CoRE Framework Learns Rule Routing for Knowledge Retrieval Without Supervision
Zhisheng Qi · hf · 2026-10-26
A paper from University of Georgia, Michigan State and collaborators proposes CoRE (Co-Adaptive Rule Routing and Constraining Retrieval) for structured knowledge retrieval.
- Existing methods either retrieve unconstrained or rely on predefined query-rule supervision pairs that are rarely available in practice
- CoRE uses a routing agent to assign each query a reasoning rule, while the retriever traverses the knowledge base and ranks evidence satisfying that rule's constraints
- The framework formulates this as alternating optimization: reinforcement learning for rule routing and contrastive learning for the rule-constraining retriever
- No predefined query-rule pairs are needed for training
More from Research
- Judea Pearl boosts Oregon State PhD opening at causal inference × AI intersection — yudapearl · 2026-10-26
- davidad digs into 'dynamical-systems attractor-structure functionalism' via Conley index theory — davidad · 2026-10-26
- Sakana AI hosts Tokyo RSI symposium: AI Scientist in Nature, Schmidhuber keynotes — RobertTLange · 2026-10-26
- HuggingFace's Carbon-X Spots Pathogenic Splice Variant Where Gemini 3.8 Flash Misreads the Gene — LoubnaBenAllal1 · 2026-10-26
- ETH Zurich paper: dynamic evaluation allocation matches 10x-budget model rankings — zouharvi · 2026-10-26
- DuoLM: Fast LLM-Based Personalized Recommendation via Compact Encoder-Ranker — GoogleDeepMind · 2026-10-26