arXiv:2606. 02282v1 Announce Type: new Abstract: Orchestrating Large Language Models into Multi-Agent Systems (LLM-MAS) has unlocked remarkable reasoning capabilities, yet emergent failures and hallucinations that resist characterisation block their deployment in safety-critical domains -- a gap made legally untenable by emerging AI regulation.
arXiv:2608.22160v1 Announce Type: new Abstract: Physical automation is scaling toward fleets of embodied machines commanded by an AI brain. Early deployments already run factories and warehouses at p...
EDGE is a framework that attributes multiple related errors in multi-agent large language model systems by constructing an error dependency graph from observed error events. It validates a reliable causal subset through counterfactual rollout and uses this inference graph to guide a two-stage LLM-as-judge detector for error attribution. Experiments on TRAIL and MAST demonstrate that EDGE improves category-level multi-error attribution across most models and settings, and that the graph aids explanation and repair analysis.
arXiv:2606. 00765v1 Announce Type: new Abstract: LLM-based agents increasingly solve complex tasks through long trajectories involving reasoning steps, tool calls, and inter-agent communication.
The paper introduces Adaptive Influence Graphs (AIGs), a two‑stage framework that first converts a failed trace into a structured graph and then navigates it to pinpoint the critical error in multi‑agent large language model systems. Experiments across multiple models demonstrate that richer trace representations and adaptive graph construction improve failure attribution, with AIGs achieving state‑of‑the‑art results on the Who&When benchmark. The study shows that both the diagnosing model and the way traces are represented and explored are crucial for accurate failure attribution.
The paper introduces DCFA, a training‑free framework for attributing failures in large language model‑based multi‑agent systems. DCFA uses a global module to build causal‑inspired dependency graphs from system traces, pinpointing the earliest decisive error, and a local module that refines this attribution through counterfactual reasoning. Experiments on the Who&When benchmark across six LLMs demonstrate that DCFA improves step‑level accuracy by up to 8.27% over existing baselines.
arXiv:2606. 09071v1 Announce Type: new Abstract: Large language model (LLM) agents now solve complex tasks through long plan-and-execution traces, yet the ability to locate errors in a completed traces still lags far behind, especially in the \emph{silent failure} regime.
Large language model (LLM) agents are increasingly evaluated on their ability to use tools, plan multi-step tasks, coordinate with other agents, and operate over extended horizons. Reported benchmark gains often obscure recurring failure modes documented across otherwise unrelated evaluation efforts.
arXiv:2606. 01365v1 Announce Type: new Abstract: Tool-using multi-agent large language model (LLM) systems spend computation through model tokens, tool calls, retries, and code execution before producing an answer.
CockpitHAT is a hierarchical attribution framework for embodied multi‑agent systems that replaces positional windows with dependency‑distance thresholds derived from interaction DAGs, incorporates multi‑channel evidence through an embodied adapter, and applies a safety‑uplift to high‑risk failures during confidence‑weighted analyst consensus. The authors also release CockpitBench, a benchmark of 212 annotated failure traces labeled with ISO 26262 ASIL severity. On both the public Who&When benchmark and CockpitBench, CockpitHAT outperforms the text‑only state‑of‑the‑art ECHO, achieving higher agent‑level and step‑exact accuracies across multiple splits.
arXiv:2606. 04990v2 Announce Type: replace-cross Abstract: Large language model (LLM)-based agents are evolving from passive text generators into autonomous systems capable of planning, tool use, retrieval, memory access, environmental interaction, and multi-agent collaboration.
DeFA is a dependency-guided framework that attributes failures in large language model agents by constructing an event dependency graph and a failure propagation graph from protocol relations and semantic dependencies. It identifies violating events, traces their sources and effects, and determines the decisive error, responsible agent, and error category. The method supports long trajectories through segmentation and has shown superior accuracy on text, image, and video tasks, while its diagnostic feedback can improve agent performance on subsequent tasks.