Context engineering
Technique · Agents · 2 items since Jun 2026
Deciding what information goes into a model's context, and when, to steer its behavior.
Related
- Organizations
Trends
Items
- Jul 3
Agents often fail to stop when they should
Across 28,000+ tasks and 13 agent systems, larger models often abstain less promptly; the CONVOLVE context-engineering method lifts Llama-3.3-70B's timely-abstention recall from 26.7 to 57.4 without weight updates.
- Jun 15
Zhejiang University's TokenPilot
A dual-granularity context manager that stabilizes prompt prefixes and evicts stale context only when its task relevance expires, cutting long-horizon agent inference costs by 56-87% without breaking the prompt cache.