Metraipolis › archive › dc_3eb449982cfd
RECEIPT: Measuring and Repairing the Return Assumption of LLM Agents in Web Service Operations — arXiv:2611.01930
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01930
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:47:59.725Z
- SHA-256 of the archived text
294471d449acb8e8d026353983419d4cba5306758d83cfcfd304bdd0c04e65ae- Stable URL of this page
https://metraipolis.com/documento/dc_3eb449982cfd
How to cite
RECEIPT: Measuring and Repairing the Return Assumption of LLM Agents in Web Service Operations — arXiv:2611.01930 — arXiv (en), https://arxiv.org/abs/2611.01930 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3eb449982cfd (Metraipolis archive dc_3eb449982cfd, sha256 294471d449acb8e8d026353983419d4cba5306758d83cfcfd304bdd0c04e65ae)
BibTeX
@misc{dc3eb449982cfd,
title = {RECEIPT: Measuring and Repairing the Return Assumption of LLM Agents in Web Service Operations — arXiv:2611.01930},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01930},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3eb449982cfd; sha256 294471d449acb8e8d026353983419d4cba5306758d83cfcfd304bdd0c04e65ae},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01930. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM agents operate Web infrastructure from the command line and rely on a return assumption, namely that each tool call returns within a bounded time and with its requested action finished. Many commands, however, ask a question before they act, and the agent's harness either closes the program's input or keeps it open as a terminal at which nobody types. With closed input, the program can return status 0 without the requested action. With open input, it waits until a time limit, and the agent pays in time and tokens. To the best of our knowledge, this paper is the first to measure and repair the return assumption. We collect 91,469 production tool calls and 89,047 public agent trajectories, test how 8 widely used harnesses launch commands, and build Litmus, a catalog of 158 checked command-line invocations, and Tripwire, a benchmark of 25 task pairs that differ only in whether a question guards the requested action. We then propose RECEIPT, which keeps the input open, reads what each process waits for from system calls, and returns this state to an unmodified agent through a model-checked protocol. On Litmus, closed input causes 11.5% of tested invocations to return status 0 without performing the requested action, and 7 of 8 harnesses close input when no terminal is attached. An unanswered question at a plain terminal multiplies a task's token use by 2.9, and the input connection moves an LLM from 7th to 3rd place among 8. Across 5 LLMs, RECEIPT reduces false claims of success by 73.5% and completes all 25 guarded tasks on a second harness. An agent's reliability therefore depends on what its harness lets it observe as well as on its LLM. Agent builders should report what each tool call did, not only how it ended, and benchmark maintainers should fix and report the input connection before they rank LLMs. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.01930 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T10:39:50.524Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).