From AutoResearch to Continual AutoResearch: Do Agents Learn Across Tasks?
Source check: Source checked. Not independent scientific confirmation.
Finding / tested result: Matched persistent and reset agent sessions across nine task families show an empirical efficiency gain that does not consistently carry over to final held-out quality.
Technology: LLM research agents with persistent versus reset sessions
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Five frontier agents run matched persistent or reset research sessions with the same tasks, tools, and time limits.
- Limitation / still unknown
- Matched task streams and time budgets are used; several model-task comparisons have one run pair, and final-quality gains are inconsistent.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://arxiv.org/html/2611.05108v1
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.