Self evolving agents improve themselves by updating models and tools together
Evo$^2$: Evolving the Evolver through Weight-Harness Co-Evolution
Computation and Language
Summary
Improving AI agents can involve changing their underlying models or the tools they use, but usually these happen separately. This paper introduces a method called Evo² that updates both the AI's model and its tools together in a coordinated way. The approach uses one policy that suggests and reviews changes, learning from both the edits made and their results. Their experiments show this method works better than previous ones on coding tasks and even helps when trying new tasks or different AI models.
What this means in practice
- •For software engineering teams: Improve code generation tools by automatically evolving both the underlying models and their control logic to enhance correctness without manual coding.
- •For ai platform developers: Boost AI agent performance on various tasks by co-evolving model weights and control strategies, enabling adaptable, self-improving systems.
Authors
Chejian Xu, Shujian Zhang, Wenxuan Zhou, John Lambert, Beck Chen, Bo Li, Andrew Hard, Rajiv Mathews
Abstract
Self-evolving agents are increasingly used to improve language model systems without human intervention through either weight updates or harness improvements. Existing approaches typically pursue these directions separately: some methods update model weights using self-generated experience, while others rewrite the harness that defines how an agent uses prompts, tools, context, and execution feedback. However, these approaches overlook the relationship between model weights and the agent harness. To connect these processes and ensure effective and smooth agent self-evolving, we propose Evo$^2$, a framework for weight-harness co-evolution. For harness updates, we design a unified dual-role pipeline that a single policy serves as both a Proposer, which writes harness edits, and a Reflector, which diagnoses their effects and guides revision. For weight updates, harness modifications and their execution outcomes guide the training of both the Proposer and the Reflector. We further develop EvoTIDE, a training pipeline that recovers usable trajectories through edit extraction and prefix continuation, then combines SFT with interleaved GRPO across the two roles. Extensive experiments across three coding benchmarks demonstrate that Evo$^2$ significantly outperforms existing self-evolution methods. It achieves 82.1% on Polyglot and 48.3% on SWE-bench Verified, compared with 62.6% and 41.0% for the strongest baseline, respectively. We also show that the evolved harnesses transfer to different tasks without further evolution and rank first in cross-benchmark evaluations. Our dual-role harness improvement framework is also able to extend to self-evolution with proprietary models, improving a GPT-5-mini agent's performance from 24.4% to 48.3%. These results demonstrate the applicability of the framework Evo$^2$ across domains and its broad transferability across models and tasks.