KnowEvo: Knowledge Evolution for Protein Optimization

Published
Source
arXiv
Paper number
1454
Field
AI Agents
arXiv ID
2611.09013

Key points

  • The authors propose KnowEvo, which treats externalized knowledge itself as the optimization target, addressing the problem that acquired expertise stays embedded in model weights or scattered across iterative problem-solving processes.
  • Knowledge is represented as executable expertise blocks whose refinements are organized into strategy mutation trees, aligning the unit of execution with the unit of evidence.
  • The forward phase adaptively distributes evaluation budgets across strategy variants using a Thompson-style posterior allocation strategy.
  • In the backward phase, a code agent operates in an isolated sandbox to translate rollout evidence into localized program updates, and validated revisions are appended as child nodes.
  • On the Rosetta stability task, KnowEvo improved pass@1 from 42.4% to 50.5%, and on the SaProt solubility task it improved pass@1 from 31.6% to 51.5%.
  • It outperformed LLM-guided evolution baselines such as GEPA and AdaEvolve across all six metrics on both tasks.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)