The Signal

Everything that matters in AI, with our take.

Updated through the day. Every headline links straight to the source. The two lines underneath are ours.

agents162 research126 infra70 claude69 capital49 labs43 culture39 safety38 openai33 regulation30 anthropic24 security24 reasoning19 evaluation18 robotics13 frontier-models12

arXiv cs.AIPaper9d ago

RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing

RAG's weak point is that it assumes evidence sits in a database waiting to be found. RECAST flips this: evidence is computed from multiple sources through routing decisions. This matters for builders working on complex tasks (financial analysis, policy research, scientific reasoning) where the answer lives in the pattern across sources, not in any single item. Early signal on a real problem in the RAG stack.

rag agents retrieval reasoning

arXiv cs.CLPaper11d ago

T-Search: An Open Agentic Retriever and Playground for Hard Multi-Step Search

This is a clean decomposition. The retriever runs search independently, leaves answer generation to whatever model you want, and includes three new benchmarks including a Russian hard-search dataset. 61.3 Recall@10 with three fused rollouts is solid. For builders: if you need a retrieval backbone for RAG or search-augmented generation, this is a usable open-weight option. The fact it swaps the backend without retraining is the real win.

retrieval agents open-source

arXiv cs.LGPaper24d ago

The Sirens' Song: When Proximal Background Context Overshadows Distant Evidence

Long-context LLMs have a real problem: they ignore distant information not because it's far away, but because nearby noise is louder. LYRA's solution is mechanically sound and shows gains across standard benchmarks. For builders using long-context models for retrieval-heavy tasks (RAG, document QA, multi-hop reasoning), this is a concrete win. The practical question is whether the improvement justifies reranking or other post-processing, or if you just need to be smarter about what goes in the context window.

research long-context attention retrieval