HMA 多智能体会话交替框架在 MLE-bench 取得 78.2% 奖牌率
Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits
两个智能体轮流干、每次重置上下文，Kaggle 奖牌率干到 78.2%，还只用基线四分之一时间，做 MLE 智能体的可以细看。
论文提出 HMA 框架，用两个智能体在共享工作区上交替工作，每次会话最多 k 个实验并重置上下文，无需任务专用 harness。作者将这种交替建模为 CR-SMDP，推导出会话上限保持优势的条件。在 MLE-bench 的 75 个 Kaggle 任务上，HMA 的 any-medal 率达 78.2%，比最强开源基线高 8.0 个百分点，且只用其四分之一时间预算。跨 5 组异构智能体对的 6 种配置平均提升 6.4 个百分点，另在内核优化案例中达到 878 cycles，距社区榜单第一仅 1.6%。
Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits
Existing LLM-based agent approaches for long-horizon machine learning engineering (MLE) often use context engineering, implemented through custom harnesses that manage tools, skills, and accumulated experience. However, we find that as single-session execution lengthens, the agent's reasoning intensity declines alongside slowing progress, summarized as long-horizon deceleration, and the benefits of these custom harnesses vanish as the underlying model improves, summarized as harness staleness. These findings suggest that their benefits may not persist across versions, which motivates a workflow-level approach in which agents build on one another's work across sessions. We model these alternating agent sessions as a context-reset semi-Markov decision process (CR-SMDP) and establish sufficient conditions for alternation to exceed single-agent reference limits, derive an explicit experiment-budget bound, and characterize when session caps preserve this advantage. Guided by this analysis, we introduce Humanize MLE Agents (HMA), which alternates two agents on a shared workspace, limits each session to at most k experiments and resets the context between sessions, without additional task-specific harness or prior knowledge supplements. Across 75 Kaggle tasks in MLE-bench, HMA reaches a state-of-the-art any-medal rate of 78.2%, exceeding the strongest open-source baseline by 8.0 points with a quarter of its time budget. Moreover, among six configurations spanning five heterogeneous agent pairs, HMA improves any-medal rate over the constituent baselines by 6.4 points on average, demonstrating cross-pair generality. A supplementary case on kernel optimization reaches 878 cycles, within 1.6% of the community leaderboard leader, demonstrating applicability beyond MLE.
