No More, No Less: Task Alignment in Terminal Agents

Sina Mavali, David Pape, Jonathan Evertz, Samira Abedini, Devansh Srivastav, Thorsten Eisenhofer, Sahar Abdelnabi, Lea Schönherr

Abstract

Terminal agents are increasingly capable of executing complex, long-horizon tasks autonomously from a single user prompt. To do so, they must interpret instructions encountered in the environment (e.g., README files, code comments, stack traces) and determine their relevance to the task. This creates a fundamental challenge: relevant cues must be followed to complete a task, whereas irrelevant or misleading ones must be ignored. Existing benchmarks do not capture this ability. An agent may appea

Categories

Cite This Resource

@article{llmsec202600097,
  title = {No More, No Less: Task Alignment in Terminal Agents},
  author = {Sina Mavali and David Pape and Jonathan Evertz and Samira Abedini and Devansh Srivastav and Thorsten Eisenhofer and Sahar Abdelnabi and Lea Schönherr},
  year = {2026},
  url = {https://arxiv.org/abs/2605.12233},
}