Bifrost: 通过引导战略轨迹填补上下文差距以实现自我改进智能体
Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents
AI总结：
Bifrost通过引导轨迹适应填补上下文差距，提升智能体在上下文转换中的自我改进能力。
摘要：
自主智能体通过反思和迭代改进来实现自我改进，通过重用成功的任务轨迹作为上下文示例来辅助后续推理。然而，任务切换往往引入上下文不匹配。现有方法要么丢弃轨迹，要么使用启发式方法操纵它们，导致非可忽略的微调成本或不可保证的性能。为填补这一差距，我们揭示了上下文轨迹相关性，其中上下文的移动高度平行于轨迹的移动。基于这一发现，我们提出了BrIdge contextual gap FoR imprOvised trajectory STeering（Bifrost），一种无需训练的方法，利用上下文差异精确引导已解决轨迹向目标任务的适应，缓解由上下文转换引起的不匹配。我们的轨迹适应在表示层面通过智能体隐藏状态进行，确保轨迹转换准确对齐于目标上下文在共享空间中。在多样化的基准测试中，Bifrost始终优于现有轨迹重用和微调自我改进方法，证明了智能体可以有效利用过去经验，即使存在显著的上下文转换。
英文摘要：
Autonomous agents excel in self-improvement through reflection and iterative refinement, which reuse successful task trajectories as in-context examples to assist subsequent reasoning. However, shifting across tasks often introduces a context mismatch. Hence, existing approaches either discard the trajectories or manipulate them using heuristics, leading to a non-negligible fine-tuning cost or unguaranteed performance. To bridge this gap, we reveal a context-trajectory correlation, where shifts of context are highly parallel with shifts of trajectory. Based on this finding, we propose BrIdge contextual gap FoR imprOvised trajectory STeering (Bifrost), a training-free method that leverages context differences to precisely guide the adaptation of previously solved trajectories towards the target task, mitigating the misalignment caused by context shifts. Our trajectory adaptation is conducted at the representation level using agent hidden states, ensuring trajectory transformation accurately aligns with the target context in a shared space. Across diverse benchmarks, Bifrost consistently outperforms existing trajectory reuse and finetuned self-improvement methods, demonstrating that agents can effectively leverage past experiences despite substantial context shifts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
