arxiv
PublishedMay 27, 2026 at 4:00 AM
MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation
Publisher summary· verbatim
arXiv:2605.27186v1 Announce Type: new Abstract: Large language models often solve tasks from a fully specified prompt but degrade when the same requirements unfold over multiple turns, known as the lost-in-conversation (LiC) gap. We trace part of this degradation to self-contamination: intermediate
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning8harxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning8harxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models8harxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents8hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗