One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness
Paper recorded by Signals 4 on 2026-10-14 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-14 on arXiv · recorded by Signals 4 on 2026-10-15
Category: cs.AI · 人工智能 · first seen 2026-10-15
Abstract
Post-training binds the competence of an LLM agent to the interface it was trained on. Semantics-preserving perturbations of that interface, such as renaming an action or changing the notation, leave the underlying task unchanged yet make the agent worse at it. Scoring each sample independently means interface randomization only broadens this dependence from a single interface to the training inte
Read on arXiv →
Cite this page: One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness: the #308 most recent of 960 cs.AI papers we have recorded (as of 2026-10-14). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/one-task-many-interfaces-simple-cross-interface-consistency-training-improves-ll.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free