The paper presents a taxonomy of communication failures in multi-agent large language model systems, derived from 3,211 failed multi-round trajectories across diverse domains such as medical QA, coding, finance, multi-hop reasoning, ethics, and embodied text tasks. It analyzes how failures arise, noting that they are largely driven by recovery/correction and consensus/decision issues rather than isolated first-round errors, and highlights patterns like early convergence, minority-signal suppression, and wrong framing persistence. The authors recommend stronger disagreement handling, evidence verification, minority-signal preservation, and recovery checks before finalizing decisions.
arXiv:2609.36855v1 Announce Type: new Abstract: Multi-agent LLM systems rely on message passing among specialized agents to accomplish complex tasks. However, an upstream agent may provide useful inf...
The paper introduces Independent–Communicate–Revise (ICR), a framework that isolates communication effects in large language model multi‑agent systems by fixing initial reasoning and measuring how messages influence answer revision. ICR evaluates correction, preservation, and selectivity across four reasoning benchmarks, revealing that similar overall accuracy can mask divergent revision behaviors. The study shows that richer messages can both improve and harm outcomes, and that receiver policies can shift preservation and correction dynamics differently across tasks.
The Agent Error Dataset (AED) presents 50,228 error–diagnosis pairs collected from 9,961 source tasks across 33 environments, 19 harness families, and 23 policy models in text‑based agent systems. A five‑stage Agentic Error‑to‑Training (AET) pipeline generates diagnoses and proposed corrections, verifies them against recorded evidence, and creates separate training views for diagnosis and actor recovery. Experiments show that first‑proposal corrections improve verifier pass rates from 18.4% to 51.1%, and fine‑tuning with full‑diagnosis data raises Qwen3‑8B’s exact‑step agreement from 47.2% to 63.6% on a holdout set.
arXiv:2610.16117v2 Announce Type: new Abstract: LLM-based multi-agent collaboration is increasingly used to solve complex tasks by dividing work among specialized agents and integrating complementary...
arXiv:2607. 07989v1 Announce Type: cross Abstract: Large language model (LLM) based multi-agent systems enable complex problem solving through coordinated reasoning and action, but their distributed structure also introduces new challenges in diagnosing system-level failures.
arXiv:2608.25920v2 Announce Type: replace Abstract: As large language model (LLM)-based multi-agent systems (MASs) are increasingly applied to long-horizon complex tasks, their reliability has emerge...
arXiv:2611.07140v1 Announce Type: cross Abstract: Teams increasingly build software from cooperating large language model (LLM) agents, often assuming more agents mean more reliability. Yet the usual...
arXiv:2607. 09996v1 Announce Type: new Abstract: Automated failure attribution uses LLMs to identify where and why agentic systems fail.
The paper investigates automated failure attribution (AFA) in large language model (LLM)-based agentic systems, where multiple agents collaborate on complex tasks. It finds that LLMs contain sufficient internal knowledge to attribute failures but often fail to output the correct step, revealing a knows‑but‑won’t‑say gap. To address this, the authors introduce grafting—a manual intervention that leverages latent model knowledge—showing it consistently outperforms direct prompting across several LLMs and benchmarks.
arXiv:2608.29228v1 Announce Type: new Abstract: Failures in agentic AI systems can arise from interactions among messages exchanged by multiple large language model (LLM) agents. Pointwise attributio...
The study evaluates how large language model agents maintain consistency over extended interactions by simulating a 20‑step delayed‑gratification task. Researchers ran 84,540 trajectories across eight model families, using survival analysis to track when agents first claim a reward and discrete‑time hazard regression to assess how factors like social visibility, persona stressors, and deliberation policy affect failure risk. They also developed a seven‑category taxonomy from 13,780 deliberation traces, revealing that early failures are impulse‑driven, later ones are fatigue‑ or cost‑benefit‑framed, and public settings elicit norm‑oriented justifications; longer deliberation correlates with higher intra‑rationale contradictions, challenging assumptions about reasoning depth and consistency.
arXiv:2610.15459v1 Announce Type: cross Abstract: LLM-based multi-agent systems (LLM-MAS) use specialized agents that exchange messages to accomplish complex tasks. Their reliance on networked protoc...