Rewarding Efficient Reasoning Improves Abstention on Underspecified Tasks in Reasoning Models
arXiv 2609.20846v1•e33975043df88f3b81da9bb331375e8b959ac9905367fb4af28874043ab54d81
Paper metadata
- arXiv ID
- 2609.20846
- Version
- v1
- Category
- cs.CL, cs.LG
- Authors
- Polina Tsvilodub, Max H\"oth, Michael Franke, Bj\"orn Deiseroth, Carina Kauf
- Publication date
- 2026-09-21T04:00:00Z
- Source identifier
- 2609.20846v1
- Public record ID
- record:sha256:e33975043df88f3b81da9bb331375e8b959ac9905367fb4af28874043ab54d81
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.
Evidence and limitations
- Source ID
- arxiv_research
- Record identifier
- e33975043df88f3b81da9bb331375e8b959ac9905367fb4af28874043ab54d81
- Record type
- Source metadata
This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.