Commission

Compare study types →

Study types

Before you commission

Research

All research areas →

Agent Evaluation and Coordination

Generated-Code and GPU-Kernel Correctness

Efficient inference

Federated Learning and Privacy

Privacy threat models

Decentralised Systems and Protocol

Methods

All methods →

Methods

Free tools

Papers

Evidence

Writing & work

Collaborate

Compare routes →

Ways to work together

About Contact Bring a technical claim

#AI Agents

Two entries on this site carry the AI Agents tag: two papers, dated 2026. Explore the full list of related work below.

Papers

Evaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime Governance
Paper · 2026 · arXiv · cited by 0 RegLLM: a diagnostic harness for bounded autonomy in regulated agents, tracking six indicators including citation validity, escalation correctness and unsafe-action rate, with a runtime supervisor.
Before the Pull Request: Mining Multi-Agent Coordination
Paper · 2026 · arXiv · cited by 0 Studies how concurrent coding agents claim, divide and collide over shared work before a pull request exists, using grite, a git-native append-only coordination log. Duplicate work falls from 78% to 0% and failure modes become minable from the log.