Completion $\neq$ Collaboration: Scaling Collaborative Effort with Agents
This addresses the need for more effective collaborative agents in real-world applications, though it is incremental as it builds on existing agent design by shifting evaluation focus.
The paper tackles the problem that current agent evaluations focus on one-shot task completion, ignoring the iterative and collaborative nature of real-world problems, and proposes a framework called collaborative effort scaling to assess how agents enhance human effort, showing that state-of-the-art agents often underperform in multi-turn scenarios.
Current evaluations of agents remain centered around one-shot task completion, failing to account for the inherently iterative and collaborative nature of many real-world problems, where human goals are often underspecified and evolve. We argue for a shift from building and assessing task completion agents to developing collaborative agents, assessed not only by the quality of their final outputs but by how well they engage with and enhance human effort throughout the problem-solving process. To support this shift, we introduce collaborative effort scaling, a framework that captures how an agent's utility grows with increasing user involvement. Through case studies and simulated evaluations, we show that state-of-the-art agents often underperform in multi-turn, real-world scenarios, revealing a missing ingredient in agent design: the ability to sustain engagement and scaffold user understanding. Collaborative effort scaling offers a lens for diagnosing agent behavior and guiding development toward more effective interactions.