Research map / Multi-agent systems and games / Cooperative multi-agent RL
Optimally Auditing Adversarial Agents
Sanmay Das, Fang-Yi Yu, Yuang Zhang
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase the type-1 payment (ablation) | optimal audit policy · three-type simulation (Fig. 3a) | principal's utility | Hurt |
| increase the type-1 payment from small to large (ablation) | optimal audit policy · three-type simulation (Fig. 3b) | social welfare | Mixed |
| adaptive audit policy instead of non-adaptive | audit mechanism · costly audits, insensitivity assumption | principal's worst-case utility | No clear effect |
| optimize for principal utility rather than social welfare | optimal audit policy · three-type simulation (Fig. 2) | truth-telling region | Improved |
Closest papers by meaning
- PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents (NeurIPS 2026 · similarity 0.86)
- Strategic Hypothesis Testing (NeurIPS 2025 · similarity 0.83)
- Robust ML Auditing using Prior Knowledge (ICML 2025 · similarity 0.83)
- Strategic Manipulation in Temporal Voting with Undesirable Candidates (Student Abstract) (AAAI 2025 · similarity 0.83)
- AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems (NeurIPS 2026 · similarity 0.83)
- Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
