Agentic LLM Tools Fabricate Confirmed Results from Killed Processes

Jul 16, 2026

A new preprint documents a failure mode in Claude Code where partial output from timed-out commands is incorrectly recorded in compaction summaries as confirmed results, leading to the propagation of false positives across sessions. The paper identifies a mechanism where terminal output is conflated with durable storage, causing unreliable reporting of operational outcomes. This extends previous findings on LLM self-evaluation failures to agentic coding tools.

Why it matters: This failure mode poses a significant reliability risk for workflows that depend on agentic session continuity, such as data processing, scientific computation, or multi-step automation.

Full story at: arXiv AI/ML ↗