PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

Recursive self-improvement requires agents to turn accumulated experience into better future behavior. Personal AI agents offer a concrete setting for studying this capability because they retain preferences, task histories, tool routines, and learned skills across sessions. Yet whether retained experience actually improves them over time has not been systematically tested. We introduce PAST-Bench, a benchmark designed to isolate this question. Each agent runs through ordered sequences of fresh-session tasks under matched conditions that turn retained experience on and off. It spans 26 scenarios and 204 episodes across memory, procedural reuse, information gathering, and update. We report both later-task gains and whether those gains follow the intended save, retrieve, and update pathway. Across seven base models and four agent frameworks, improvement is real but uneven across capabilities. Agents with the same headline gain can differ markedly in whether that gain is supported by evidence of the intended pathway. Guided by these findings, we develop Hermes+, which extends Hermes with five targeted interventions across stages of the agent loop.

Introduction. Recursive self-improvement (RSI) concerns the ability of an AI system to use experience generated through its own operation to improve its future capabilities (Lee et al., 2026; Qu et al., 2024; Ren et al., 2026; Wang et al., 2026; Yin et al., 2025). While stronger forms of RSI may eventually involve modifying model parameters, learning algorithms, or agent architectures, a more immediate and operational layer is already emerging in personal AI agents (Gao et al., 2025; Sarukkai et al., 2025; Wang et al., 2026). Personal AI agents now persist across sessions. They read messages, operate over user workspaces, call tools, and accumulate files, memories, skills, and session histories over days and months (Nous Research, 2026; OpenClaw, 2026).

Discussion / Conclusion. We introduced PAST-Bench, a performance-attribution benchmark that pairs persistence-on/off evaluations within task families and reports mechanism evidence alongside task scores, separating base-model, runtime, and retained-experience contributions to later-task performance. Experiments across seven models and four frameworks show that self-evolution is capability-specific and that similar persistence gaps can hide different persistence paths. Under MiniMax-M2.7, Hermes+ raises the reported mean Overall Δ from +0.13 to +0.15 and Mech from 0.64 to 0.73, with its clearest gain on Update; the +0.02 Overall difference is smaller than run-to-run variation. The effect is not uniform across capabilities or base models, so we treat Hermes+ as a diagnostic scaffold rather than a universal improvement.