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
580 results for “keyword:"horizon"” in ICLR 2027. 121 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Loc2Drive: Beyond Visual History with Explicit 3D World State for Long-Horizon Driving Video Generation▼5.8k2.33
[PDF]PVWander: 3D Memory-guided Panoramic Video Wandering with Path-Facing Canonicalization▼5.8k2.33
[PDF]What Does Context Compression Cost an Agent? Interaction Costs Unrevealed by Task-Completion Metrics▼1361.33
[PDF]When Every Rollout Fails: Splicing Learner-Conditioned Options into Long-Horizon Agent RL▼5.8k2.33
[PDF]Collect for Coverage, Replay with Evidence: Adaptive and Efficient On-Policy Distillation for Long-Horizon Agents
[PDF]Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic Tasks in Real-World Professional Fields▼5.8k2.33
[PDF]What Should a VLM Tell an Action Expert? Comparing Conditioning Interfaces for Long-Horizon Furniture Assembly▼1361.33
[PDF]LongWM-Bench: Benchmarking Persistent and Navigable Worlds over Long-Horizon Interaction▼4.5k2.67
[PDF]DMC-5: Dual-Model Collaboration with Cache-aware Context Compression for Long-horizon Agents▲6.1k2.00
[PDF]From Trajectory Evidence to Control: Latent Control-State Inference for Long-Horizon Language Agents▼1.2k1.67
[PDF]Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation▲6.6k3.33
[PDF]AnchorNav: Long-Horizon 3D Game Navigation with Persistent Memory and Waypoint-Conditioned Control▼4.3k2.00
[PDF]IterLab: Training Agents to Experiment and Improve over Long Horizons with Calibrated Synthetic Tasks▼4.3k2.00
[PDF]From Local Accuracy to Global Forecasting: Expert Selection for Multistep Multivariable Tokamak Fusion Dynamics▲3.0k2.33
[PDF]SRE-Marathon: A Continuous, Change-Driven Benchmark for Autonomous Site Reliability Agents▲432.75
[PDF]ToolPlan-Bench: Diagnosing Hidden Planning Failures in Long-Horizon Tool-Calling Agents Beyond Success Rate▲3.9k1.75
Withdrawn or desk rejected (121)
[PDF]Beyond Local Cycles: Long-Horizon Repetitive Action Counting via Multi-Scale Temporal Representation LearningDesk rejected
[PDF]Defect Responses in Visual World Models: Long-Horizon Propagation, Gradient Interaction, and Planning OutcomesWithdrawn1.33
[PDF]Beyond Tokens: Read and Predict N-gram Spans with a Shared Dictionary for Genomic Foundation ModelsWithdrawn
[PDF]EarthArena: Benchmarking Agents on Real-world, Long-Horizon Scientific Tasks in Earth ObservationWithdrawn1.67