Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis

• URL: http://arxiv.org/abs/2607.20216v1
• Date: Wed, 22 Jul 2026 14:36:10 GMT
• Title: Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis
• Abstract summary: Large language models (LLMs) demonstrate impressive capabilities for technical artifact interpretation.<n>Many open-weight models are large, demanding significant compute resources and incurring non-trivial hosting costs.<n>This paper investigates whether orchestrated ensembles of small language models (SLMs) can match or exceed single LLM performance.
• Score: 2.549390156222399
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language models (LLMs) demonstrate impressive capabilities for technical artifact interpretation, the opacity and escalating API costs of closed-weight frontier models motivate exploration of open-weight alternatives. However, many open-weight models are large, demanding significant compute resources and incurring non-trivial hosting costs that place them beyond reach for resource-constrained deployments. This paper investigates whether orchestrated ensembles of small language models (SLMs) can match or exceed single LLM performance on structured questions about malware detonation reports. We established baselines by testing eleven open-weight SLMs, three cyber security pre-trained models, and six frontier LLMs on Meta's CyberSecEval Malware Analysis benchmark. We then designed and evaluated four orchestration architectures: (i) a multi-agent pipeline that decomposes analysis into structured evidence-collection and reasoning stages, (ii) an adversarial debate framework in which two agents iteratively critique each other's reasoning, (iii) a hierarchical consultation system that pairs a general-purpose SLM with a cyber-specialised expert model, and (iv) a hybrid architecture that combines evidence-grounded pipelines with adversarial debate reasoning. The hybrid system (Qwen3-4B with Foundation-Sec-8B) achieved 35.30% overall accuracy, exceeding the strongest cyber-specialised baseline (22.54%) and the strongest ungrounded frontier baseline (34.77%); when given the same evidence pipeline, grounded Gemini remained the strongest configuration at 38.22%. These findings show that evidence-grounded orchestration can substantially improve the performance of collaborative SLMs for supporting interpretation of malware detonation reports.

Related papers

• RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deployable Anomaly Detection Assistants [48.63201300674347]
  Multimodal industrial anomaly inspection assistants are a critical component of next-generation smart factories.<n>MSLMs offer a deployable alternative, yet progress is constrained by the lack of comprehensive robustness analyses.<n>We develop RobustMAD to evaluate model robustness through diverse open-ended queries.
  arXiv  Detail & Related papers  (2026-06-26T09:15:07Z)
• SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks [65.14594927081983]
  We present SciOrch, a framework that trains a lightweight 8B model to orchestrate frontier LLMs for scientific reasoning.<n>On a 240-question test set spanning SGI-Reasoning and Scientists' First exam, SciOrch reaches 56.66% average accuracy.<n>It also attains the best accuracy on both SGI and SFE with less than half the API cost of typical multi-agent methods.
  arXiv  Detail & Related papers  (2026-06-14T15:45:34Z)
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• Feedback-Driven Execution for LLM-Based Binary Analysis [6.612857121548629]
  We present FORGE, a system that rethinks LLM-based analysis as a feedback-driven execution process.<n> FORGE interleaves reasoning and tool interaction through a reasoning-action-observation loop.<n>We evaluate FORGE on 3,457 real-world firmware binaries.
  arXiv  Detail & Related papers  (2026-04-16T15:15:58Z)
• SALLIE: Safeguarding Against Latent Language & Image Exploits [1.6440434996206623]
  We introduce SALLIE, a lightweight runtime detection framework rooted in mechanistic interpretability.<n> SALLIE extracts robust signals directly from the model's internal activations.<n>At inference, SALLIE defends via a three-stage architecture.
  arXiv  Detail & Related papers  (2026-04-06T16:29:05Z)
• Box Maze: A Process-Control Architecture for Reliable LLM Reasoning [0.0]
  This paper proposes a conceptual process-control architecture that decomposes large language models into three explicit layers: memory grounding, structured inference, and boundary enforcement.<n>Preliminary results indicate that process-level control may offer a promising direction for improving reliability in large language model reasoning.
  arXiv  Detail & Related papers  (2026-03-19T17:41:18Z)
• AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents [75.67445299298949]
  AgentCPM-Explore is a compact 4B agent model with high knowledge density and strong exploration capability.<n>We introduce a holistic training framework featuring parameter-space model fusion, reward signal denoising, and contextual information refinement.<n>AgentCPM-Explore achieves state-of-the-art (SOTA) performance among 4B-class models, matches or surpasses 8B-class SOTA models on four benchmarks, and even outperforms larger-scale models such as Claude-4.5-Sonnet or DeepSeek-v3.2 in five benchmarks.
  arXiv  Detail & Related papers  (2026-02-06T08:24:59Z)
• RHINO: Guided Reasoning for Mapping Network Logs to Adversarial Tactics and Techniques with Large Language Models [9.065322387043546]
  We introduce RHINO, a framework that decomposes Large Language Models into three interpretable phases mirroring human reasoning.<n> RHINO bridges the semantic gap between low-level observations and adversarial intent while improving output reliability through structured reasoning.<n>Our results demonstrate that RHINO significantly enhances the interpretability and scalability of threat analysis, offering a blueprint for deploying LLMs in operational security settings.
  arXiv  Detail & Related papers  (2025-10-16T02:25:46Z)
• Benefits and Limitations of Communication in Multi-Agent Reasoning [11.788489289062312]
  We propose a theoretical framework to analyze the expressivity of multi-agent systems.<n>We derive bounds on (i) the number of agents required to solve the task exactly, (ii) the quantity and structure of inter-agent communication, and (iii) the achievable speedups as problem size and context scale.<n>Our results identify regimes where communication is provably beneficial, delineate tradeoffs between agent count and bandwidth, and expose intrinsic limitations when either resource is constrained.
  arXiv  Detail & Related papers  (2025-10-14T20:04:27Z)
• mSCoRe: a $M$ultilingual and Scalable Benchmark for $S$kill-based $Co$mmonsense $Re$asoning [74.97363626515236]
  We propose a textbfMultilingual and Scalable Benchmark for textbfSkill-based textbfCommonsense textbfReasoning (textbfmSCoRe)<n>Our benchmark incorporates three key components that are designed to systematically evaluate LLM's reasoning capabilities.<n>Our results reveal the limitations of such reasoning-reinforced models when confronted with nuanced multilingual general and cultural commonsense.
  arXiv  Detail & Related papers  (2025-08-13T18:59:02Z)
• T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models [88.63040835652902]
  Text to video models are vulnerable to jailbreak attacks, where specially crafted prompts bypass safety mechanisms and lead to the generation of harmful or unsafe content.<n>We propose T2VShield, a comprehensive and model agnostic defense framework designed to protect text to video models from jailbreak threats.<n>Our method systematically analyzes the input, model, and output stages to identify the limitations of existing defenses.
  arXiv  Detail & Related papers  (2025-04-22T01:18:42Z)
• Why Do Multi-Agent LLM Systems Fail? [87.90075668488434]
  We introduce MAST-Data, a comprehensive dataset of 1600+ annotated traces collected across 7 popular MAS frameworks.<n>We build the first Multi-Agent System Failure taxonomy (MAST)<n>We leverage MAST and MAST-Data to analyze failure patterns across models (GPT4, Claude 3, Qwen2.5, CodeLlama) and tasks (coding, math, general agent)
  arXiv  Detail & Related papers  (2025-03-17T19:04:38Z)

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.