HalluProp, a Propagation-aware Hallucination inference framework that estimates individual agent failures and emergent system-level hallucination risks before inter-agent interaction, and effectively complements post-hoc methods, highlighting the potential of pre-hoc risk inference for building more reliable multi-agent systems.
Abstract
LLM-based multi-agent systems (MAS) have exhibited remarkable capabilities in collaborative reasoning and decision-making, yet their interconnected communications introduce new systemic risk: localized hallucinations can propagate along agent communication chain, amplify through interactions, and ultimately trigger cascading failures. Existing countermeasures predominantly follow a post-hoc paradigm, identifying failures only after unsafe behaviors emerge, by which time harmful effects may have already spread throughout the agent network. To tackle this problem, we investigate a complementary pre-hoc approach and propose HalluProp, a Propagation-aware Hallucination inference framework that estimates individual agent failures and emergent system-level hallucination risks before inter-agent interaction. First, we model intrinsic hallucination risks by identifying fine-grained semantic misalignment between agent roles and task queries. We then characterize inter-agent risk propagation by modeling both semantic influence and communication topology. Finally, we integrate these two risks via a differentiable Noisy-OR inference mechanism to derive a systemic diagnosis. Extensive experiments show that HalluProp accurately localizes faulty agents, achieving an average AUROC of 84.6%, while enabling sub-second diagnosis with over $65\times$ speedup over post-hoc methods. By facilitating early intervention through upstream screening, HalluProp effectively complements post-hoc methods, highlighting the potential of pre-hoc risk inference for building more reliable multi-agent 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
ForesightSafety-TIDE, a controlled evaluation framework that strictly pairs all-honest collaboration with controlled deception by a key evidence holder and analyzes the aggregation process through multi-stage voting, testimony adoption, and evidence-root lineage propagation, reveals both the fragility of distributed fact recovery and its underlying mechanism.
Chen Yan, Zeyang Yue, Feifei Zhao et al.· 0 citations
AFANet is introduced, a lightweight graph-based framework that models interaction trajectories through step-level semantic signals and agent-level relationships and suggests that effective agent failure attribution does not require heavy LLM reasoning and a lightweight, structured approach can achieve strong performance.
Ting-Wei Li, Yuanchen Bei, Xiao Lin et al.· 0 citations
PropUQ-MAS is proposed, 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.
Yaokun Liu, Yifan Liu, D. Zhang et al.· 0 citations
Multi-agent systems powered by large language models (LLMs) have demonstrated potential for collaborative problem-solving, yet increasing the number of agents often introduces redundant reasoning and communication overhead, sometimes degrading performance. We propose AgentDropout, a dynamic strategy inspired by dropout regularization in neural networks, which selectively deactivates low-contribution agents during multi-agent collaboration. At each round of discussion, AgentDropout computes a semantic novelty score for every agent by measuring the divergence of its output relative to the current group consensus. Agents whose novelty score falls below an adaptive threshold are temporarily deactivated, reducing token consumption without sacrificing viewpoint diversity. We evaluate AgentDropout on mathematical reasoning (GSM8K), commonsense reasoning (StrategyQA), and collaborative code generation (HumanEval) tasks. Across three independent runs, AgentDropout achieves accuracy comparable to or modestly above fixed 5-agent debate while reducing total token consumption by 38.0–43.5% and debate rounds by 20.5% on average. Pareto analysis reveals a promising efficiency–quality trade-off, suggesting that dynamic agent deactivation may be useful for deploying multi-agent LLM systems under computational budget constraints.
Zhengxi Xiao, Qi Guo, Yuyue Wang et al.· 2026 8th International Confe...· 1 citation
Exploration is essential for reliable autonomy in multi-agent systems, yet it remains unclear whether large language model (LLM) agents can explore effectively when interacting with one another. We show that modern LLM agents fail to do so, often exhibiting myopic and polarized interaction patterns that lead to suboptimal coordination and increased regret. We formalize this challenge as the Multi-Agent Exploration problem, modeling it as a partially observable stochastic game (POSG) problem in which agents must probe peers to infer their capabilities and identify effective interaction strategies. To address this, we introduce Multi- Agent Contextual Exploration (MACE), a lightweight framework that explicitly promotes exploration through structured peer selection. Across both contextual and parametric diversity settings, MACE substantially improves exploration behavior and downstream task performance. We further show theoretically that the value of exploration increases with agent diversity. Overall, our results highlight a fundamental limitation of current LLM agents and underscore the importance of explicitly guided exploration for reliable multi-agent autonomy. Code will be released in https://github.com/deeplearning-wisc/mace
Hyeong Kyu Choi, Jiatong Li, Wendi Li et al.· 1 citation