arXiv · 2611.18642
Agents Cannot Hand Over What They Have Not Yet Understood
Abstract
Agents that work beyond a single context window, or in teams, hand their work to a successor as a short written summary. Evaluation has focused on whether an agent can solve a task, and relatively little is known about how much of what an agent has learned survives being written down. We study this in 56 interactive worlds with hidden rules, where an agent that is told nothing fails and an agent given a 300-character statement of the rules succeeds. We compare one agent that plays eight lives and keeps its whole history with a chain of eight agents that each play one life and inherit a 300-character note. All six models we test learn less in the chain: after eight generations it stands where the single agent stood after about four lives. Controlled variants of the chain decompose this handoff loss into three components: none from changing the agent, a smaller loss from compressing to 300 characters, and a larger loss from compressing repeatedly. When each note is written from the full record of earlier lives instead of from the previous note, the same 300 characters recover 70% to 82% of the loss. The loss is robust across model sizes and is not alleviated by instructing the writer to record evidence, to revise the inherited note, or to keep a structured ledger. In simpler terms, an agent cannot hand over what it has not yet understood: a note holds what its writer has worked out, and a rule that takes several lives to see is lost with the lives that were not passed on.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Yibo Liu. 2026-10-14. Agents Cannot Hand Over What They Have Not Yet Understood. https://searcharxiv.com/abs/2611.18642
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.