---
title: "Eureka：面向科学发现的任务条件元智能体编排架构"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.19047v1"
permalink: "https://feed.astralor.com/items/itm_abf86bf10c3e62d4613b0219"
published: "2026-08-19T15:40:21.000Z"
score: 78
channel: "tech"
tags: ["Eureka","元智能体","宏智能体","智能体编排","科学发现"]
---

# Eureka：面向科学发现的任务条件元智能体编排架构

## AI 点评

> 值得关注的是，Eureka把智能体的能力从“模型多大”转向“架构怎么长”，这种视角对当前Agent研究很有冲击力。如果你在做科学发现自动化或长程任务智能体，这套以义务图和演化机制为核心的编排方式值得细读。

## 速览

Eureka是一种任务条件元智能体架构，将长时程任务编译为具有显式接受语义的动态义务图，并通过滚动规划、架构提升与最小充分编译形成专用宏智能体。实验显示，Eureka完成170个递归任务并生成3948个无假接受证书，主动上下文将输入压缩约58%，增量处理避免65.38%重计算。同一架构实例化的理论发现智能体与数学猜想智能体在量子过程、时空理论及黎曼猜想研究中取得进展，表明科学智能体能力关键取决于架构与任务认知结构的匹配。

## 关键点

- Eureka引入动态义务图与显式接受语义，支持长时程任务的可靠分解与验证。
- 在12000个任务中避免65.38%重计算，16000个并发执行保持串行一致性。
- 同一元智能体实例化理论发现与数学猜想两个智能体，在量子过程、时空理论及黎曼猜想研究中取得具体成果。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_abf86bf10c3e62d4613b0219