Source record

Published by arXiv cs.MA (T1 source). The original is at https://arxiv.org/abs/2609.00012.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

A research paper tests whether LLMs can maintain exact intermediate state across long sequences of dependent tool calls by having a model compute MD5 step by step across 196 calls and 64 rounds. Using gpt-oss-120b, it finds that keeping the model's own reasoning in context and voting over a thinking-enabled worker enables correct end-to-end execution.

Isolates state-tracking from instruction following using a cryptographic ground truth, and surfaces two concrete fixes—context-resident reasoning and worker voting—for long-horizon agent failures.

Cited by

No citations on record.