Which LLM Multi-Agent Protocol to Choose?
- URL: http://arxiv.org/abs/2510.17149v2
- Date: Sun, 26 Oct 2025 05:33:41 GMT
- Title: Which LLM Multi-Agent Protocol to Choose?
- Authors: Hongyi Du, Jiaqi Su, Jisen Li, Lijie Ding, Yingxuan Yang, Peixuan Han, Xiangru Tang, Kunlun Zhu, Jiaxuan You,
- Abstract summary: We introduce ProtocolBench, a benchmark that compares agent protocols along four measurable axes: task success, end-to-end latency, message or byte overhead, and under failures.<n>On ProtocolBench, protocol choice significantly influences system behavior.<n> Protocol completion is a learnable protocol router that selects per-scenario protocols from requirement and runtime signals.
- Score: 30.16052895726503
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: As large-scale multi-agent systems evolve, the communication protocol layer has become a critical yet under-evaluated factor shaping performance and reliability. Despite the existence of diverse protocols (A2A, ACP, ANP, Agora, etc.), selection is often intuition-driven and lacks standardized guidance. We introduce ProtocolBench, a benchmark that systematically compares agent protocols along four measurable axes: task success, end-to-end latency, message or byte overhead, and robustness under failures. On ProtocolBench, protocol choice significantly influences system behavior. In the Streaming Queue scenario, overall completion time varies by up to 36.5% across protocols, and mean end-to-end latency differs by 3.48 s. Under Fail-Storm Recovery, resilience also differs consistently across protocols. Beyond evaluation, we present ProtocolRouter, a learnable protocol router that selects per-scenario (or per-module) protocols from requirement and runtime signals. ProtocolRouter reduces Fail-Storm recovery time by up to 18.1% versus the best single-protocol baseline, and achieves scenario-specific gains such as higher success in GAIA. We also release ProtocolRouterBench to standardize protocol evaluation and improve reliability at scale.
Related papers
- LLM-Assisted Model-Based Fuzzing of Protocol Implementations [9.512044399020514]
Faults in protocol behavior can lead to vulnerabilities and system failures.<n>A common approach to protocol testing involves constructing Markovian models that capture the state transitions and expected behaviors of the protocol.<n>We propose a novel method that leverages large language models (LLMs) to automatically generate sequences for testing network protocol implementations.
arXiv Detail & Related papers (2025-08-03T13:16:18Z) - Experimental Simulation of Two Pulses and Three Pulses Coherent One Way Quantum Key Distribution Protocol in Noisy/Noiseless and Wired/Wireless Environment [1.8638865257327277]
Coherent One Way (COW) protocol is one of the most famous protocol because of its ease of hardware deployment.
We demonstrate the encoding as well as decoding portions of the protocols under both noisy and noiseless scenario.
arXiv Detail & Related papers (2024-09-23T11:02:52Z) - Making Existing Quantum Position Verification Protocols Secure Against
Arbitrary Transmission Loss [0.889974344676093]
In quantum position verification (QPV) protocols, even relatively small loss rates can compromise security.
We modify the usual structure of QPV protocols and prove that this modification makes the potentially high transmission loss between the verifiers security-irrelevant.
We show possible implementations of the required photon presence detection, making c-$mathrmQPV_mathrmBB84f$ a protocol that solves all major practical issues in QPV.
arXiv Detail & Related papers (2023-12-19T21:38:10Z) - Bicoptor 2.0: Addressing Challenges in Probabilistic Truncation for Enhanced Privacy-Preserving Machine Learning [6.733212399517445]
This paper focuses on analyzing the problems and proposing solutions for the probabilistic truncation protocol in existing PPML works.
In terms of accuracy, we reveal that precision selections recommended in some of the existing works are incorrect.
We propose a solution and a precision selection guideline for future works.
arXiv Detail & Related papers (2023-09-10T01:43:40Z) - Multi-User Entanglement Distribution in Quantum Networks Using Multipath
Routing [55.2480439325792]
We propose three protocols that increase the entanglement rate of multi-user applications by leveraging multipath routing.
The protocols are evaluated on quantum networks with NISQ constraints, including limited quantum memories and probabilistic entanglement generation.
arXiv Detail & Related papers (2023-03-06T18:06:00Z) - Single-photon-memory measurement-device-independent quantum secure
direct communication [63.75763893884079]
Quantum secure direct communication (QSDC) uses the quantum channel to transmit information reliably and securely.
In order to eliminate the security loopholes resulting from practical detectors, the measurement-device-independent (MDI) QSDC protocol has been proposed.
We propose a single-photon-memory MDI QSDC protocol (SPMQC) for dispensing with high-performance quantum memory.
arXiv Detail & Related papers (2022-12-12T02:23:57Z) - Towards Semantic Communication Protocols: A Probabilistic Logic
Perspective [69.68769942563812]
We propose a semantic protocol model (SPM) constructed by transforming an NPM into an interpretable symbolic graph written in the probabilistic logic programming language (ProbLog)
By leveraging its interpretability and memory-efficiency, we demonstrate several applications such as SPM reconfiguration for collision-avoidance.
arXiv Detail & Related papers (2022-07-08T14:19:36Z) - Byzantine-Robust Federated Learning with Optimal Statistical Rates and
Privacy Guarantees [123.0401978870009]
We propose Byzantine-robust federated learning protocols with nearly optimal statistical rates.
We benchmark against competing protocols and show the empirical superiority of the proposed protocols.
Our protocols with bucketing can be naturally combined with privacy-guaranteeing procedures to introduce security against a semi-honest server.
arXiv Detail & Related papers (2022-05-24T04:03:07Z) - Data post-processing for the one-way heterodyne protocol under
composable finite-size security [62.997667081978825]
We study the performance of a practical continuous-variable (CV) quantum key distribution protocol.
We focus on the Gaussian-modulated coherent-state protocol with heterodyne detection in a high signal-to-noise ratio regime.
This allows us to study the performance for practical implementations of the protocol and optimize the parameters connected to the steps above.
arXiv Detail & Related papers (2022-05-20T12:37:09Z) - Minimum Entanglement Protocols for Function Estimation [0.0]
We prove necessary and sufficient conditions for the existence of optimal protocols using at most $k$-partite entanglement.
Our protocols require some amount of time-dependent control, and we show that a related class of time-independent protocols fail to achieve optimal scaling for generic functions.
arXiv Detail & Related papers (2021-10-14T18:00:00Z) - Round-robin differential phase-time-shifting protocol for quantum key
distribution: theory and experiment [58.03659958248968]
Quantum key distribution (QKD) allows the establishment of common cryptographic keys among distant parties.
Recently, a QKD protocol that circumvents the need for monitoring signal disturbance, has been proposed and demonstrated in initial experiments.
We derive the security proofs of the round-robin differential phase-time-shifting protocol in the collective attack scenario.
Our results show that the RRDPTS protocol can achieve higher secret key rate in comparison with the RRDPS, in the condition of high quantum bit error rate.
arXiv Detail & Related papers (2021-03-15T15:20:09Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.