← Back to all news
arXiv Computer Vision By Qing Yang, Yuqi Xiong, Pengcheng Huang, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Yu Gu, Ge Yu

Procedural Exposure Bias in Skill-Augmented Language Model Agents

Read the original on arXiv Computer Vision →

The paper investigates how language‑model agents use external procedural skills and discovers a bias called Procedural Exposure Bias (PEB), where repeated exposure to a skill’s pattern makes the model favor its associated action even when the context is unchanged. PEB is much weaker when the skill is presented visually rather than textually, mainly due to visual encoding rather than layout. Experiments across multiple environments show that visual skills lead to higher task success than textual ones, highlighting the importance of skill representation for agent decision‑making.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Aug 12

SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation

arXiv:2608. 10775v1 Announce Type: new Abstract: Computer-using agents can perceive rich software interfaces, yet their decisions often lack visual procedural memory: they may recognize individual controls without identifying which familiar workflow is active, which control matters next, or what evidence would confirm progress.

By Zhou Liu, Ligang Huang, Zeli Su, Zewei Pan, Zhaoyang Han, Xing Chen, Yuanfeng Song, Wentao Zhang
llmsragagentsefficiencymultimodal
More like this →
arXiv AI
Oct 12

Task Context Shapes Component Roles in Language Models

The study investigates how task context reshapes the roles of shared attention heads in large language models. By applying identical graph facts and measuring interventions on attention heads and downstream activations, the authors show that task changes redistribute influence across five open‑weight models, causing the same heads to respond to different facts and affect later components differently. Linear response maps before and after activation edits reveal significant reductions in prediction error, indicating that task context alters both the facts processed and the downstream impact of shared components.

By Sovesh Mohapatra, Dani S Bassett
llms
More like this →