NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
505 results for “keyword:"multi agent syste"” in ICLR 2027. 132 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Which Graph Is Safest? Predicting Adversarial Capture of LLM Agent Groups from Local Kernels▼4.3k2.00
[PDF]From Market Facts to Executable Markets: Grounding Heterogeneous Trader Populations in Empirical Market Evidence▼4.3k2.00
[PDF]Agent Forest: Controlled Complexity Growth for RL Environments via a Multi-Agent Orchestration System▼1.2k1.67
[PDF]Disentangling Agent Contribution in LLM Multi-Agent Systems through Controlled Interventions▲5.4k3.00
[PDF]Training-Free Failure Attribution in Multi-Agent Systems via Structured Trajectory Diagnosis▼1361.33
[PDF]Bridging Scientific Goals and AI Execution: A Multi-Agent Framework with Hierarchical Self-Evolution▼1361.33
[PDF]MemPermit: Governing Writes to Multi-Agent Shared Memory via Risk-Constrained Sequential Verification▼1.2k1.67
[PDF]Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems▼5.8k2.33
[PDF]Communication as Evidence Routing: Adaptive Relational Graphs via Optimal Transport for Multi-Agent LLM Reasoning▲13k2.33
[PDF]AdaFleet: An Adaptive Orchestrator–Subagent Coevolution Framework for Efficient Quantitative Signal Discovery▼4.3k2.00
[PDF]Knowing When to Stop: IGP-Bench and the Multi-Agent System GALOIS for the Inverse Galois Problem▼4.3k2.00
[PDF]PatMask: Pluggable Adversarial Topology Masking for Multi-Agent Reinforcement Learning under Communication Disconnection▼5.8k2.33
[PDF]Deep Cognition: A Transparent, Fine-Grained Multi-Agent Deep Research System for Human-Agent Collaboration▼4.3k2.00
[PDF]HG-MAQG: Heterogeneous Graph Constrained Multi-Agent System For Personalized Question Generation▼4.3k2.00
[PDF]Emergent Trading Biases in LLM Agent Swarms: Behavioral-Finance Benchmarks and Information-Channel Ablation▼4.3k2.00
[PDF]Auditing the Auditors: Validating Automatic Evaluation in Multi-Model LLM Consensus Systems▼1361.33
[PDF]Quantize the Team: Joint Quantization and Topology Adaptation for Multi-Agent LLM Systems▼1.2k1.67
Withdrawn or desk rejected (132)
[PDF]Multilingual Latent Representation Distortion Drives Generative Drift and Bounds Latent-Channel Communication CapacityWithdrawn2.00
[PDF]Stateful Search with Stateless Agents: Scaling Long-Horizon Automated ResearchDesk rejected3.00
[PDF]SHAPE: Learning to Search with an Evolving Harness for Target-Binding Antimicrobial Peptide DesignDesk rejected