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
1,091 results for “keyword:"systems"” in ICLR 2027. 249 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When to Aggregate: Delay-Aware Message Scheduling with Physics-Motivated Operator Decomposition for Dynamics Prediction▲3952.67
[PDF]From Agent Failures to Faulty Directives: Attribution-Based Aggregate Analysis of Skill Files▼4.3k2.00
[PDF]SLC: Constructing Semantic-Aware Latent Communication for LLM-based Multi-Agent Collaboration▲6.1k2.00
[PDF]CoEvolve: Counterfactual-Guided Co-Evolution of Memory and Collaboration in Multi-Agent System▲5.4k3.00
[PDF]ConsumerGym: Training LLM Agents for Real-World Conversational Commerce via Multi-Turn Reinforcement Learning▼5.8k2.33
[PDF]Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play▼5.8k2.33
[PDF]Physiology as Topology: Intervenable Organ Graphs for Longitudinal Patient Forecasting▼1.3k1.75
[PDF]REALMS-CG: Resilient Ensemble of Autonomous LLM Multi-agent with Spectral clustering for Code Generation▲3.0k2.33
[PDF]TSOrchestra: Time Series Agentic Orchestration Framework towards Dynamic and Faithful Forecasting▲5.4k3.00
[PDF]MELD: Recursive Self-Improvement via Hierarchical Coordination for Multi-Agent Scientific Discovery▲9.2k2.67
[PDF]Evaluator-in-the-Loop Monte Carlo Tree Search Via LLM Agents for Motif Scaffolding in Protein Design▲9.2k2.67
[PDF]CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning▲3952.67
[PDF]RITE: Evaluating End-to-End Resilience to Silent Tool Errors in E-Commerce Agentic Systems▼5.8k2.33
[PDF]The Update Bottleneck: Re-examining Joint Training for Semantic-ID-Based Generative Recommendation▼1.2k1.67
[PDF]Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning▼5.8k2.33
[PDF]Do Claims, Evidence, and Actions Align? Evidence-Linked Consistency Checking in Multi-Agent Systems▼4.3k2.00
[PDF]Finding Root Causes, Not Symptoms: A Mechanism and Method for Agent Failure Attribution▼5.8k2.33
[PDF]Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution▼5.8k2.33
[PDF]GSRT: Granularity-Selected Residual Transfer for Sparse Targets in Two-Tower Retrieval▲6.1k2.00
Withdrawn or desk rejected (249)
[PDF]Population Contracts for Scalable Language-Guided Multi-Robot Planning and ControlDesk rejected
[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
[PDF]Spectral Invariants of Reasoning Trajectories: A Koopman‑DMD Dynamical View on LLM Internal Logic GeometryWithdrawn1.50
[PDF]WorldMirror: Agentic Real-to-Sim Generation of Interactive Worlds from In-the-Wild Robot DemonstrationsWithdrawn1.67
[PDF]When Evidence Changes the Subject: Subject-Typed Claim Licensing for Learned RoutingWithdrawn1.67