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
21 results for “keyword:"error propagation"” in ICLR 2027. 4 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]What Accurate Predictions Hide: Tracing Action-Effect Errors in World Models via Paired Rollouts▼1.2k1.67
[PDF]The Irreversibility Threshold: When Error in LLM Agent Pipelines Outruns Human Correction▼1351.33
[PDF]How Communication Topology Density Shapes Performance in LLM-Based Multi-Agent Systems▼4.3k2.00
[PDF]The Safety Criticality Number: Cascade Stability and Intervention Thresholds for AI Agents▼5.8k2.33
[PDF]Multi-Agent Debate Amplifies but Rarely Creates: A Calibrated Dissection at the Frontier of Model Capability▼5.8k2.33
[PDF]Towards a Theoretical Foundation for Tool-Augmented LLM Skill Libraries: The Price of Composition, Propagation, and Safety Under Evolution▼4.3k2.00
[PDF]A Wrong Turn in Addition: Generation, Routing, and Correction of Arithmetic Errors in LLMs▲5103.00
[PDF]From Local Errors to System Failures: Modeling and Benchmarking Error Propagation in Multi-Agent LLM Systems▼4.3k2.00
Withdrawn or desk rejected (4)
[PDF]Is LLM-Curated Policy Evidence Trustworthy Enough for Causal Analysis? An Audit-then-Propagate Framework Applied to Global Digital-Nomad Visa DataWithdrawn1.33