AI Paper Atlas

Research map / Large language models / Agents, code and math

KnowEvo: Knowledge Evolution for Protein Optimization

Zijie Xing, Xingyue Liu, Runze Wang, Luoming Hu, Yanming Shen

NeurIPS 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes KnowEvo, a framework that makes knowledge for LLM-driven protein optimization explicit, persistent, and reusable rather than implicit in weights or transient solution histories.

Problem

LLMs for scientific discovery such as protein optimization lack a mechanism for persistent, reusable knowledge accumulation; existing methods keep knowledge implicit in model weights or scattered across transient solution histories.

Approach

Makes accumulated optimization knowledge an explicit, persistent artifact that evolves across iterations and can be reused, instead of relying on parameter updates or trajectory refinement. Only the abstract was available, so finer mechanism details are unknown.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Evolve executable expertise blocks with KnowEvoRoot seed blocks · Rosetta stabilitypass@1: 42.4 -> 50.5Improved
Evolve executable expertise blocks with KnowEvoRoot seed blocks · SaProt solubilitypass@1: 31.6 -> 51.5Improved
Replace Thompson-style allocation with uniform random node sampling (ablation)KnowEvo · SaProt solubilityMRR: 67.8 -> 65.4Hurt
Replace sandbox agentic revision with single-step LLM revision (ablation)KnowEvo · SaProt solubilityMRR: 67.8 -> 64.2Hurt
Replace mutation tree with chain-only growth (ablation)KnowEvo · SaProt solubilitypass@3: 83.2 -> 54.1Hurt
Give the same sandboxed code agent to AdaEvolveAdaEvolve · SaProt solubilitypass@1: 49.0 -> 42.3Hurt
Start from cold-start random roots instead of human-written (ablation)KnowEvo · SaProt solubilitypass@1: 51.5 -> 46.4No clear effect
Use warm-start roots (ablation)KnowEvo · SaProt solubilitypass@1: 51.5 -> 54.6No clear effect
Re-score Rosetta-evolved strategies with ThermoMPNNKnowEvo · Stability cross-predictorpass@1: 9.1 -> 15.7Improved
Increase accepted revisions from 10 to 100 (ablation)KnowEvo · SaProt solubilitypass@3: 59.5 -> 74.2Improved
Allow more agent-work budget per revision (ablation)KnowEvo · SaProt solubilityendpoint gainImproved
Use DeepSeek instead of MiniMax as revision backbone (ablation)KnowEvo · SaProt solubilityendpoint performanceImproved

Limitations

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy