- 1. The Fusion Tax: A Diagnostic Analysis of When Hybrid Retrieval Hurts · 📖 Deep dive
Hybrid retrieval fuses the results of term-matching sparse retrieval such as BM25 with those of dense vector retrieval into a single ranking, and it always wins on average…
Appeared in: 10-24
- 2. pplx-embed-v2-late Technical Report · 📖 Deep dive
Perplexity releases 0.6B and 9B multi-vector retrievers that encode text, images, and document screenshots: each document token stores a 128-d vector, and scoring sums MaxSim of each query vector against document…
Appeared in: 10-23
- 3. OpenSaC: A Python Library for Search as Code in Deep Research Agents
OpenSaC lets research agents write programs that combine search, reading, reranking, and local processing, returning selected evidence to the model. On BrowseComp, it cuts model-token use by 37.8%.
Appeared in: 10-21
- 4. FALCA: Falsification-Aware Reinforcement Learning with Hierarchical Credit Assignment for Long-Horizon Deep Search Agents
Deep search can reinforce an early mistaken hypothesis. FALCA separates answer proposals from independent counterevidence searches and trains research-state revision with hierarchical credit…
Appeared in: 10-22
- 5. When Agentic Retrieval Fails Silently: Framework and Production Evidence from a Creative AI Assistant · 📖 Deep dive
In Adobe Express's AI assistant, retrieval metrics that assume the user saw a ranked list and acted on it stop working. The chat entry point has a reformulation rate of 44.4%…
Appeared in: 10-25
- 6. Chunk Recomputation under Real Document Revisions: Measuring Update Cost and Retrieval Quality of Fixed, Recursive, and Content-Defined Chunking · 📖 Deep dive
Chunking schemes for RAG are almost always compared on one static corpus, yet the documents in a knowledge base keep changing. Each chunk is embedded on its own, so if an edit moves a chunk boundary…
Appeared in: 10-24
- 7. EG-GRPO: Evidence-Guided Step-level Credit Assignment for Deep Search Agents
EG-GRPO rewards the first search step that finds support for a required claim, then compares actions from similar evidence states. The 4B agent reaches 45.9% accuracy on GAIA.
Appeared in: 10-21
- 8. Grounded Credit Assignment in Reinforcement Learning for Multi-Turn Search Agents
A search agent can answer correctly without using retrieved evidence. Grounded Credit Assignment separates credit for finding evidence from credit for answering. On the larger evaluated model…
Appeared in: 10-20
- 9. Directional Posterior Feedback Fusion for Query Reformulation in Dense Retrieval · 📖 Deep dive
When rewriting a query vector with first-round retrieved documents or an LLM-written hypothetical answer (HyDE), the usual approach averages feedback vectors and interpolates with the original query…
Appeared in: 10-23
- 10. Let Agents Design How They Search: Automatic Interface Optimization for Agentic Search · 📖 Deep dive
Korea University and KAIST have Claude Code (Claude Opus 5.5) design retrieval tools for a search agent: it reads each question's execution log and score, jointly edits pre-generated index files…
Appeared in: 10-23