- Rating
- 3(+1)
- Confidence
- 3(+1)
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies continual learning through prompt optimization with frozen language models. It proposes Evolving Functional Repertoires (EFRE), which replaces a single prompt with an evolving repertoire of prompt-based functions. Historical consistency checks guide functional refinement, reuse, and emergence, while a selector routes inputs to suitable functions. Experiments on the ToolUse → FinQA → SciKE-Bio sequence report improved adaptation and retention over the evaluated prompt-optimization baselines, with additional gains in single-task optimization and minimal-agent settings.
Critical strengths
- By combining historical consistency checks with the maintenance of prompt-based functions, the paper provides a concrete approach to continual adaptation without updating model parameters.
- EFRE† largely retains its FinQA performance after SciKE-Bio adaptation, with substantially less forgetting than GEPA; default EFRE also improves final performance over the prompt-optimization baselines. Table 2 compares history retention settings, historical consistency tolerances, and function-selection strategies, while Figure 2 and Table 1 show cross-task reuse patterns, helping characterize the system’s behavior.
Critical weaknesses
- Under Equation 7 and Appendix Algorithm 2, ε=1 disables effective historical constraints and, with single-function initialization, dynamic expansion. Always selecting the first function likewise does not enforce single-function training. Neither the main text nor the appendix compares against a single function with matched historical checks, prompt snapshots using the same selector, or a fixed-size repertoire. The incremental benefit of conflict-driven expansion therefore remains unclear.
- The main cross-task experiment uses only ToolUse → FinQA → SciKE-Bio, without alternative orders, longer task streams, or task revisits. Appendix D.2 acknowledges incomplete historical coverage and potentially accumulating performance losses, but these limitations lack corresponding long-term evaluation. Aggregate rewards in the agent experiments also do not directly establish retention of earlier capabilities.
Questions for authors
Please refer to the two points in Critical Weaknesses. I will raise my score if the authors adequately address these concerns through additional experiments and clarification.