Safety
From Migration to Calibration: Preserving Agent Capabilities across Models, Jurisdictions, and Scale
arXiv:2609.35149v2 Announce Type: replace Abstract: Deploying, migrating, or scaling an agent can change its model, harness, infrastructure, application, and intended users. We formulate agent calibra
arXiv:2609.35149v2 Announce Type: replace Abstract: Deploying, migrating, or scaling an agent can change its model, harness, infrastructure, application, and intended users. We formulate agent calibration as standards-first adaptation: define basic-capability, technical-environment, and user-context standards; diagnose gaps; generate and apply revisions; and recheck the same standards within fixed budgets. These standard families interact across information, harness, and user-acceptance layers. Source behavior is diagnostic, not a perfect reference or capability ceiling: model replacement can turn correct answers into errors or errors into correct answers. Qualification requires all mandatory known tests, actual end-to-end deployment paths, hard predicates, and declared task/user minimums to pass; aggregate gains cannot erase hard failures. Revisions may change tools or harnesses, add demonstrations and task descriptions, or use validated target-native trajectories to train a policy, controller, or compact skill model served through the harness. Semantic checkpoints validate executed artifacts, localize repair, and revalidate dependencies. The loop exports reusable configuration or training artifacts with a qualification record, while final task outputs undergo their own checks. Independent factual evidence precedes relative preference judgment; DPO and GRPO optimize policies rather than establish truth. Frozen held-out evaluation tests generalization and compares equal-budget target-native optimization. We specify an automatic calibration tool using limited authorized user trajectories and tests as future work. The framework and tool remain proposals; confirmatory empirical validation is pending.
Related
- Structured Agent Distillation for Large Language Model
- SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
- Asymptotic Universal Alignment: A New Alignment Framework via Test-Time Scaling
- The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
Source: arXiv cs.AI | 2026-10-05