evidence-management

LongHarness 是一个模型无关的智能体框架，通过「证据-结论协同演化」和「证据生命周期管理」机制，在超过 1 亿 token 的文档语料上进行有状态的证据管理，显著提升了长上下文推理任务的准确率（如 OfficeQA Pro V1 上从 15.8% 提升至 60.2%），并超越了 Claude Code 和 Codex 等现有智能体框架。

The AQuA v2 preprint introduces a memory system for research agents that uses persistent evidence from accepted and rejected experiments to guide future proposals, emphasizing the importance of evidence lifecycle management.

Axon CEO Rick Smith reports a 700%+ year-over-year increase in revenue from AI policing tools, as the company pivots from Tasers to AI software for law enforcement.