EvoX improves success for multi-model AI agent tasks by 3 points
EvoX: Rethinking the Agent Harness as a Runtime Policy
Artificial IntelligenceSoftware Engineering
Summary
Sometimes AI agents that use language models to interact with tools make good decisions but mess up when actually doing tasks. The authors present EvoX, a system that carefully manages how these AI agents act and follow through on tasks to improve success rates. They tested EvoX on many tasks and models, and it performed better than other similar systems. This shows that controlling how agents operate is important to make AI models work well in real tasks.
What this means in practice
- •For software engineers: Build AI agents that reliably use multiple language models and tools to complete complex tasks with fewer errors.
- •For cloud platform operators: Deploy multi-model AI runtimes that improve task success rates across different AI providers to support diverse user needs.
- •For customer support automation teams: Enhance chatbot workflows by reducing interrupted tool calls and mismatches, achieving smoother automated task completion.$Commercial implications: Makes it possible to sell more effective AI support systems that handle varied tasks with fewer failures.
Authors
Haoyang Zhang, Qumeng Sun, Xiao Zhang, Xiang Liu, Zhidong Fan, Junjie Wang
Abstract
Large language model (LLM) agents increasingly interact with tools and environments, yet plausible model decisions do not always translate into successful execution due to tool-call mismatches, interrupted workflows, and unsupported completion claims. We present EvoX, a Rust-based, multi-model agent runtime guided by The Second Policy, which views the harness as an Operational Policy complementing the foundation model's Semantic Policy. EvoX combines model-facing guidance with deterministic runtime control through three complementary mechanisms: Action Realization, Execution Continuity, and Outcome Grounding. To evaluate harnesses without suppressing their native behaviors, we introduce Contrast, a controlled and auditable framework integrating explicit fairness constraints, provider-bound request verification, and evidence-based adjudication. Across five benchmarks, six foundation models, and six agent harnesses, EvoX achieves the highest numerical success rate of 56.2% over 691 common task--model pairs, exceeding the average of the other five harnesses by approximately 3.0 percentage points. Its larger advantages on GLM-5.3 (+10.7 points) and Kimi K3 (+7.9 points) highlight the model-dependent effectiveness of harness design and the potential for cross-provider adaptability. Achieved without memory, evolution, or extensions, these results establish EvoX as a competitive multi-model agent runtime and underscore the importance of harness-level operational control in realizing foundation-model capabilities.