Evolving semantic indexes for generative retrieval
LLM-driven evolutionary search is starting to auto-design the discrete pieces of generative search indexes.
DailyUpdated 2026-11-07 12:20 UTC5 articles
Context & memory
Context engineering, retrieval, long-horizon memory, knowledge for agents
Latent Compaction: training KV caches at test time
How Latent Compaction treats the KV cache as a trainable latent and squeezes 32× context with minimal accuracy loss.
Wiring multimodal patients into clinical KGs
MM-KG makes explicit, testable links between patient data and biomedical graphs, changing how clinical LLM stacks should use knowledge.
Recursive video hierarchies for robot agents
Turning demo videos into navigable tool hierarchies instead of bloated prompts.
Source learning and persistent source models
Turning repeated source access into reusable, source-specific competence for LLM agents
Live signals on Context & memory
- Show HN: Gauge – Open-Source CLI to recursively improve your docs Hacker News · 2 days ago · frontier 71%
- @ladyxtel: We decoupled memory from the model. X · vibecoding radar · 3 days ago · frontier 74%
- @AnthropicAI: Memory is what allows Claude to learn from experience. In a new Engineering Blog post, we… X · ai radar · 18 h ago · frontier 69%
- @omarsar0: Highly recommended paper from NVIDIA. X · vibecoding radar · 3 days ago · frontier 77%
- MedGraph: Maintaining Patient State with Graph Memory for Long-Term Medical Dialogue arXiv · 1 days ago · frontier 70%
- SpecCompact: Accelerating LLM Agent Context Compaction with Slot-Parallel Semantic Speculative Verification arXiv · 2 days ago · frontier 72%
- Enhancing Local and Global Structure in Compressed AI Agent Memory arXiv · 1 days ago · frontier 70%