AutoRAS: Learning Robust Agentic Systems with Primitive Representations

• URL: http://arxiv.org/abs/2606.21445v1
• Date: Fri, 19 Jun 2026 14:05:37 GMT
• Title: AutoRAS: Learning Robust Agentic Systems with Primitive Representations
• Abstract summary: AutoRAS is a framework for the automated design of robust agentic systems.<n>Experiments show that AutoRAS achieves the best performance in both vanilla and adversarial settings.
• Score: 24.053606410215128
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The automated design of agentic systems offers a promising pathway for scaling large language models (LLMs) beyond single-agent reasoning. While prior work has advanced task performance through handcrafted or automatically generated multi-agent workflows, robustness is often treated as an afterthought, leaving systems vulnerable to external adversaries and internal failures. We propose AutoRAS, a framework for the Automated design of Robust Agentic Systems. AutoRAS formulates system design as generating a sequence of symbolic primitives that jointly encode structural connectivity and behavioral actions, and learns to optimize this sequence using execution-derived safety signals and flow-based sequence-level objectives. Extensive experiments show that AutoRAS achieves the best performance in both vanilla and adversarial settings, with the smallest performance degradation under attacks. Further analyses demonstrate strong transferability, stable optimization behavior, stability across primitive sets, and favorable cost trade-offs. Our code is available at $\href{https://github.com/guohezuy/AutoRAS}{\text{this https URL}}$.

Related papers

• Stateful Multi-Agent LLMs for Cross-View Interface Alignment in Automotive Model-Based Systems Engineering [29.585470064353014]
  Large Language Models (LLMs) can accelerate Model-Based Systems Engineering (MBSE) for software-defined vehicles.<n>Their probabilistic nature causes "architectural drift", fabricating interfaces in behavioral views that lack structural foundations.<n>We propose a stateful, multi-agent validation pipeline to enforce deterministic interface alignment.
  arXiv  Detail & Related papers  (2026-08-08T09:49:10Z)
• The Illusion of Multi-Agent Advantage [63.92466143571383]
  We show that expert-architected Multi-Agent Systems (MAS) consistently outperforms automatically generated architectures in raw performance and cost-efficiency.<n>Existing evaluation frameworks mask critical architectural gaps and inefficiencies by failing to account for the marginal utility of increased computational cost.
  arXiv  Detail & Related papers  (2026-06-11T07:39:24Z)
• GenAutoML: An Agentic Framework for Dynamic Architecture Generation and Optimization in Time-Series Analysis [0.22166578153935787]
  GenAutoML is an agentic framework that leverages Large Language Models as neural architects to bridge natural-language requirements and PyTorch implementations.<n>Experiments on the ETTh1, ETTm1, and Weather benchmarks demonstrate that GenAutoML can dynamically generate task-specific neural architectures tailored to dataset characteristics.<n>By emphasizing computational efficiency, architectural adaptability, and stable optimization behavior, GenAutoML enables the creation of ultra-lightweight neural networks suitable for resource-constrained and latency-sensitive Edge AI deployments.
  arXiv  Detail & Related papers  (2026-06-04T08:35:40Z)
• Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models [69.55139736609367]
  Agent-GWO is a dynamic prompt optimization framework for complex reasoning.<n>We show that Agent-GWO consistently improves accuracy and stability over existing prompt optimization methods.
  arXiv  Detail & Related papers  (2026-04-14T07:35:37Z)
• Loosely-Structured Software: Engineering Context, Structure, and Evolution Entropy in Runtime-Rewired Multi-Agent Systems [9.34019956999278]
  Building robust multi-agent systems requires engineering discipline focused on architecture to manage complexity under uncertainty.<n>This paper introduces emphLoosely-Structured Software (LSS), a new class of software systems that shifts the engineering focus from constructing deterministic logic to managing the runtime entropy.
  arXiv  Detail & Related papers  (2026-03-16T02:07:34Z)
• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering [51.07491603393163]
  tAgent is a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals.<n>By leveraging soft supervision and weighted aggregation of agent outputs, Agent learns principled collaboration schemes that capture the complementary strengths of diverse agents.
  arXiv  Detail & Related papers  (2025-10-06T23:20:49Z)
• MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems [40.44248136759827]
  We introduce MAS$2$, a multi-agent system that autonomously architects bespoke multi-agent systems.<n> MAS$2$ achieves performance gains of up to $19.6%$ over state-of-the-art MAS.
  arXiv  Detail & Related papers  (2025-09-29T06:20:10Z)
• Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement [112.04307762405669]
  G"odel Agent is a self-evolving framework inspired by the G"odel machine.<n>G"odel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
  arXiv  Detail & Related papers  (2024-10-06T10:49:40Z)

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.