The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
hub
arXiv preprint arXiv:2411.04468 , year=
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
SDP constructs a task-induced state space from raw text by having agents commit to and certify natural-language predicates as states, enabling structured planning and analysis in unstructured language environments.
LC-MAPF uses multi-round local communication between neighboring agents in a pre-trained model to outperform prior learning-based MAPF solvers on diverse unseen scenarios while preserving scalability.
OMC framework turns multi-agent AI into self-organizing companies with Talents, Talent Market, and E²R search, achieving 84.67% success on PRDBench (15.48 points above prior art).
Open 4B and 8B visual web agents achieve state-of-the-art results on browser benchmarks by predicting actions from screenshots and instructions, outperforming similar open models and some closed larger-model agents, with full release of data and code planned.
Evo-Memory is a new benchmark for self-evolving memory in LLM agents across task streams, with baseline ExpRAG and proposed ReMem method that integrates reasoning, actions, and memory updates for continual improvement.
AgentCollabBench shows that multi-agent reliability is limited by communication topology, with converging-DAG nodes causing synthesis bottlenecks that discard constraints and explain 7-40% of information loss variance.
Agent workflows can diverge substantially from contaminated inputs yet recover correct answers, or stay similar while failing, as measured by trace divergence on GAIA tasks.
BONSAI introduces a four-layer architecture and four-phase workflow for human-AI co-development of visual analytics applications, shown in case studies to enable efficient novel tool creation and reconstruction from paper descriptions.
Introduces harm recovery as a post-execution safeguard for computer-use agents, operationalized via a human-preference rubric, reward model, and BackBench benchmark that shows improved recovery trajectories.
CADMAS-CTX replaces static skill profiles with context-conditioned Beta posteriors and uncertainty-penalized routing, yielding higher accuracy on GAIA (0.442) and SWE-bench (31.4%) than static baselines.
A single transformer model trained offline on expert trajectories from three distinct MARL environments achieves competitive performance against specialized baselines without per-task tuning.
RGAO combines retrieval-based complexity assessment with a formal budget algebra to enable dynamic topology selection in multi-agent code generation with provable conservation.
AssemPlanner is a ReAct-based multi-agent system that autonomously generates production plans from natural language inputs by integrating scheduling, knowledge, line balancing, and scene graph feedback.
citing papers explorer
-
Why Do Multi-Agent LLM Systems Fail?
The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
-
State-Centric Decision Process
SDP constructs a task-induced state space from raw text by having agents commit to and certify natural-language predicates as states, enabling structured planning and analysis in unstructured language environments.
-
Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding
LC-MAPF uses multi-round local communication between neighboring agents in a pre-trained model to outperform prior learning-based MAPF solvers on diverse unseen scenarios while preserving scalability.
-
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
OMC framework turns multi-agent AI into self-organizing companies with Talents, Talent Market, and E²R search, achieving 84.67% success on PRDBench (15.48 points above prior art).
-
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
Open 4B and 8B visual web agents achieve state-of-the-art results on browser benchmarks by predicting actions from screenshots and instructions, outperforming similar open models and some closed larger-model agents, with full release of data and code planned.
-
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
Evo-Memory is a new benchmark for self-evolving memory in LLM agents across task streams, with baseline ExpRAG and proposed ReMem method that integrates reasoning, actions, and memory updates for continual improvement.
-
AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
AgentCollabBench shows that multi-agent reliability is limited by communication topology, with converging-DAG nodes causing synthesis bottlenecks that discard constraints and explain 7-40% of information loss variance.
-
Trace-Level Analysis of Information Contamination in Multi-Agent Systems
Agent workflows can diverge substantially from contaminated inputs yet recover correct answers, or stay similar while failing, as measured by trace divergence on GAIA tasks.
-
BONSAI: A Mixed-Initiative Workspace for Human-AI Co-Development of Visual Analytics Applications
BONSAI introduces a four-layer architecture and four-phase workflow for human-AI co-development of visual analytics applications, shown in case studies to enable efficient novel tool creation and reconstruction from paper descriptions.
-
Human-Guided Harm Recovery for Computer Use Agents
Introduces harm recovery as a post-execution safeguard for computer-use agents, operationalized via a human-preference rubric, reward model, and BackBench benchmark that shows improved recovery trajectories.
-
CADMAS-CTX: Contextual Capability Calibration for Multi-Agent Delegation
CADMAS-CTX replaces static skill profiles with context-conditioned Beta posteriors and uncertainty-penalized routing, yielding higher accuracy on GAIA (0.442) and SWE-bench (31.4%) than static baselines.
-
MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning
A single transformer model trained offline on expert trajectories from three distinct MARL environments achieves competitive performance against specialized baselines without per-task tuning.
-
Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation
RGAO combines retrieval-based complexity assessment with a formal budget algebra to enable dynamic topology selection in multi-agent code generation with provable conservation.
-
AssemPlanner: A Multi-Agent Based Task Planning Framework for Flexible Assembly System
AssemPlanner is a ReAct-based multi-agent system that autonomously generates production plans from natural language inputs by integrating scheduling, knowledge, line balancing, and scene graph feedback.
- MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signals