Agent exploration produces valuable procedural knowledge, yet much of this experience remains confined to transient execution traces and is not systematically reused. We introduce Evolver, an experience-driven framework that transforms agent exploration into persistent, reusable capabilities without updating foundation model parameters. Built around structured Gene assets, Evolver integrates experience acquisition, retrieval, and feedback-guided evolution to support experience-conditioned execution across existing agent harnesses. We evaluate Evolver using Claude Code and Codex, two foundation model configurations, and four benchmarks: Terminal-Bench 2.1, SWE-bench Multilingual, SWE-rebench, and GAIA. On a selected diagnostic set of 320 paired executions, Evolver improves task success from 83.13% to 87.50% (+4.38 percentage points) while reducing recorded task-execution token consumption by 24.24%. Furthermore, among 265 pairs successful under both conditions, token consumption decreases by 17.57%, demonstrating efficiency benefits even when task success is preserved. These findings suggest that persistent procedural experience can improve both task effectiveness and execution efficiency, providing a practical foundation for transforming agent exploration into evolving capabilities.
Figures & tables
Figure 1: Overview of Evolver and its Exploration-to-Evolution framework, illustrating experience acquisition, persistent strategy assets, experience-conditioned execution, feedback-supported evolution, EvoMap connectivity, and operational trust boundaries.
Figure 2: Overall task success with and without Evolver across two agent harnesses and the combined evaluation set.
Figure 3: Task success across agent harnesses, foundation models, and benchmarks, with 20 paired evaluations per configuration.
Figure 4: Recorded task-execution token usage with and without Evolver across all selected pairs (A) and pairs successful under both conditions (B).
Figure 5: Representative cases showing preserved task success with reduced token consumption and model invocations.