From Migration to Calibration: Aligning Agents with Deployment Requirements
cs.AI, cs.MA, cs.SE
Submitted: 2026-09-28
Updated: 2026-10-15
Comments: 40 pages, 8 figures. Methodological proposal; no confirmatory empirical results reported. CPU controller update/export example is implemented on synthetic data only; the integrated automatic RL calibration tool, consultant workflow, trajectory-distilled skill service, and manufacturing experiments remain future work
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- PromptBridge: Cross-Model Prompt Transfer for Large Language Models
- HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
- HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
- When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents
- Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Models
- UXBench: Benchmarking User Experience in AI Assistants
- PERSONAJUDGE: Simulating Individual Human Preference Judgments with Evaluator-Specific Demonstration Data
- From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM Agents
- EMPATH: A Multilingual Auditor-Judge Benchmark for Safety Evaluation of Emotional-Support Chatbots
- LLM Judges Can Be Too Generous When There Is No Reference Answer
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Agent Lightning: Train ANY AI Agents with Reinforcement Learning
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Distilling LLM Agent into Small Models with Retrieval and Code Tools
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
- DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training
- CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems