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 Canonical reference
Generative agents: Interactive simulacra of human behavior
Canonical reference. 100% of citing Pith papers cite this work as background.
20
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 9
citation-polarity summary
roles
background 9polarities
background 9representative citing papers
SMMBench is a benchmark evaluating multimodal agents on cross-source reasoning, conflict resolution, preference reasoning, and action prediction, showing current systems struggle with evidence distributed across heterogeneous sources.
MemDocAgent generates consistent hierarchical repository-level code documentation by combining dependency-aware traversal with memory-guided agent interactions that accumulate work traces.
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
SkillGuard extracts executable environment contracts from LLM skill documents to detect only relevant drifts, reporting zero false positives on 599 cases, 100% precision in known-drift tests, and raising one-round repair success from 10% to 78%.
SalesSim benchmarks MLLMs as retail user simulators, finds gaps in persona adherence and over-persuasion, and introduces UserGRPO RL to raise decision alignment by 13.8%.
Introduces OmniBehavior benchmark from real-world data and shows LLMs exhibit hyper-activity, persona homogenization, and utopian bias in behavior simulation.
DecentMem is a decentralized dual-pool memory framework for self-evolving multi-agent systems that provides O(log T) regret guarantees and yields up to 23.8% accuracy gains over centralized baselines.
MementoGUI introduces a modular memory-control framework with working and episodic memory operators that improves long-horizon GUI agent performance over history-replay and text-only baselines.
PrivacySIM shows that conditioning LLMs on user personas like demographics and attitudes improves simulation of privacy choices but reaches only 40.4% accuracy against real responses from 1,000 users.
Agentic memory improves clean reasoning but worsens performance when spurious patterns are present in stored trajectories; CAMEL calibration reduces this reliance while preserving clean performance.
LLM agent societies develop power-law coordination cascades and intellectual elites through an integration bottleneck that grows with system size.
Robo-Cortex proposes a self-evolving embodied navigation agent using dual-grain cognitive memory and autonomous knowledge induction from trajectories, reporting SPL gains on IGNav, AR, AEQA and preliminary real-robot tests.
LAR learns a compact latent action space from trajectories that shortens the effective decision horizon for LLM agents, reducing token count and inference time while preserving task success.
Bian Que is an agentic framework using a unified operational paradigm, flexible Skill Arrangement, and self-evolving mechanism to automate O&M tasks, achieving 75% alert reduction and over 50% MTTR cut in production deployment.
Evo-MedAgent adds three evolving memory stores to LLM agents for chest X-ray diagnosis, raising MCQ accuracy from 0.68 to 0.79 on GPT-5-mini and 0.76 to 0.87 on Gemini-3 Flash without any training.
Global Workspace Agents (GWA) is proposed as an active, event-driven cognitive architecture for LLMs featuring an entropy-based intrinsic drive and dual-layer memory to enable sustained self-directed agency.
Explicit provenance across the full agentic AI lifecycle is the necessary condition for making responsibility computable and actionable.
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.
-
SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory
SMMBench is a benchmark evaluating multimodal agents on cross-source reasoning, conflict resolution, preference reasoning, and action prediction, showing current systems struggle with evidence distributed across heterogeneous sources.
-
Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation
MemDocAgent generates consistent hierarchical repository-level code documentation by combining dependency-aware traversal with memory-guided agent interactions that accumulate work traces.
-
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
-
Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
SkillGuard extracts executable environment contracts from LLM skill documents to detect only relevant drifts, reporting zero false positives on 599 cases, 100% precision in known-drift tests, and raising one-round repair success from 10% to 78%.
-
SalesSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators
SalesSim benchmarks MLLMs as retail user simulators, finds gaps in persona adherence and over-persuasion, and introduces UserGRPO RL to raise decision alignment by 13.8%.
-
Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
Introduces OmniBehavior benchmark from real-world data and shows LLMs exhibit hyper-activity, persona homogenization, and utopian bias in behavior simulation.
-
Self-Evolving Multi-Agent Systems via Decentralized Memory
DecentMem is a decentralized dual-pool memory framework for self-evolving multi-agent systems that provides O(log T) regret guarantees and yields up to 23.8% accuracy gains over centralized baselines.
-
MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents
MementoGUI introduces a modular memory-control framework with working and episodic memory operators that improves long-horizon GUI agent performance over history-replay and text-only baselines.
-
PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior
PrivacySIM shows that conditioning LLMs on user personas like demographics and attitudes improves simulation of privacy choices but reaches only 40.4% accuracy against real responses from 1,000 users.
-
The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory
Agentic memory improves clean reasoning but worsens performance when spurious patterns are present in stored trajectories; CAMEL calibration reduces this reliance while preserving clean performance.
-
Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems
LLM agent societies develop power-law coordination cascades and intellectual elites through an integration bottleneck that grows with system size.
-
Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction
Robo-Cortex proposes a self-evolving embodied navigation agent using dual-grain cognitive memory and autonomous knowledge induction from trajectories, reporting SPL gains on IGNav, AR, AEQA and preliminary real-robot tests.
-
Latent Action Reparameterization for Efficient Agent Inference
LAR learns a compact latent action space from trajectories that shortens the effective decision horizon for LLM agents, reducing token count and inference time while preserving task success.
-
Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations
Bian Que is an agentic framework using a unified operational paradigm, flexible Skill Arrangement, and self-evolving mechanism to automate O&M tasks, achieving 75% alert reduction and over 50% MTTR cut in production deployment.
-
Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve
Evo-MedAgent adds three evolving memory stores to LLM agents for chest X-ray diagnosis, raising MCQ accuracy from 0.68 to 0.79 on GPT-5-mini and 0.76 to 0.87 on Gemini-3 Flash without any training.
-
"Theater of Mind" for LLMs: A Cognitive Architecture Based on Global Workspace Theory
Global Workspace Agents (GWA) is proposed as an active, event-driven cognitive architecture for LLMs featuring an entropy-based intrinsic drive and dual-layer memory to enable sustained self-directed agency.
-
Responsible Agentic AI Requires Explicit Provenance
Explicit provenance across the full agentic AI lifecycle is the necessary condition for making responsibility computable and actionable.
- Benchmarking LLMs for Community Governance Simulation with Life-history Narratives
- CogniFold: Always-On Proactive Memory via Cognitive Folding