research
The Explanation Had to Follow the Agent’s Footsteps
A post-hoc framework turns observable execution traces into reports designed to flag unsupported claims, unjustified actions and evidence gaps.
Summary
A post-hoc framework turns observable execution traces into reports designed to flag unsupported claims, unjustified actions and evidence gaps.
Traditional explainability methods focus on model outputs or feature influence, while tool-using agents leave a sequence of observable decisions. This framework structures a long execution trace, then produces a natural-language explanation grounded in that record. Human and automated evaluations across multiple benchmarks and agent architectures report better trace faithfulness and stronger identification of unsupported claims, unjustified actions and evidence gaps than naive language-model explanations. Because the method sees behavior rather than hidden reasoning, it can audit what happened without claiming access to an agent’s private internal state.
Why it matters
A post-hoc framework turns observable execution traces into reports designed to flag unsupported claims, unjustified actions and evidence gaps.
Limits and context
No additional limitation was separately recorded.
Key claims
A post-hoc framework turns observable execution traces into reports designed to flag unsupported claims, unjustified actions and evidence gaps.
Evidence: source-2026-09-09-005
Sources
- arXiv preprint 2609.06063arXiv · primary research
Corrections
No corrections have been recorded for this story.