Research map / Multi-agent systems and games / Cooperative multi-agent RL
Blameworthiness in Multi-Agent Settings
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Lower the cost of changing one's vote from $2000 to $500 | Agent 2 under the group-blame apportionment method · Committee voting example | individual blameworthiness: ≈0.073 -> ≈0.120 | Helped |
| Make social pressure less effective, increasing each agent's yes-vote probability by n × 3% rather than n × 5% | Group blameworthiness method · Committee voting example | group blameworthiness: ≈0.390 -> ≈0.317 | Hurt |
| Increase the cost of social pressure from n × 100 to n × 150 | Group blameworthiness method · Committee voting example | group blameworthiness: ≈0.390 -> ≈0.361 | Hurt |
| Lower other agents' initial yes-vote probability from 60% to 40% | Group blameworthiness method · Committee voting example | group blameworthiness: ≈0.390 -> ≈0.560 | Helped |
| Vote yes rather than no | Agent 6 under the group-blame apportionment method · Committee voting example | individual blameworthiness: ≈0.073 -> ≈0.022 | Hurt |
| Vote yes rather than no | Group blameworthiness method · Committee voting example | group blameworthiness: ≈0.390 -> ≈0.157 | Hurt |
| Account for feasible collective coordination and its cost when assessing responsibility | Group blameworthiness method · Tragedy of the Commons | group blameworthiness | Helped |
| Use the Shapley value to apportion group blame among individuals | Individual blameworthiness derived from group blameworthiness · Multi-agent settings | axiom satisfaction | Helped |
Closest papers by meaning
- Many LLMs Are More Utilitarian Than One (NeurIPS 2025 · similarity 0.86)
- Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games (NeurIPS 2024 · similarity 0.85)
- Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect Theory (ICML 2025 · similarity 0.84)
- Reasoning About Actual Causes in Nondeterministic Domains (AAAI 2025 · similarity 0.83)
- From Single to Societal: Analyzing Persona-Induced Bias in Multi-Agent Interactions (AAAI 2026 · similarity 0.83)
- Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents (NeurIPS 2025 · 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.