FlowBank: NeurIPS paper reuses complementary agent workflows for 73.40 avg vs 70.40 baseline
furongh · x · 2026-10-05
A thread introducing FlowBank, a NeurIPS paper on optimizing the workflow layer of LLM multi-agent systems.
- Key insight: most optimizers keep a single winning workflow, but a below-average workflow often solves exactly the queries the winner misses
- FlowBank precomputes complementary workflows offline, curates a compact bank, and adaptively selects one per query to balance performance and cost
- Motivated by OpenAI's 10,000 agents collaborating on Navier–Stokes: which ways of agent collaboration are worth reusing?
More from coding & agent
- Free AI Engineering course covers foundation models, evals, prompt engineering and security — Negative_War_65 · 2026-10-05
- Most coding agents today are hand-rolled loops, not framework abstractions — arpit_bhayani · 2026-10-05
- Indie dev tinyfool starts prototyping his next game, now stress-testing game logic engine — tinyfool · 2026-10-05
- Five questions to ask before letting an AI agent call a state-changing tool in production — ainexfinder · 2026-10-05
- Flowsint, an open-source graph-based OSINT investigation platform, hits 9.1k GitHub stars — tom_doerr · 2026-10-05
- AWS launches Well-Architected Agent that scans 65+ services and ranks risks by your business goals — DigitalColmer · 2026-10-05