LLM Digest

Story

arxiv_agent_systems_research · Nov 4, 2026 · paper

Source brief

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

arxiv.orgNov 4, 2026
original source linked

In brief

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 fro

Read the original at arxiv.org →Open in live feed Read that day’s brief

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

Earlier in this thread 4 items

CRESiST: Self-Enhancing Explorative Policy Learning for Simultaneous Speech Translation

LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation

What can an LLM build with only 32 CPU instructions?

Optimizing Stochastic Policy Geometry for Few-Step Flow Reinforcement Learning