# BANDMAS: Causality-Inspired Semantic Packet Scheduling for Bandwidth-Efficient Multi-Agent Collaboration

arXiv: https://arxiv.org/abs/2608.00458 · HTML: https://mlsanity.com/paper/2608.00458/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 1 Aug 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 27 of 27)

- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [Deep Learning Enabled Semantic Communication Systems](https://mlsanity.com/paper/2006.10685/) (2020)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- [Multi-agent Architecture Search via Agentic Supernet](https://mlsanity.com/paper/2502.04180/) (2025)
- [Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2410.02506/) (2024)
- [Generative Causal Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.06643/) (2021)
- [Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks](https://mlsanity.com/paper/1812.09755/) (2018)
- [G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks](https://mlsanity.com/paper/2410.11782/) (2024)
- [Improving Multi-Agent Debate with Sparse Communication Topology](https://mlsanity.com/paper/2406.11776/) (2024)
- [Learning to Schedule Communication in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1902.01554/) (2019)
- [MasRouter: Learning to Route LLMs for Multi-Agent Systems](https://mlsanity.com/paper/2502.11133/) (2025)
- [KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems](https://mlsanity.com/paper/2510.12872/) (2025)
- [FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Models](https://mlsanity.com/paper/2402.14116/) (2024)
- [SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication](https://mlsanity.com/paper/2508.11733/) (2025)
- [S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning](https://mlsanity.com/paper/2511.06727/) (2025)
- [Q-KVComm: Efficient Multi-Agent Communication Via Adaptive KV Cache Compression](https://mlsanity.com/paper/2512.17914/) (2025)
- [HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference](https://mlsanity.com/paper/2512.22137/) (2025)
- [Semantic Packet Aggregation for Token Communication via Genetic Beam Search](https://mlsanity.com/paper/2504.19591/) (2025)
- [Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation](https://mlsanity.com/paper/2605.04922/) (2026)
- [HALO: Semantic-Aware Distributed LLM Inference in Lossy Edge Network](https://mlsanity.com/paper/2601.11676/) (2026)

## Abstract (arXiv)

LLM-based multi-agent systems make decisions based on the aggregated information via exchanging messages across specialized agents. Forwarding every generated message among agents increases application-layer traffic. Yet, it introduces tremendous input tokens for agent processing, potentially raising inference latency and computational overhead. Existing approaches attempt to address the above issues by pruning agents or discarding redundant messages. Nevertheless, such agent-level or message-level optimization results in insufficient evidence supporting for final decisions or still containing redundant message transmissions. To address these challenges, we propose BANDMAS, a multi-agent collaboration framework that models inter-agent communications as task-oriented traffic, which enables efficient transmission via causality-inspired replay valuation. Specifically, we decompose messages into several data packets by analyzing their semantic features such as evidence and requests. The system only transmits these packets if their predicted replay-derived contribution exceeds their resource cost. Consequently, BANDMAS is able to adaptively schedule communication packets while adhering to bandwidth, latency, deadline, and receiver context constraints. On frozen Qwen3-4B traffic across SciFact, HotpotQA, and FanOutQA, our framework reduces application-layer bytes by 53.2% to 77.3% at selected caps and attains the highest mean task metric among constrained methods on all three workloads.