When both Grounding and not Grounding are Bad -- A Partially Grounded Encoding of Planning into SAT (Extended Version)
arXiv 2603.19429•add3b5f465b91924c810edbf546f105c1f22860efedb88cd7f09961fdfac0a00
IsabelleItinBenchLean 4SAT encodingagentsalignmentartificial intelligencebenchmarkscounterexample generationformal methodsformal verificationhybrid workflowslarge language modelslifted representationsmobile power managementmulti-objective optimizationneuro-symbolic searchplanningprivacyreinforcement learningsafetyseL4self-improvementtheorem proving
Paper metadata
- arXiv ID
- 2603.19429
- Version
- Not specified by this published record
- Category
- Computer Science — Artificial Intelligence (cs.AI)
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
Evidence and limitations
- Source ID
- arxiv_cs_ai
- Record identifier
- add3b5f465b91924c810edbf546f105c1f22860efedb88cd7f09961fdfac0a00
- Enrichment time
- 2026-03-23T08:52:13Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.