arxiv
PublishedJune 2, 2026 at 4:00 AM
▲bullish
KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning
Publisher summary· verbatim
arXiv:2606.00532v1 Announce Type: new Abstract: Context engineering can improve large language models without updating their weights, but mathematical reasoning exposes a key limitation: feedback accumulated in one growing prompt causes context bloat and limits the amount of learned guidance that ca
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 Pruning10harxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning10harxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models10harxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents10hThe Bubble Brief
WEEKLYRead context-engineering insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗