- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes OrbitPO, a framework for improving the robustness of tool-using language agents to semantics-preserving interface transformations. It combines mass-preserving semantic alignment, orbit-relative credit assignment, and counterfactual complete-history replay to encourage cross-interface policy equivariance. Theoretical analysis establishes relevant properties under exact interface transformations, while extensive experiments across multiple benchmarks and model backbones demonstrate improvements in worst-view robustness over competitive baselines.
Critical strengths
- The mass-preserving alignment objective addresses a limitation of candidate-normalized consistency by retaining residual probability mass.
- The experiments results are comprehensive, which cover diverse benchmarks and model backbones. The improvements in worst-view robustness without additional inference calls are particularly encouraging.
- The paper is generally well written and easy to follow.
Critical weaknesses
- The method relies on exact, invertible, semantics-preserving mappings, whereas real-world API changes often involve semantic or behavioral modifications.
- OrbitPO incurs additional training overhead, and its performance falls slightly below LocalCanon-GRPO under approximately matched training FLOPs (53.8 vs. 54.6 WVA, Table 6).
Questions for authors
See Weaknesses