# DOLORES preprint reports 24.8% gain from adaptive agent reasoning

_Published Monday, October 26, 2026 at 11:06 AM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers report that an agent called DOLORES improved performance by 24.8% on average over the strongest evaluated scaffold baseline across four difficult benchmarks. The preprint tests an approach that lets an agent construct a task-specific reasoning structure during execution rather than follow a fixed sequence.

The system uses a formal language to divide work among associative inference, formal computation and recursive problem solving. Tests covered multi-hop reasoning, long-chain question answering, long-context aggregation and research-style information seeking across three model sizes and two model families.

An 8B version surpassed all evaluated 32B baselines from the same family in more than half the settings; the results concern the evaluated benchmarks.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2605.11388)

---
Canonical: https://techandbusiness.org/newswire/n7J4OdZwuiQlC54BFPi2jZ
Published: 2026-10-26T15:06:10.070Z
Story chronology: 2026-10-26T04:00:00.000Z
Retrieved: 2026-10-26T18:01:15.261Z
Publisher: Tech & Business (techandbusiness.org)