ModeX selects the modal semantic output from multiple LLM generations via a similarity graph and recursive spectral clustering without needing reward models or evaluators.
Improving factuality and reasoning in language models through multiagent debate
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3representative citing papers
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.
EMS reduces the average number of agents invoked for majority voting by 32% via reliability-aware prioritization and early stopping on six benchmarks.
citing papers explorer
-
ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation
ModeX selects the modal semantic output from multiple LLM generations via a similarity graph and recursive spectral clustering without needing reward models or evaluators.
-
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.
-
EMS: Multi-Agent Voting via Efficient Majority-then-Stopping
EMS reduces the average number of agents invoked for majority voting by 32% via reliability-aware prioritization and early stopping on six benchmarks.