Skip to content
Google's Self-Improvement Memory Enables Agents to Evolve Across Models Continuously

Google's Self-Improvement Memory Enables Agents to Evolve Across Models Continuously

Google researchers introduce Self-Improvement Memory (SIM), a mechanism that records optimization rationales and outcomes for agent harnesses, enabling continual recursive self-improvement across model and task changes, with experiments showing SIM outperforms framework-only transfer in cross-dataset and cross-model settings.

SmartApe AI
SmartApe AI
SmartApe AI

Background and Motivation

Google Cloud AI, Google DeepMind, and Pennsylvania State University researchers published the paper Self-Improvement Memory Enables Continual Recursive Self-Improvement (November 13, 2024). The work addresses a practical problem: when an agent's harness (the framework managing context, tools, and execution flow) is optimized for one model (e.g., Claude Opus 5.5), directly transferring that harness to a different model (e.g., Gemini 3.8 Flash) often degrades performance below the new model's original harness. The optimization history — why a rule was added, what failure it fixed, which alternatives were tried — is lost, making further adaptation difficult.

Self-Improvement Memory (SIM) and Continual Recursive Self-Improvement (CRSI)

SIM is a persistent, updatable record attached to the harness. Each entry is organized by recurring root-cause categories and stores:

The code change and its rationale

The task the change aimed to fix

Expected outcome (recorded before evaluation) and actual measured outcome

Domain, benchmark, model, and iteration identifiers

During each optimization round, the proposer and selector components read the full SIM. Proposals must link to an existing root cause or introduce a new one. Only accepted modifications and their measured results are written back; rejected proposals leave SIM unchanged. When the task or model changes, both the harness and its SIM are carried forward, allowing the optimizer to retain, adjust, replace, or delete mechanisms while preserving historical context. This loop is termed Continual Recursive Self-Improvement (CRSI).

Experimental Setup

Experiments covered four domains: programming, text classification, office tasks, and engineering design. Two transfer scenarios were tested:

Cross-dataset (same model): Six setups, each optimized for 10 iterations with 5 candidates per iteration.

Cross-model: Harness first optimized around Claude Opus 5.5, then transferred to Gemini 3.8 Flash for continued optimization on the same benchmarks. Proposer and selector used Gemini 3.8 Flash in both phases.

Four baselines compared: from-scratch optimization, framework-only inheritance, framework + root-cause inheritance, and framework + full SIM. All shared the same starting harness, target model, iteration budget, and candidate count.

Results

Cross-Dataset Transfer

Full SIM achieved the highest final score in all six setups, leading framework-only by 2.43–4.35 points. However, retaining only root causes (without full history) sometimes hurt: in the AHE programming setup, root-cause-only scored 18.79 vs. framework-only's 20.61.

Cross-Model Transfer (Claude → Gemini)

The transferred harness initially underperformed Gemini's original harness in all four domains, confirming that model-specific adaptations do not transfer automatically. After continued optimization:

Office tasks showed the largest gap: framework-only reached 73.42, root-cause-only 79.22, full SIM 84.75 (starting from 68.41).

To test reproducibility, 10 independent source-phase optimizations on Terminus-2 were each split into SIM and no-SIM branches on TB4. SIM won 9 of 10 pairs, average advantage 2.36 points (95% CI 1.05–3.68, paired p = 0.003). One pair favored no-SIM by 0.61 points.

Sequential Model Generations (Gemini 3.5 Flash → 3.8 Flash → 4 Argon)

CRSI led independent optimization by 3.5 points on 3.5 Flash and 1.6 points on 3.8 Flash, but trailed by 0.8 points on 4 Argon, indicating that accumulated experience can sometimes become a liability.

Shared Framework Across Multiple Models

On text classification, a single harness optimized using aggregated feedback from Grok, Opus, and Gemini scored 75.24 on average, versus 75.20 for per-model optimized harnesses and 73.28 for the original shared harness.

Optimizer Model Sensitivity

Swapping the source-phase proposer/selector model from Gemini to Opus improved independent evaluation scores by 1.06 and 0.05 points on two programming harnesses, showing that optimizer capability matters independently of SIM.

Limitations and Open Questions

The authors acknowledge that historical experience is not universally beneficial; cases where inheritance underperformed from-scratch optimization appeared. Identifying outdated experience and controlling memory growth require longer-horizon experiments. The central question remains: as AI participates in its own improvement, can each trial leave more usable experience for the next?

SIM architecture diagram
SIM architecture diagram
CRSI loop illustration
CRSI loop illustration
First author Xin Yu background
First author Xin Yu background
SIM entry structure
SIM entry structure
Cross-dataset results chart
Cross-dataset results chart
Cross-model transfer results
Cross-model transfer results
Paired reproducibility experiment
Paired reproducibility experiment
Sequential model generations results
Sequential model generations results
Shared framework across models results
Shared framework across models results
Original Source

Signed-in readers can open the original source through BestHub's protected redirect.

Sign in to view source
Republication Notice

This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactadmin@besthub.devand we will review it promptly.

AI agentsMemory MechanismsGoogle DeepMindCross-Model TransferAgent Harness OptimizationContinual Recursive Self-ImprovementSelf-Improvement Memory
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.