MIT AI Risk Repository · Risk Sub-Category · 73.02.02
Groups of LLM-Agents May Show Emergent Functionality
Category: Multi-Agent Safety Is Not Assured by Single-Agent Safety
Description
"Multi-agent learning, either through explicit finetuning or implicit in-context learning, may enable LLM-agents to influence each other during their interactions (Foerster et al., 2018). Under some environmental settings, this can create feedback loops that result in novel and emergent behaviors that would not manifest in the absence of multi-agent interactions (Hammond et al., 2024, Section 3.6). Emergent functionality is a safety risk in two ways. Firstly, it may itself be dangerous (Shevlane et al., 2023). Secondly, it makes assurance harder as such emergent behaviors are difficult to pre
From Foundational Challenges in Assuring Alignment and Safety of Large Language Models (Anwar2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).
Classification
- Subdomain
- 7.6 Multi-agent risks
- Causal entity
- Other
- Intent
- Other
- Timing
- Post-deployment
Subdomain definition: Risks from multi-agent interactions, due to incentives (which can lead to conflict or collusion) and/or the structure of multi-agent systems, which can create cascading failures, selection pressures, new security vulnerabilities, and a lack of shared information and trust.
How other frameworks describe this risk
Other entries from Anwar2024
- Agentic LLMs Pose Novel Risks
- Natural Language Underspecifies Goals
- Goal-Directedness Incentivizes Undesirable Behaviors
- Safety Risks from Affordances Provided to LLM-agents
- Multi-Agent Safety Is Not Assured by Single-Agent Safety
- Foundationality May Cause Correlated Failures
- Collusion between LLM-Agents
- Dual-Use Capabilities Enable Malicious Use and Misuse of LLMs
- Misinformation and Manipulation
- Cybersecurity
- Cybersecurity
- Cybersecurity