让智能体在不改模型的情况下持续进化，通过动态调整提示、记忆等外部组件。
Harness Continual Learning: Continual Adaptation Beyond Model Parameters
- 以冻结的模型为基础，通过更新提示、记忆等外部组件实现持续学习。
- 在文本推理等任务中相对基线提升超10%，并能恢复失败行为。
- 适合需要长期演化但不能重训模型的场景，如智能助手、机器人系统。
持续学习长期聚焦于模型参数的更新。现代智能体还可通过提示、记忆、工具、技能和路由规则等‘组合’进行适应。这些内容共同决定后续执行，即使模型冻结，组合更新也可能破坏已有可靠行为。这引出新问题：如何在不修改模型的前提下持续优化外部状态，同时保留早期能力？我们提出Harness Continual Learning（HCL），一种以冻结基础模型为核心、让‘组合’持续演化的新型持续学习范式，并将由此导致的早期行为退化定义为‘组合级遗忘’。我们构建了四项面向执行的组件：任务接口、经验记忆、能力图谱与自适应路由器。引入受保护的组合演化机制，将候选更新生成与状态提交分离。持续优化器根据执行后反馈生成候选组合，持续评估器在确认当前改进、历史保留与有效性后才提交。在文本推理、多模态感知与开放世界交互任务上，实验验证了能力累积与故障恢复能力，多个场景相对基线提升超10%。组件消融分析揭示各组件贡献，受控保留测试量化了组合级遗忘，并表明稳定性与可塑性权衡可显式调节。
原文摘要 · Abstract (English)
Continual learning has largely been model-centric, treating model parameters as the state that changes with sequential experience. Modern agents can also adapt through a harness of prompts, memories, tools, skills, and routing rules. Because these contents jointly shape later execution, a harness update can disrupt previously reliable behavior even when the model is frozen. This raises a new question: how can an agent continually improve its state outside the model while retaining behavior acquired earlier? We formulate Harness Continual Learning (HCL), a new continual learning paradigm in which the harness evolves around a frozen foundation model, and define the resulting loss of earlier behavior as harness-level forgetting. We instantiate HCL with four execution-facing components: the Task Interface, Experience Memory, Capability Map, and Adaptive Router. We further introduce guarded harness evolution to separate update generation from state commitment. A Continual Optimizer proposes candidate harnesses from post-execution feedback, and a Continual Evaluator commits the resulting candidate harness only after checking current improvement, historical retention, and validity. Experiments on textual reasoning, multimodal perception, and open-world interaction demonstrate capability accumulation and failure recovery, with relative gains exceeding 10% over corresponding baselines in multiple settings. Component ablations assess the contribution of each harness component, while controlled retention sweeps reveal measurable harness-level forgetting and show that the stability--plasticity trade-off can be explicitly adjusted.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。