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
514 results for “keyword:"agent systems"” in ICLR 2027. 134 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]GeneralsArena: Evaluating End-to-End Agent Systems through Persistent Real-Time Competition▲3.0k2.33
[PDF]Show or Stow: Learning Evidence Admission from Stage-Specific Utility in Multi-Agent Search▼5.8k2.33
[PDF]SCHEMAS: Leveraging a Scalable Heterogeneous Graph for Query-Guided Reasoning in Multi-Agent Systems▼4.3k2.20
[PDF]Organizing Collaboration Around Contributions: Agentic Intellectual Property for Long-Horizon Multi-Agent Systems▲6.1k2.00
[PDF]One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems▼5.8k2.33
[PDF]Certify, Then Act: Formal Safety Certificates for Cooperative LLM Agents in Stochastic Environments▲3952.67
[PDF]MatBak: Targeted-Behavior Adversarial Attacks on Multiple Reinforcement Agents via Preference-Based Intention Policies▼1.2k1.67
[PDF]From Local Errors to System Failures: Modeling and Benchmarking Error Propagation in Multi-Agent LLM Systems▼4.3k2.00
[PDF]MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning▼4.3k2.00
[PDF]MessageFlow: Proactive Message-Aware Execution for Efficient On-Device Multi-Agent Systems▼4.5k2.67
[PDF]MUSE: Agentic 3D Scene Authoring via Memory-Grounded Incremental Requirement Satisfaction▲3952.67
[PDF]Tapestry: Enabling Continuous Collaboration Across Episodes in Embodied Multi-Agent Systems▼2443.33
Withdrawn or desk rejected (134)
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00
[PDF]ReLoC: Recursive Local Causal Modeling for Explaining and Predicting LLM-Based Multi-Agent BehaviorWithdrawn1.33