EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision

• URL: http://arxiv.org/abs/2608.07196v1
• Date: Fri, 07 Aug 2026 13:11:42 GMT
• Title: EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision
• Abstract summary: We introduce EMAS (Evolving Multi-Agent System) to revise MAS topology and prompts without updating LLM parameters.<n>Across four benchmarks and two LLMs, EMAS attains the highest task-weighted overall accuracy for both backbones.<n> EMAS can turn experience from new samples into reusable updates to MAS topology and prompts.
• Score: 49.07453709918038
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system unchanged on subsequent samples. Experience from these samples is rarely consolidated into reusable system updates, while accuracy-oriented designs may incur high token costs. We introduce EMAS (Evolving Multi-Agent System), which uses this experience to revise MAS topology and prompts without updating LLM parameters, either to improve accuracy or to reduce cost. EMAS converts traces into structured diagnoses that specify a revision operation and target. It generates a candidate revision only when the same diagnosis recurs across samples and applies it only if paired validation against the current MAS meets the corresponding acceptance criterion. Across four benchmarks and two LLMs, EMAS attains the highest task-weighted overall accuracy for both backbones and is best or tied in six of eight model--benchmark settings. Within two evolution epochs, EMAS achieves relative gains of 6.30% and 20.10% in task-weighted accuracy on Kimi-K2-6 and Qwen3.6-27B, respectively. On MBPP with Qwen3.6-27B, EMAS raises accuracy from 55.09% to 89.12% while reducing token use per task by 62.2%. These results show that EMAS can turn experience from new samples into reusable updates to MAS topology and prompts.

Related papers

• LLM-as-a-Verifier: A General-Purpose Verification Framework [74.40111651545979]
  We introduce LLM-as-a-Verifier, a general-purpose verification framework.<n>It provides fine-grained feedback for agentic tasks without requiring additional training.<n>It achieves state-of-the-art performance on several benchmarks.
  arXiv  Detail & Related papers  (2026-07-06T17:59:35Z)
• FDM: A Framework for Decision-making to build ML-based Malware detection systems [3.552368449344917]
  This paper proposes the Framework for Decision-making (FDM) to build ML-based malware detection systems.<n>The FDM ranks five operational parameters to ranked recommendations across nine configuration dimensions.<n>Four experiments were conducted on three datasets to validate the framework.
  arXiv  Detail & Related papers  (2026-06-05T04:21:22Z)
• EngiAI: A Multi-Agent Framework and Benchmark Suite for LLM-Driven Engineering Design [0.4499833362998488]
  We introduce a benchmark suite with three evaluation dimensions.<n>We present EngiAI, a Multi-Agent System (MAS) implementation built on LangGraph.
  arXiv  Detail & Related papers  (2026-05-19T12:12:09Z)
• PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents [53.369140518949656]
  We introduce PersonalAI 2.0 (PAI-2), a novel framework to enhance large language model (LLM) based systems through integration of external knowledge graphs (KG)<n>The proposed approach addresses key limitations of existing Retrieval-Augmented Generation (GraphRAG) methods by incorporating a dynamic, multistage query processing pipeline.<n>We show that use of graph algorithms (e.g. BeamSearch, WaterCircles) gain superior results compared to standard flatten retriever on average 6%, while enabled search plan enhancement mechanism gain 18% boost compared to disabled one by LLM-as-a-Judge across six datasets.
  arXiv  Detail & Related papers  (2026-05-13T13:06:30Z)
• Fragile Reasoning: A Mechanistic Analysis of LLM Sensitivity to Meaning-Preserving Perturbations [2.7946918847372277]
  Large language models demonstrate strong performance on mathematical reasoning benchmarks, yet remain surprisingly fragile to meaning-preserving surface perturbations.<n>We systematically evaluate three open-weight LLMs, Mistral-7B, Llama-3-8B, and Qwen2.5-7B, on 677 GSM8K problems paired with semantically equivalent variants.<n>All three models exhibit substantial answer-flip rates (28.8%-45.1%), with number paraphrasing consistently more disruptive than name swaps.
  arXiv  Detail & Related papers  (2026-04-02T05:30:20Z)
• Evolutionary Multi-Objective Fusion of Deepfake Speech Detectors [0.17398560678845076]
  We propose an evolutionary multi-objective score fusion framework that jointly minimizes detection error and system complexity.<n>Experiments on the ASVspoof 5 dataset with 36 SSL-based detectors show that the obtained fronts outperform simple averaging and logistic regression baselines.<n>Our method also provides a diverse set of trade-off solutions, enabling deployment choices that balance accuracy and computational cost.
  arXiv  Detail & Related papers  (2026-04-01T19:17:59Z)
• Improving Sampling for Masked Diffusion Models via Information Gain [9.059619122219502]
  Masked Diffusion Models (MDMs) offer greater flexibility in decoding order than autoregressive models.<n> Existing samplers typically adopt greedys, prioritizing positions with the highest local certainty to decode at each step.<n>We propose the Info-Gain Sampler, a principled decoding framework that balances immediate uncertainty with information gain.
  arXiv  Detail & Related papers  (2026-02-20T12:26:03Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• LLM2: Let Large Language Models Harness System 2 Reasoning [65.89293674479907]
  Large language models (LLMs) have exhibited impressive capabilities across a myriad of tasks, yet they occasionally yield undesirable outputs.<n>We introduce LLM2, a novel framework that combines an LLM with a process-based verifier.<n>LLMs2 is responsible for generating plausible candidates, while the verifier provides timely process-based feedback to distinguish desirable and undesirable outputs.
  arXiv  Detail & Related papers  (2024-12-29T06:32:36Z)
• How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts [54.07541591018305]
  We present MAD-Bench, a benchmark that contains 1000 test samples divided into 5 categories, such as non-existent objects, count of objects, and spatial relationship. We provide a comprehensive analysis of popular MLLMs, ranging from GPT-4v, Reka, Gemini-Pro, to open-sourced models, such as LLaVA-NeXT and MiniCPM-Llama3. While GPT-4o achieves 82.82% accuracy on MAD-Bench, the accuracy of any other model in our experiments ranges from 9% to 50%.
  arXiv  Detail & Related papers  (2024-02-20T18:31:27Z)

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.