LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic topology design, ARG-Designer, has reframed this problem as autoregressive graph generation.
arXiv:2608. 20099v1 Announce Type: cross Abstract: LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption.
The paper introduces K‑GAT, a neuro‑symbolic framework that generates multi‑agent collaboration topologies conditioned on external evidence, treating the design as a knowledge‑conditioned structure learning problem. Unlike prior methods that rely mainly on large language model parameters, K‑GAT integrates external evidence directly into autoregressive graph generation, reducing redundant interactions and improving verification in knowledge‑intensive tasks. Experiments on benchmarks such as the expert‑level GPQA dataset show K‑GAT achieving a +15.7% accuracy gain over the LLM‑Debate baseline while using fewer computational tokens.
MAGIC introduces a dense‑reward reinforcement learning framework for generating mixed‑granularity agent graphs in large‑language‑model based multi‑agent systems. The method sequentially selects functional roles, instantiates them as either single agents or reusable groups, and connects them to existing units, optimizing the construction policy with intermediate feedback from probe‑based utility and structural signals. Experiments show MAGIC outperforms state‑of‑the‑art baselines on eight benchmarks and achieves strong inference efficiency.
arXiv:2508. 00429v5 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) have achieved remarkable success in graph-based learning by propagating information among neighbor nodes via predefined aggregation mechanisms.
Unified-MAS is a two-stage framework that decouples node implementation from orchestration in Automatic Multi-Agent Systems. It first searches external knowledge to synthesize domain‑specific node blueprints, then uses a perplexity‑guided reward to optimize bottleneck nodes. Experiments across four specialized domains show that adding Unified-MAS to existing baselines improves performance‑cost trade‑offs by up to 14.2% while lowering costs.
arXiv:2609.05774v1 Announce Type: new Abstract: Recent multi-agent LLM systems increasingly rely on graph-structured communication to coordinate specialized agents. We revisit multi-agent orchestrati...
GRAIN is a single-agent reinforcement learning framework that improves large language models’ robustness to real‑world shifts in node identifiers and task formulations by treating reasoning as a semantic parsing and tool‑execution pipeline. It introduces a Structure Invariance Reward that validates intermediate graphs against ground‑truth topologies, encouraging the model to learn genuine text‑to‑structure mappings instead of overfitting to surface patterns. On the new GRIT benchmark, GRAIN surpasses multi‑agent baselines by 16.45% in accuracy, reduces latency by about 24%, and halves the out‑of‑distribution gap of fine‑tuned models while remaining robust on large‑scale graphs beyond the training distribution.
Multi-agent debate (MAD) has emerged as a promising paradigm for improving the reasoning accuracy of large language models (LLMs) through iterative peer interaction. Communication topology plays a cen...
The paper investigates whether complex communication topologies are necessary for effective multi‑agent debate (MAD) among large language models. It demonstrates that a simple random-without-replacement routing policy—where each agent debates with two newly sampled peers each round—consistently improves the accuracy‑cost trade‑off in sparse MAD setups. Additionally, the study shows that lightweight deliberation stopping can further reduce inference costs without sacrificing accuracy.
arXiv:2608. 07905v1 Announce Type: new Abstract: Embodied agents using LLM-based planners often struggle with physical hallucinations, poor generalization to long-horizon tasks, and lack of environmental awareness.
The paper introduces TopoPlanner, a framework that transforms tool dependency graphs into cellular workflow complexes to enable topology‑consistent task planning for large language model (LLM) agents. It retrieves request‑relevant closed subcomplexes via cosheaf‑consistent cellular retrieval, performs multidimensional structural reasoning on the topology, and feeds the resulting representation to an LLM for generating tool sequences. Experiments on four tool‑planning benchmarks demonstrate consistent improvements over prompt‑based and graph‑enhanced baselines across various LLM backbones, especially for workflows involving loops, merges, and loop‑merge patterns.
arXiv:2608. 12921v1 Announce Type: cross Abstract: The performance of large language model (LLM)-based multi-agent systems (MAS) largely depends on effective communication topologies.