Abstract
Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results. Current evaluation metrics reduce such a trajectory to a binary success flag or compare it against a reference by exact matching. A success flag cannot distinguish a sound solution from one that succeeds by luck, and says nothing about why a failed run went wrong. Exact matching penalizes plans that are valid but reordered or decomposed differently from the reference.
We reframe trajectory evaluation as a distance between the agent's execution graph and a set of valid solution graphs, and instantiate it via an unbalanced fused Gromov-Wasserstein transport problem over attributed dependency graphs. The resulting score, termed \otap{} (Optimal Transport for Agentic Planning), is a pseudo-metric that is provably invariant to dependency-preserving reorderings and has bounded sensitivity to redundant steps. Its unbalanced marginals handle missing or hallucinated steps without forcing a match, and its soft coupling accommodates variation in plan granularity.
On controlled perturbations and three public benchmarks, \otap{} separates valid from invalid trajectories in a regime where semantics-only metrics score below chance. Its accuracy is highest when the dependency graph is recovered exactly, and drops only when the graph is inferred heuristically from free-text traces.
Blogger's Review: This research provides a fresh perspective on trajectory evaluation, significantly enhancing accuracy and reliability through the introduction of structure-aware optimal transport methods. The innovative methodology is noteworthy, especially for its flexibility in handling complex dependencies, which could lead to performance optimization in future intelligent agents.