Recent agentic systems (Claude Code, Codex, RLM, etc.) push context out of the prompt and into the environment (e.g., as files). This helps them maintain long-term knowledge about their goals and functionality.
๐จ While this is a good idea, we show a surprising result: systems that use external environments like this perform much better when given a small, fixed-size, in-context, agent-managed cache that "๐ฑ๐ฆ๐ฆ๐ฌ๐ด ๐ช๐ฏ๐ต๐ฐ" these environments.
๐ Our paper, ๐ฃ๐๐๐: ๐ ๐จ๐ฎ๐จ๐ฉ๐๐ข ๐๐ค๐ง ๐๐ช๐๐ก๐๐๐ฃ๐ ๐๐ฃ๐ ๐ข๐๐๐ฃ๐ฉ๐๐๐ฃ๐๐ฃ๐ ๐ฎ๐ป ๐ผ๐ฟ๐ถ๐ฒ๐ป๐๐ฎ๐๐ถ๐ผ๐ป ๐ฐ๐ฎ๐ฐ๐ต๐ฒ ๐๐ค๐ง ๐๐๐ ๐๐๐๐ฃ๐ฉ๐จ, introduces this idea.
Compared with strong baselines, including RAG, Compaction Agents, and SOTA prompt-learning frameworks, PEEK dominates the costโquality Pareto frontier: achieving +6.3โ34.0% in quality, with fewer iterations and lower cost.
Paper: https://t.co/67pm4Dqbw5
GitHub: https://t.co/JNMehuzN9M
More in the thread below! (1/N)
๐ข CfP: Conference on Innovative Data Systems Research #CIDR2027 (Amsterdam, The Netherlands). Papers due: August 4, 2026. @ViktorLeis, @samrmadden, and I are looking forward to your paper & demo submissions! https://t.co/Vf4TDqWqJO
๐ฃ We're spreading the word about #SemBench -- a brand new benchmark for semantic query processing over multimodal workloads including text, image, audio, and tabular data!
๐Paper: https://t.co/Vai6Z3aRQK
๐ปWebsite: https://t.co/yAPaQwhagF
๐พCode: https://t.co/nSBE9vEXbC
๐ข CfP: Conference on Innovative Data Systems Research #CIDR2026 (Chaminade, USA). Papers due: August 5, 2025. Gustavo Alonso, @samrmadden, and I are looking forward to your paper & demo submissions! https://t.co/oOB4kPp3R3
@sirrice@sigmod@VLDBconf Just go build stuff you think is cool, and publish about it in the venue you think is the best fit. Our community will be fine; we will find fascinating ways to build new AI powered data systems!
@sirrice@sigmod@VLDBconf Thanks for this post, @sirrice . As Iโm sure Iโve said to you, Iโm not a huge fan of โnavel gazingโ. We had these same conversations in 2000, 2010, etc โ and we found ways to contribute to the Internet, Big Data, Cloud, โฆ
@joe_hellerstein@overleaf Did I miss some announcement? It looks like UCB pays for a site license? For those asking, I find for multi-author papers supporting concurrent editing is significantly better than git-based versioning. I do agree that it is worrying that papers are now archived on Overleaf.
It took three years to finish, but our follow-up to the 2006 "What Goes Around Comes Around" is finally out! Stonebraker and I examine the last 20 years in databases and discuss why relational databases + SQL will continue to remain on top.
๐PDF: https://t.co/ZwTWSxXLWb
๐จ NEW EPISODE: High Impact in Databases with... Joe Hellerstein (@joe_hellerstein) is available now!
๐ง Listen on Apple โก๏ธ https://t.co/02zfDQ6O5Y
๐ง Listen on Spotify โก๏ธ https://t.co/PgTrDblzJx
โ๏ธ Support the podcast โก๏ธ https://t.co/tVHEIk5EgN
If this (very high-level) summary of our work has piqued your interest -- go read our full paper!
๐Paper: https://t.co/x7K4fmb2MX
๐ปCode: https://t.co/XwDp6K2mtM
We would love to hear any feedback, ideas for more use cases, and/or opportunities for collaboration.