A semantic-uncertainty-guided orchestration approach, HASSUM is introduced as a general framework for uncertainty-aware coordination in multi-agent systems and suggests that semantic uncertainty is a practical and general-purpose signal for improving robustness and trustworthiness in agentic AI systems.
Abstract
As large language model (LLM)-based multi-agent systems become increasingly capable, coordinating agents under uncertainty becomes a fundamental challenge. Existing orchestration strategies typically rely on fixed interaction patterns and often lack mechanisms for assessing the reliability of intermediate reasoning steps, allowing errors and hallucinations to propagate through the system. This paper introduces a semantic-uncertainty-guided orchestration approach, HASSUM as a general framework for uncertainty-aware coordination in multi-agent systems. The method estimates uncertainty using semantic entropy and semantic density, which measure trust at the level of answer semantics rather than output probabilities. These signals enable adaptive orchestration decisions, including output verification, selective reprompting, additional deliberation, and confidence-aware response selection. Because the approach operates independently of any particular agent architecture, it can be integrated into a broad range of hierarchical and collaborative multi-agent systems. The evaluations demonstrate an implementation within a hierarchical agent framework and evaluate it on StrategyQA, JailbreakBench, and TruthfulQA benchmarks. Across tasks that require complex reasoning and are prone to ambiguity or hallucinations, uncertainty-guided orchestration yields more reliable outcomes than uncertainty-unaware coordination. Semantic entropy and semantic density in tandem outperformed either metric alone. Ablations testing different thresholds and model sizes demonstrated that both influence the effectiveness of semantic metrics. The results suggest that semantic uncertainty is a practical and general-purpose signal for improving robustness and trustworthiness in agentic AI systems.
Experimental results show that AgentLocate consistently outperforms existing failure localization methods in identifying both responsible agents and failure steps, while remaining efficient in terms of token usage and running time.
Yu Xia, Anjun Gao, Yueyang Quan et al.· 0 citations
Power-system decision support increasingly requires the joint interpretation of heterogeneous information sources, including real-time measurements, topology states, alarm logs, operating rules, dispatch instructions, and historical restoration cases. Existing LLM-based approaches remain limited in such settings because their reasoning is often weakly grounded in power-domain knowledge and difficult to verify under physical and procedural constraints. To address this issue, we propose a knowledge-enhanced LLM framework for power semantic understanding and multi-agent decision learning. The framework first organizes heterogeneous grid information into a dynamic semantic graph, then performs graph-grounded semantic understanding, translates the inferred semantics into an executable task graph for hierarchical multi-agent collaboration, and finally applies safety-constrained verification with evidence tracing before action execution. Experiments on Grid2Op/L2RPN WCCI 2022, SMART-DS, RTS-GMLC, and PowerGym show that the proposed framework consistently improves semantic grounding accuracy, restoration quality, and feasible-decision rate over rule-based, text-centric RAG, and graph-retrieval multi-agent baselines, while exhibiting stronger robustness under partial observation. These results indicate that explicit semantic grounding and safety-aware collaborative reasoning are both necessary for reliable LLM-assisted power-system decision support.
Yunfeng Zou, Ming Li, Yueqiang Li et al.· International journal of pat...· 0 citations
LLM-based multi-agent systems (MAS) solve complex tasks through communication among role-specialized agents. However, inter-agent dependencies introduce reliability risks beyond isolated agent failures. For instance, errors in intermediate messages could be inherited and amplified by downstream agents. Existing uncertainty quantification (UQ) methods mainly target isolated responses or single-agent reasoning, and therefore fail to capture uncertainty propagation in MAS. To this end, we propose PropUQ-MAS, an error propagation-aware UQ framework that represents MAS execution as a communication-structured graph and estimates each step's reliability by combining local uncertainty with uncertainty inherited from upstream messages. Extensive experiments demonstrate that PropUQ-MAS consistently improves UQ in MAS, with average relative gains of +6.10% in AUROC and +47.58% in PRR.
Yaokun Liu, Yifan Liu, D. Zhang et al.· 0 citations
Large Language Model (LLM)–based agents are rapidly evolving from passive assistants into autonomous, tool-using, and collaborative systems capable of executing complex, long-horizon tasks across web, software, and physical environments. However, the current literature remains fragmented, with inconsistent terminology, ad hoc architectures, and limited evaluation standards, making it difficult to compare systems or deploy them reliably in real-world settings. This paper presents a unified, taxonomy-driven, and deployment-oriented survey of agentic AI systems, synthesizing recent advances through a modular reference architecture and a four-dimensional taxonomy that characterizes agents along the axes of autonomy, tool use, collaboration, and safety–governance. We systematically analyze representative single-agent, tool-augmented, and multi-agent frameworks within this taxonomy, highlighting design trade-offs, capability scaling patterns, and recurring failure modes. Beyond architectural analysis, we review emerging evaluation methodologies that move beyond static benchmarks to assess agent behavior, robustness, grounding, and operational cost in interactive environments. Importantly, the survey emphasizes practical considerations for enterprise and safety-critical deployment, including access control, human-in-the-loop oversight, and policy enforcement. By unifying conceptual foundations with empirical trends and deployment constraints, this work provides a structured roadmap for researchers and practitioners to design, evaluate, and govern next-generation LLM-based agentic systems.
Sparsh Bajoria, Shreyanshu Ranjan, Adhitya M et al.· Cognitive Computation· 0 citations
Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents. However, most existing systems primarily optimize task success while giving limited consideration to execution efficiency under practical constraints such as executor capability and computational cost. Existing router-based methods have limited ability to reason over rich, evolving task contexts, multi-step dependencies, and intermediate execution feedback, and often generalize poorly to unseen executors. We propose EASy, a trainable agentic framework that jointly optimizes task performance and computational efficiency through reinforcement learning. EASy equips an LLM-based orchestrator with explicit knowledge of the capability and cost profiles of heterogeneous executors, enabling context-sensitive coordination beyond performance-only routing. It further introduces a milestone-plan-act workflow that decomposes complex tasks into manageable milestones, constructs dependency-aware execution graphs, assigns suitable executors, and parallelizes independent steps while adapting subsequent decisions to intermediate outcomes. To train the orchestrator, we develop a tree-structured rollout procedure that explores alternative milestone decompositions and execution plans, together with multi-component rewards that capture task correctness, execution efficiency, and trajectory completeness. Extensive experiments on mathematical reasoning, embodied decision-making, and deep research benchmarks show that EASy consistently achieves stronger performance-efficiency trade-offs than strong agentic baselines.
Junnan Liu, Linhao Luo, Thuy-Trang Vu et al.· 0 citations
Large Language Model (LLM) applications increasingly rely on multi-agent and retrieval-augmented generation (RAG) architectures to solve complex, knowledge-intensive tasks. However, when deployed as generic platforms serving multiple customers and heterogeneous user groups, existing systems often rely on agent-level routing and prompt hardcoding, leading to poor modularity, limited reuse, and weak controllability. In particular, current approaches lack an explicit abstraction for modeling system capabilities and controlling which capabilities are accessible to different users. We propose an expert-guided multi-agent architecture that separates execution from capability modeling. Agents are responsible for LLM interaction and tool execution, while experts represent indivisible business or task capabilities and guide agent orchestration through dynamic prompt injection. This design enables a generic, multi-instance system in which different customer deployments and user groups share the same agent implementations while exposing different capability sets at the business level. The architecture enforces strong guarantees in terms of answerability, traceability, and controllability. A first working implementation has been developed, and an open-source release is currently in preparation.
Ying Zhang, M. Guillaume, Edouard Leleux et al.· 2026 6th International Confe...· 0 citations