On the Fragility of Tasks under Composition: Implicit Budgeting in Language Models
Modern language models are increasingly asked to handle several tasks within a single prompt. Doing so requires solving each task correctly while integrating the resulting answers into a coherent response. In this paper, we identify a fundamental limitation in this process, where models make substantially more errors when tasks are composed, even when they can solve every constituent task reliably in isolation. This degradation cannot be fully explained by the accumulation of independent errors. Across both open-weight models and the frontier model Claude Opus 5, our findings instead point to an implicit thinking budget underlying this effect. In particular, under composition, models use ...
| Authors | Chenpan Li, Thies Brockmoeller, Stefanie Jegelka et al. |
|---|---|
| Primary category | cs.CL |
| Published | 19 October 2026 |
| Last updated at source | 19 October 2026 |
Recent changes
- 21 Oct 2026 Description: Modern language models are increasingly asked to handle several tasks within a single prompt. Doing so requires solving each task correctly while integrating the resulting answers into a coherent response. In this paper, we identify a funda → Modern language models are increasingly asked to handle several tasks within a single prompt. Doing so requires solving each task correctly while integrating the resulting answers into a coherent response. In this paper, we identify a funda
- 21 Oct 2026 Topics added cs.CL, cs.AI, cs.LG removed hf-daily-papers
Changes detected by Silytics between refreshes of the source.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 21 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.