CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal how a task behaves relative to a given solver setting. In this paper, we present CalibForge, an autonomous terminal-task synthesis system that uses verified solver behavior to revise candidate tasks through adversarial solver calibration. Multi-solver calibration targets disagreement within a heterogeneous solver pool, whereas contrastive solver calibration targets a designated strong-pass/weak-fail relation; both operationalize a solver-relative learnable zone anchored in demonstrated...
| Authors | Fanzhe Meng, Guoxin Chen, Jiale Zhao et al. |
|---|---|
| Primary category | cs.LG |
| Published | 6 August 2026 |
| Last updated at source | 6 August 2026 |
Connected in the knowledge graph
- AweAI-Team/CalibForgeDataset · cited by
Models and datasets referencing this paper
- AweAI-Team/CalibForgeDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.