LC-MAPF uses multi-round local communication between neighboring agents in a pre-trained model to outperform prior learning-based MAPF solvers on diverse unseen scenarios while preserving scalability.
Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Structured per-agent randomness via ranked masking in attention allows symmetric agents to break ties and coordinate, achieving perfect success on symmetric tasks where deterministic policies fail and enabling zero-shot transfer across team sizes.
MAGIC estimates multi-step action effects between agents with counterfactual interventions, gates them by advantage, and converts them to intrinsic rewards, yielding 26.9% and 10.1% relative gains on MPE and SMAC benchmarks.
citing papers explorer
-
Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding
LC-MAPF uses multi-round local communication between neighboring agents in a pre-trained model to outperform prior learning-based MAPF solvers on diverse unseen scenarios while preserving scalability.
-
Randomness is sometimes necessary for coordination
Structured per-agent randomness via ranked masking in attention allows symmetric agents to break ties and coordinate, achieving perfect success on symmetric tasks where deterministic policies fail and enabling zero-shot transfer across team sizes.
-
MAGIC: Multi-Step Advantage-Gated Causal Influence for Multi-agent Reinforcement Learning
MAGIC estimates multi-step action effects between agents with counterfactual interventions, gates them by advantage, and converts them to intrinsic rewards, yielding 26.9% and 10.1% relative gains on MPE and SMAC benchmarks.