Agentic Uncertainty Reveals Agentic Overconfidence
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914311359692800 |
|---|---|
| author | Kaddour, Jean Patel, Srijan Dovonon, Gbètondji Richter, Leo Minervini, Pasquale Kusner, Matt J. |
| author_facet | Kaddour, Jean Patel, Srijan Dovonon, Gbètondji Richter, Leo Minervini, Pasquale Kusner, Matt J. |
| contents | Can AI agents predict whether they will succeed at a task? We study agentic uncertainty by eliciting success probability estimates before, during, and after task execution. All results exhibit agentic overconfidence: some agents that succeed only 22% of the time predict 77% success. Counterintuitively, pre-execution assessment with strictly less information tends to yield better discrimination than standard post-execution review, though differences are not always significant. Adversarial prompting reframing assessment as bug-finding achieves the best calibration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06948 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Agentic Uncertainty Reveals Agentic Overconfidence Kaddour, Jean Patel, Srijan Dovonon, Gbètondji Richter, Leo Minervini, Pasquale Kusner, Matt J. Artificial Intelligence Machine Learning Can AI agents predict whether they will succeed at a task? We study agentic uncertainty by eliciting success probability estimates before, during, and after task execution. All results exhibit agentic overconfidence: some agents that succeed only 22% of the time predict 77% success. Counterintuitively, pre-execution assessment with strictly less information tends to yield better discrimination than standard post-execution review, though differences are not always significant. Adversarial prompting reframing assessment as bug-finding achieves the best calibration. |
| title | Agentic Uncertainty Reveals Agentic Overconfidence |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.06948 |