Techniques

Self-improving agents

Technique · Agents · 2 items since Apr 2026

Agents that rewrite their own code, tools, or procedures from experience.

Related

Organizations
Fudan UniversityOpenAI
Techniques
Agent memory

Items

  1. May 27

    OpenAI builds self-improving tax agents with Codex

    Codex agents analyze their own failures, rewrite domain reasoning logic, and rerun validation suites in iterative cycles, reporting measurable accuracy gains on IRS-style tax calculations without manual intervention.

  2. Apr 18

    Fudan's GenericAgent

    A self-evolving agent that maximizes decision-relevant information within a sub-30K context using nine atomic tools, hierarchical on-demand memory, and verified trajectories crystallized into reusable SOPs and code, outperforming agents that consume 200K-1M tokens on task completion and web browsing.