今日速览
| 序号 | 标题 | 来源 | 日期 | 主题 | 推荐等级 |
|---|---|---|---|---|---|
| 1 | Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents | arXiv | 2026-09-10 | AI-Agent | 高 |
| 2 | From Intent to Execution Grant: An Execution-Boundary Conformance Profile for High-Risk AI Actions | arXiv | 2026-09-10 | AI-Agent | 高 |
重点论文与技术动态
1. Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents
- 来源：arXiv
- 日期：2026-09-10
- 作者/机构：Ruiqing Yue, Yu Cui, Zhuoyu Sun, Sicheng Pan, Xianhong Xue, Tingyu Li
- 主题标签：
AI-Agent,arXiv - 推荐等级：高
- 分类：cs.SE, cs.AI
一句话结论
Ecdysis框架通过系统性失败诊断区分模型特定适应与框架级修复，显著提升LLM代理运行时框架训练效率与推理准确率。
核心内容
- 现有方法依赖迭代搜索反复执行代理和修改代码，导致高时间开销、过拟合特定任务，降低对未见任务的泛化能力。
- Ecdysis识别跨任务失败模式，区分模型缺陷与框架系统缺陷，避免不必要的模型特定适应。
- 采用批量级失败聚合与失败驱动协作优化，结合跨实例分析与多角色诊断，实现更高效的框架进化。
方法与数据
- 方法包括batch-level cross-instance failure aggregation和Failure-Driven Collaborative Refinement。
- 摘要未明确实验数据集细节。
价值判断
- 值得关注：实验显示训练速度提升1.84倍，推理准确率提高18.56%。
- 可复用点：失败诊断机制可推广至其他LLM代理优化任务。
- 局限/待核查：摘要未明确提及局限。
摘要
Self-evolving runtime harnesses can substantially improve the capabilities of large language model (LLM) agents and provide a promising paradigm for optimizing agent execution. Existing harness evolution methods typically rely on iterative search, repeatedly evaluating and revising candidate harnesses based on execution feedback from task instances. While this paradigm enables continuous harness optimization, it incurs substantial time overhead due to repeated agent executions and code modifications, and may overfit to observed tasks and specific failure patterns, resulting in degraded generalization to unseen tasks. We identify the lack of principled failure diagnosis as a key bottleneck in harness evolution: an observed failure can reflect either model-specific deficiencies or systematic harness deficiencies, and directly optimizing against individual failures can lead to unnecessary model-specific accommodation. We therefore propose Ecdysis, an efficient and effective framework that distinguishes model-specific accommodation from harness-level repair and biases adaptation toward systematic harness deficiencies by identifying recurring cross-task failure patterns. Ecdysis adopts a batch-level cross-instance failure aggregation paradigm to jointly analyze failure evidence from multiple task instances and further introduces Failure-Driven Collaborative Refinement to diagnose failure causes and iteratively refine harness modification specifications. By combining cross-instance failure analysis with multi-role diagnosis, Ecdysis enables more effective harness evolution with lower training time. Experiments show that Ecdysis achieves up to a 1.84x speedup in harness training compared with existing harness evolution methods, while improving the reasoning accuracy of the resulting harnesses by 18.56%.2. From Intent to Execution Grant: An Execution-Boundary Conformance Profile for High-Risk AI Actions
- 来源：arXiv
- 日期：2026-09-10
- 作者/机构：Mengting Wu, Lin Wang, Yong Zhang, Jiang Deng
- 主题标签：
AI-Agent,arXiv - 推荐等级：高
- 分类：cs.CR
一句话结论
EBL-Core提出一种执行边界符合性配置文件，通过执行释放合同(ERC)实现高风险AI动作在明确条件下的执行授权决策，确保从候选动作到执行权限的语义一致性。
核心内容
- EBL-Core通过ERC绑定结构化意图对象、根策略、证据义务及上下文，定义从AI候选动作到执行授权的最终过渡语义合同。
- 它指定行动绑定、策略非削弱、证据处理、确定性裁决及授权生命周期行为，验证的ALLOW ERC支持独立执行授权。
- 测试验证34个静态向量和15个生命周期检查匹配预期，100次试验中并发赎回尝试成功率为100%（32次尝试成功1次）。
方法与数据
- 方法：基于EBL-Core配置文件和参考实现，包括模式、裁决、语义重播及线性化内存授权存储。
- 数据：34静态向量与15生命周期检查匹配结果；100次试验中32次并发赎回成功一次。
价值判断
- 值得关注：解决AI动作执行授权的语义合同缺失问题，提升高风险操作（如金融转移）的安全性。
- 可复用点：EBL-Core配置文件及参考实现（如语义重播和线性化存储）可直接复用于类似AI系统。
- 局限/待核查：结果仅证明指定子集的可执行性，不涉及人类意图正确性、证据真实性、完整中介或生产就绪性。