# When Do Summaries Become Instructions? Unsupported Policy in LLM Agents' Self-Written Handoff Summaries

**Authors:** Wenhui Chu  
**Lab:** State University of New York · **Published:** 4 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.06545) · [PDF](https://arxiv.org/pdf/2611.06545) · [Code](https://github.com/Chuw1/handoff-audit) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.06545.html)

## Key numbers

- **1.2%**: confirmed unsupported restrictions in 1.2% and 2.4% of all readable summaries from two open-weight models
- **0.1%**: and unsupported authorizations in 0.1% and 1.3%
- **5.0% → 1.8%**: …saying where requirements come from cut unsupported restrictions from 5.0% to 1.8% of development summaries and

## Abstract

Long-running LLM agents compact their context, replacing most history with a summary. We ask whether handoff summaries state permissions or requirements the record does not support, whether such sentences change what the next instance (the successor) does, and where they come from. Synthetic tool-use tasks carry a ground-truth permission ledger; same-snapshot replay reruns the successor with those whole sentences replaced by neutral filler. Two AI readers, reading only rule-flagged held-out summaries, confirmed unsupported restrictions in 1.2% and 2.4% of all readable summaries from two open-weight models, and unsupported authorizations in 0.1% and 1.3%. For restrictions, a pre-specified replay test was not significant (p = 0.58); a follow-up, planned after it, found a fragile effect (p = 0.027). Neutralizing false approvals cut unauthorized actions from 24 to 7 of 120 held-out runs (post hoc; later set: 17 to 11 of 48). Most development restrictions followed the agent's earlier reasoning that an action needs approval (post hoc). In pre-specified tests, replacing the system prompt's "Some actions need approval." with one saying where requirements come from cut unsupported restrictions from 5.0% to 1.8% of development summaries and, on held-out templates, from 1.8% to 0.3% (both p < 10^-9), while requests for approvals the ledger requires barely changed. Code and data: https://github.com/Chuw1/handoff-audit

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.