Empirical study finds isolation drives gains for weak models in multi-agent RAG while scoring matters for strong ones, enabling MADARA for cost-efficient adaptive assessment.
Free-mad: Consensus-free multi-agent debate
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
The paper introduces a three-source decomposition showing that answer flips in multi-agent LLM debate include 37% spontaneous instability and 29% harmful conformity, with even vacuous reasoning persuading 20-39% of resistant agents and interventions reducing harmful conformity by 13.6 points.
AgentCollabBench shows that multi-agent reliability is limited by communication topology, with converging-DAG nodes causing synthesis bottlenecks that discard constraints and explain 7-40% of information loss variance.
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.
TS-RAG uses a discrete taxonomic bottleneck to improve transfer of argumentative logic in agentic persuasion, raising win rates from 70.5 to 78.5 in asymmetric matchups and reducing sycophancy via turn-by-turn diagnostics.
citing papers explorer
-
To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG
Empirical study finds isolation drives gains for weak models in multi-agent RAG while scoring matters for strong ones, enabling MADARA for cost-efficient adaptive assessment.
-
Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate
The paper introduces a three-source decomposition showing that answer flips in multi-agent LLM debate include 37% spontaneous instability and 29% harmful conformity, with even vacuous reasoning persuading 20-39% of resistant agents and interventions reducing harmful conformity by 13.6 points.
-
AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
AgentCollabBench shows that multi-agent reliability is limited by communication topology, with converging-DAG nodes causing synthesis bottlenecks that discard constraints and explain 7-40% of information loss variance.
-
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.
-
Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval
TS-RAG uses a discrete taxonomic bottleneck to improve transfer of argumentative logic in agentic persuasion, raising win rates from 70.5 to 78.5 in asymmetric matchups and reducing sycophancy via turn-by-turn diagnostics.