DUET: Co-Evolving Solver and Grader Agents

2026-10-02

AI Summary

This study addresses the challenges of evaluator failure and the tight coupling between evaluation and optimization in agent evolution by proposing the DUET framework. Its core innovation lies in reconceptualizing evaluation from a static feedback source into a co-optimized objective that adaptively evolves alongside the solver. Through an iterative mechanism encompassing task selection, execution, and evaluation, DUET alternately updates the solver and the scorer to achieve their co-evolution. Experimental results demonstrate that DUET significantly enhances the performance of both components across four benchmarks, comprehensively outperforming baseline methods that rely on fixed scorers.

Abstract

Agentic workflows are increasingly used across domains such as technology, finance, and enterprise operations. As these agents become more widely deployed, continually improving them becomes increasingly important. This raises an immediate challenge: How should the agent evolve? This evolution requires effective evaluation that can assess outcomes and provide useful feedback for optimization. As the agent evolves, its behaviors and failure modes may also change, making a fixed evaluator increasingly inadequate. Another fundamental question: How should we evaluate an evolving agent? These two challenges are inherently coupled; changes in agent behavior can expose limitations of the current evaluator, while a stronger evaluator provides more informative feedback for improving the agent. Motivated by this interaction, we introduce DUET, a framework that jointly optimizes a solver agent and a grader agent to improve both. DUET iteratively selects training tasks, executes them with the solver, evaluates the resulting outcomes with the grader, and uses a tool-using update module to revise the solver and the grader, alternating between the two across rounds. By updating the grader within the optimization loop, DUET turns evaluation from a fixed source of feedback into a first-class optimization objective that adapts alongside the solver. Experiments across four agent benchmarks show that DUET improves both solver and grader performance and consistently outperforms baselines that optimize the solver with a fixed grader.

Problem

• Agentic workflows
• Agent evolution
• Agent evaluation
• Co-optimization
• Solver and grader

Innovation

• Co-evolving agents
• Solver-grader optimization
• Agentic workflows
• Adaptive evaluation
• Joint optimization