Eureka：面向科学发现的任务条件元智能体编排框架
Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery
另 3 家 · 查看机构详情
- ManXis（万熙科技（ManXis））
- Guangdong University of Technology（广东工业大学）
- South China Normal University（华南师范大学）
- Shanghai Jiao Tong University（上海交通大学）
- Duke University（杜克大学）
- Hokkaido University（北海道大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究提出Eureka任务条件元智能体架构，通过动态编排完成科学发现任务，在递归任务、增量处理等实验中表现优异，还实现了数学领域的理论进展，证明科学智能体能力依赖匹配任务认知结构的架构。
中文摘要 AI 辅助
我们提出了Eureka，一种任务条件元智能体架构，它能将长程任务编译为具有显式接受语义的动态义务图。执行过程中，Eureka通过后退时域规划、架构提升和最小充分编译，形成具有专用状态、记忆、算子、工具、验证器和局部拓扑的宏智能体。当瓶颈反复出现时，成本效益门控演化会在约束下更新局部架构。理论上，我们建立了关于遗憾、规划失效、摊销、子树接口、可串行性和验证的结果。实验中，Eureka完成了170/170个递归任务，生成了3948份证书且无错误接受；主动上下文将中位数输入从9490个令牌压缩至4005个；在12000个任务中，增量处理避免了65.38%的重新计算；16000次并发执行保持一致的可串行性。同一元智能体可实例化为理论发现智能体和数学/猜想智能体，前者在量子过程和时空理论中取得结构性结果，后者识别出黎曼假设研究中的瓶颈，并将铃木局部Weil二次型的正性证书推进至0 < a ≤ 69/200 = 0.345，达到(log 2)/2的约99.55%。这些结果表明，科学智能体的能力不仅取决于基础模型，还取决于是否能形成匹配任务认知结构的架构。
英文摘要
We present Eureka, a task-conditioned Meta-Agent architecture that compiles long-horizon tasks into dynamic obligation graphs with explicit acceptance semantics. During execution, Eureka forms Macro-Agents with specialized state, memory, operators, tools, verifiers, and local topology via receding-horizon planning, architecture promotion, and minimal-sufficient compilation. When bottlenecks recur, cost-benefit-gated evolution updates the local architecture under constraints. Theoretically, we establish results on regret, planning invalidation, amortization, subtree interfaces, serializability, and verification. Experimentally, Eureka completes 170/170 recursive tasks and generates 3,948 certificates with no false acceptances. Active context compresses median input from 9,490 to 4,005 tokens; incremental processing avoids 65.38% recomputation across 12,000 tasks; 16,000 concurrent executions serialize consistently. The same Meta-Agent instantiates a Theory-Discovery Agent and a Math/Conjecture Agent. The former yields structural results in quantum-process and spacetime theory. The latter identifies bottlenecks in Riemann Hypothesis research and advances a positivity certificate for Suzuki's localized Weil quadratic form to 0 < a <= 69/200 = 0.345, reaching ~99.55% of (log 2)/2. These results suggest that scientific-agent capability depends not only on the base model but on whether an architecture can be formed to match the task's cognitive structure.
