Research
Back to researchResearch sweep · deep · 2025 – 2026
Agentic RAG — Evolution, Challenges, and Decision Criteria
Agentic RAG between November 2025 and May 2026: how retrieval-augmented generation is shifting toward agent-driven architectures, the operational problems (token burn, context management, latency, reliability), information-organisation patterns such as context catalogues and semantic categorisation, parallels with traditional data warehousing (dimensions, measures, star schemas), the evolving RAG tooling landscape, and decision criteria for switching to pure agentic workflows.
- academic
- frontier
- tech
- blogs
- vc
Synthesised 2026-05-10
Full brief
Read the synthesised summary→
Retrieval-augmented generation has stopped being a pipeline and started being a control problem. Between November 2025 and May 2026, the dominant framing across academic, industry, and investor coverage shifted from "how do we chunk and embed better" to "how does an agent decide when, what, and how to retrieve". The…
Research lanes
5 lanes
academic
25 sources
Academic & arXiv
The 2025–2026 arXiv literature reveals a rapid transition in research framing: RAG is no longer treated as a pipeline with fixed steps but as a sequential decision-making problem. Singh et al. (arXiv 2501.09136, revised April 2026) established the dominant…
Read lane →
blogs
25 sources
Blogs & Independent Thinkers
The dominant story from blogs and independent thinkers between late 2025 and mid-2026 is not that agentic RAG has replaced static RAG but that the two are converging into a layered architecture: agents orchestrate when and how to retrieve, while RAG remains…
Read lane →
frontier
25 sources
Frontier Lab & Model News
The period from late 2024 through May 2026 saw frontier labs institutionalise agentic retrieval as a first-class architectural pattern rather than a bolt-on to static RAG pipelines. Anthropic's engineering blog documented their multi-agent research system — a…
Read lane →
tech
25 sources
Tech Industry & Practitioner
Practitioner coverage from late 2025 through May 2026 reveals a clear inflection. The Thoughtworks Technology Radar's Volume 33 (November 2025) is the most authoritative single signal: after RAG dominated Volume 32 in April 2025, Volume 33 shifted its central…
Read lane →
vc
25 sources
VC & Analyst Reports
The dominant signal from VC and analyst coverage between November 2025 and May 2026 is that static RAG, effective for human-scale query volumes, is structurally inadequate for agentic workloads. A16z's December 2025 Big Ideas report named data entropy…
Read lane →