arXiv AI By Yiheng Sun, Huifei Wang, Yancheng Zhu, Zhenyu Li, Zebin Zhao, Yifan Yuan

When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows

Read the original on arXiv AI →

Large language model agents coordinate tasks via multi‑role, multi‑stage workflows that transform upstream state into intermediate artifacts such as summaries and plans. The study shows that when these artifacts are transformed—through compression, plan assimilation, or other handoff methods—the strict action‑binding constraints on upstream state can be weakened, turning mandatory requirements into optional information. In 1,296 synthetic episodes, direct handoff preserved all safety blockers, whereas transformed handoffs frequently deactivated or forbidden actions, but restoring full state fields or applying downstream verification can recover preservation.

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 AI.

arXiv AI
Aug 14

Dead text or binding clause? Measuring and restoring constraint influence in black-box LLM dialogues

arXiv:2608. 12599v1 Announce Type: new Abstract: Multi-turn dialogues let users revoke constraints as easily as impose them, but revocation does not reliably take effect: models keep enacting withdrawn requirements (occasionally beneath comments asserting their removal), a failure we call \emph{behavioral relapse}, or revocation inertia.

By Haoyuan Zhu
arXiv AI
3d ago

Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol

The paper introduces a framework for evaluating how large language model agents revise their success criteria after failures, defining five non‑compensatory conditions that must be met for a criterion revision to be considered valid. Using the CMB‑0.1 protocol, the authors test twelve cross‑domain scenarios across four system configurations, finding that no model trial satisfies all five conditions and highlighting specific failure modes such as zero‑state reconstruction and inadequate intervention sensitivity. They propose a more stringent trace‑anchored CMB‑0.4 protocol to better isolate and measure criterion revision in future studies.

By Guodong Xu