The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
Canonical reference
Autogen: Enabling next-gen llm applications via multi-agent conversations
Canonical reference. 100% of citing Pith papers cite this work as background.
5
Pith papers citing it
Background
100% of classified citations
citation-role summary
background 5
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 5polarities
background 5representative citing papers
Anonymization in multi-agent debate reduces identity bias by equalizing self and peer weights in a Bayesian update model, quantified by the Identity Bias Coefficient.
HCP-MAD reduces token costs in multi-agent debates by using heterogeneous consensus verification, adaptive pair-agent stopping, and escalated collective voting based on task complexity signals.
Generative multi-agent systems exhibit emergent collusion and conformity behaviors that cannot be prevented by existing agent-level safeguards.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
citing papers explorer
-
Why Do Multi-Agent LLM Systems Fail?
The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
-
When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning
Anonymization in multi-agent debate reduces identity bias by equalizing self and peer weights in a Bayesian update model, quantified by the Identity Bias Coefficient.
-
Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate
HCP-MAD reduces token costs in multi-agent debates by using heterogeneous consensus verification, adaptive pair-agent stopping, and escalated collective voting based on task complexity signals.
-
Emergent Social Intelligence Risks in Generative Multi-Agent Systems
Generative multi-agent systems exhibit emergent collusion and conformity behaviors that cannot be prevented by existing agent-level safeguards.
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.