INFUSER: Influence-Guided Self-Evolution Improves Reasoning
This story is from 2026-08-24. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2606.09052v4 Announce Type: replace-cross Abstract: Self-evolution offers a scalable path to stronger reasoning: a pretrained language model improves itself with only minimal external supervision. Yet existing methods either depend on extensively curated or teacher-generated training data, or…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-08-24 04:00 · arXiv stat.ML
INFUSER: Influence-Guided Self-Evolution Improves Reasoning