models

Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models