Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives

• URL: http://arxiv.org/abs/2506.09656v2
• Date: Thu, 07 Aug 2025 08:42:17 GMT
• Title: Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives
• Authors: Wei Zeng, Hengshu Zhu, Chuan Qin, Han Wu, Yihang Cheng, Sirui Zhang, Xiaowei Jin, Yinuo Shen, Zhenxing Wang, Feimin Zhong, Hui Xiong,
• Abstract summary: Value alignment for agentic AI systems aims to ensure that an agent's goals, preferences, and behaviors align with human values and societal norms.<n>This study comprehensively reviews value alignment in LLM-based multi-agent systems as the representative archetype of agentic AI systems.
• Score: 29.49571891159761
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The ongoing evolution of AI paradigms has propelled AI research into the agentic AI stage. Consequently, the focus of research has shifted from single agents and simple applications towards multi-agent autonomous decision-making and task collaboration in complex environments. As Large Language Models (LLMs) advance, their applications become more diverse and complex, leading to increasing situational and systemic risks. This has brought significant attention to value alignment for agentic AI systems, which aims to ensure that an agent's goals, preferences, and behaviors align with human values and societal norms. Addressing socio-governance demands through a Multi-level Value framework, this study comprehensively reviews value alignment in LLM-based multi-agent systems as the representative archetype of agentic AI systems. Our survey systematically examines three interconnected dimensions: First, value principles are structured via a top-down hierarchy across macro, meso, and micro levels. Second, application scenarios are categorized along a general-to-specific continuum explicitly mirroring these value tiers. Third, value alignment methods and evaluation are mapped to this tiered framework through systematic examination of benchmarking datasets and relevant methodologies. Additionally, we delve into value coordination among multiple agents within agentic AI systems. Finally, we propose several potential research directions in this field.

Related papers

• Deep Research Agents: A Systematic Examination And Roadmap [79.04813794804377]
  Deep Research (DR) agents are designed to tackle complex, multi-turn informational research tasks.<n>In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute DR agents.
  arXiv  Detail & Related papers  (2025-06-22T16:52:48Z)
• Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey [45.485318955120924]
  The transition from traditional large language models (LLMs) to more advanced AI agents represents a pivotal evolutionary step.<n>Existing evaluation frameworks often blur the distinctions between LLM chatbots and AI agents, leading to confusion among researchers selecting appropriate benchmarks.<n>This paper introduces a systematic analysis of current evaluation approaches, grounded in an evolutionary perspective.
  arXiv  Detail & Related papers  (2025-06-06T17:52:18Z)
• From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems [6.284317913684068]
  Compound Al Systems (CAIS) is an emerging paradigm that integrates large language models (LLMs) with external components, such as retrievers, agents, tools, and orchestrators.<n>Despite growing adoption in both academia and industry, the CAIS landscape remains fragmented, lacking a unified framework for analysis, taxonomy, and evaluation.<n>This survey aims to provide researchers and practitioners with a comprehensive foundation for understanding, developing, and advancing the next generation of system-level artificial intelligence.
  arXiv  Detail & Related papers  (2025-06-05T02:34:43Z)
• TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems [2.462408812529728]
  This review presents a structured analysis of textbfTrust, Risk, and Security Management (TRiSM) in the context of LLM-based Agentic Multi-Agent Systems (AMAS)<n>We begin by examining the conceptual foundations of Agentic AI and highlight its architectural distinctions from traditional AI agents.<n>We then adapt and extend the AI TRiSM framework for Agentic AI, structured around four key pillars: Explainability, ModelOps, Security, Privacy and Governance.
  arXiv  Detail & Related papers  (2025-06-04T16:26:11Z)
• InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation [63.55258191625131]
  InfoDeepSeek is a new benchmark for assessing agentic information seeking in real-world, dynamic web environments.<n>We propose a systematic methodology for constructing challenging queries satisfying the criteria of determinacy, difficulty, and diversity.<n>We develop the first evaluation framework tailored to dynamic agentic information seeking, including fine-grained metrics about the accuracy, utility, and compactness of information seeking outcomes.
  arXiv  Detail & Related papers  (2025-05-21T14:44:40Z)
• AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges [0.36868085124383626]
  This study critically distinguishes between AI Agents and Agentic AI, offering a structured conceptual taxonomy, application mapping, and challenge analysis.<n>Generative AI is positioned as a precursor, with AI Agents advancing through tool integration, prompt engineering, and reasoning enhancements.<n>Agentic AI systems represent a paradigmatic shift marked by multi-agent collaboration, dynamic task decomposition, persistent memory, and orchestrated autonomy.
  arXiv  Detail & Related papers  (2025-05-15T16:21:33Z)
• From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review [1.4929298667651645]
  We present a comparison of benchmarks developed between 2019 and 2025 that evaluate large language models and autonomous AI agents.<n>We propose a taxonomy of approximately 60 benchmarks that cover knowledge reasoning, mathematical problem-solving, code generation and software engineering, factual grounding and retrieval, domain-specific evaluations, multimodal and embodied tasks, task orchestration, and interactive assessments.<n>We present real-world applications of autonomous AI agents in materials science, biomedical research, academic ideation, software engineering, synthetic data generation, mathematical problem-solving, geographic information systems, multimedia, healthcare, and finance.
  arXiv  Detail & Related papers  (2025-04-28T11:08:22Z)
• A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems [93.8285345915925]
  Reasoning is a fundamental cognitive process that enables logical inference, problem-solving, and decision-making.<n>With the rapid advancement of large language models (LLMs), reasoning has emerged as a key capability that distinguishes advanced AI systems.<n>We categorize existing methods along two dimensions: (1) Regimes, which define the stage at which reasoning is achieved; and (2) Architectures, which determine the components involved in the reasoning process.
  arXiv  Detail & Related papers  (2025-04-12T01:27:49Z)
• MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents [59.825725526176655]
  Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents.<n>Existing benchmarks either focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination and competition.<n>We introduce MultiAgentBench, a benchmark designed to evaluate LLM-based multi-agent systems across diverse, interactive scenarios.
  arXiv  Detail & Related papers  (2025-03-03T05:18:50Z)
• Multi-Agent Risks from Advanced AI [90.74347101431474]
  Multi-agent systems of advanced AI pose novel and under-explored risks.<n>We identify three key failure modes based on agents' incentives, as well as seven key risk factors.<n>We highlight several important instances of each risk, as well as promising directions to help mitigate them.
  arXiv  Detail & Related papers  (2025-02-19T23:03:21Z)
• Survey on AI-Generated Media Detection: From Non-MLLM to MLLM [51.91311158085973]
  Methods for detecting AI-generated media have evolved rapidly.<n>General-purpose detectors based on MLLMs integrate authenticity verification, explainability, and localization capabilities.<n>Ethical and security considerations have emerged as critical global concerns.
  arXiv  Detail & Related papers  (2025-02-07T12:18:20Z)
• Agent-as-a-Judge: Evaluate Agents with Agents [61.33974108405561]
  We introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We present DevAI, a new benchmark of 55 realistic automated AI development tasks.
  arXiv  Detail & Related papers  (2024-10-14T17:57:02Z)
• Position Paper: Agent AI Towards a Holistic Intelligence [53.35971598180146]
  We emphasize developing Agent AI -- an embodied system that integrates large foundation models into agent actions. In this paper, we propose a novel large action model to achieve embodied intelligent behavior, the Agent Foundation Model.
  arXiv  Detail & Related papers  (2024-02-28T16:09:56Z)
• Large Multimodal Agents: A Survey [78.81459893884737]
  Large language models (LLMs) have achieved superior performance in powering text-based AI agents. There is an emerging research trend focused on extending these LLM-powered AI agents into the multimodal domain. This review aims to provide valuable insights and guidelines for future research in this rapidly evolving field.
  arXiv  Detail & Related papers  (2024-02-23T06:04:23Z)
• A Survey on Context-Aware Multi-Agent Systems: Techniques, Challenges and Future Directions [1.0488897291370285]
  Research interest in autonomous agents is on the rise as an emerging topic.<n>The challenge lies in enabling these agents to learn, reason, and navigate uncertainties in dynamic environments.<n>Context awareness emerges as a pivotal element in fortifying multi-agent systems.
  arXiv  Detail & Related papers  (2024-02-03T00:27:22Z)
• Measuring Value Alignment [12.696227679697493]
  This paper introduces a novel formalism to quantify the alignment between AI systems and human values. By utilizing this formalism, AI developers and ethicists can better design and evaluate AI systems to ensure they operate in harmony with human values.
  arXiv  Detail & Related papers  (2023-12-23T12:30:06Z)
• Heterogeneous Value Alignment Evaluation for Large Language Models [91.96728871418]
  Large Language Models (LLMs) have made it crucial to align their values with those of humans. We propose a Heterogeneous Value Alignment Evaluation (HVAE) system to assess the success of aligning LLMs with heterogeneous values.
  arXiv  Detail & Related papers  (2023-05-26T02:34:20Z)

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.