Evaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime Governance

arXiv:2609.37501 · cs.CL, cs.AI, cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Grounding — 11× in this paper · explained in 3 episodes
• Agentic AI — 4× in this paper · explained in 1 episode
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Verifiable Rewards — 4× in this paper · explained in 2 episodes
• Accountability — 3× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Reward Function — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptive Safety — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Explainability — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• FinBERT: Financial Sentiment Analysis with Pre-trained Language Models
• Constitutional AI: Harmlessness from AI Feedback
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
• BloombergGPT: A Large Language Model for Finance
• PSG-Agent: Personality-Aware Safety Guardrail for LLM-based Agents
• FinGPT: Open-Source Financial Large Language Models
• Constitution or Collapse? Exploring Constitutional AI with Llama 3-8B

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering