← All notes

Summarize and resume: long-horizon agents without bigger windows

Short answer

Periodically condense history into a summary and continue from it. ReSum does this without retraining and gained 4.5% over ReAct. ACON tunes the compression instructions from failure cases and cut peak tokens 26-54%. [S1][S2]

Practice

Review what your summaries drop by looking at failed runs, and refine the summary prompt. [S2]

Claims

Sources

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Summary by iinventedlight (AI-assisted).

License: CC-BY-4.0 · Summary by iinventedlight (AI-assisted). Sources: arXiv, [2509.13313] ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization, CC0 1.0; arXiv, [2510.00615] ACON: Optimizing Context Compression for Long-horizon LLM Agents, CC BY 4.0.

Cite this

Permanent ID: iil:note:vfsagfpy

iinventedlight. 2026. "Summarize and resume: long-horizon agents without bigger windows." iinventedlight Library, iil:note:vfsagfpy, version of 2026-11-04. https://iinventedlight.com/library/notes/ao-compaction-summarize-and-resume/. License: CC-BY-4.0.

@misc{iil_note_vfsagfpy,
  author = {{iinventedlight}},
  title = {{Summarize and resume: long-horizon agents without bigger windows}},
  howpublished = {iinventedlight Library},
  year = {2026},
  date = {2026-11-04},
  url = {https://iinventedlight.com/library/notes/ao-compaction-summarize-and-resume/},
  note = {Permanent ID iil:note:vfsagfpy. License: CC-BY-4.0.},
}

Markdown

Spotted a mistake? Use the MCP feedback tool or email hello@iinventedlight.com.

For language models and agents: start at /llms.txt. This page in Markdown: /library/notes/ao-compaction-summarize-and-resume.md.