3 papers
cs.MA2025
MALLM: Multi-Agent Large Language Models Framework
Jonas Becker, Lars Benedikt Kaesberg, Niklas Bauer +3
Multi-agent debate (MAD) has demonstrated the ability to augment collective intelligence by scaling test-time compute and leveraging expertise. Current frameworks for multi-agent d…
cs.AI2025
SPaRC: A Spatial Pathfinding Reasoning Challenge
Lars Benedikt Kaesberg, Jan Philip Wahle, Terry Ruas +1
Existing reasoning datasets saturate and fail to test abstract, multi-step problems, especially pathfinding and complex rule constraint satisfaction. We introduce SPaRC (Spatial Pa…
cs.MA2025
Voting or Consensus? Decision-Making in Multi-Agent Debate
Lars Benedikt Kaesberg, Jonas Becker, Jan Philip Wahle +2
Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers,…