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
308 results for “keyword:"feedback"” in ICLR 2027. 62 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Counterfactual Error Scrambling: Measuring Error-Message Use in Tool-Using Language Agents▼4.3k2.00
[PDF]Learning from Failures: Verified Edit Distillation for Variable-Length Diffusion Language Models▲1.7k3.33
[PDF]Recursive Hypercompression: Phase Transitions from Self-Improvement to Self-Deterioration▼5.8k2.33
[PDF]RGFA: Reliability Guided Feedback Adaptation in Large Language Models via Selective Feedback Utilization▲9.2k2.67
[PDF]Do Detailed Guard Denials Help Bypass Guardrails? Evaluating Runtime Feedback in DeepSeek Harness▼4.3k2.00
[PDF]Shared-Factor Distribution Shift in Multi-Task Learning: Identification and Adaptation▼4.5k2.67
[PDF]DuoOPD: Learning from Joint Teacher–Student Outcomes for Multi-Task On-Policy Distillation▲5.4k3.00
[PDF]From Spectral Measurement to Feedback Collapse: The Limits of Adaptive Orthogonal Optimization▼4.3k2.00
[PDF]When a Known Answer Unlocks Search: Split–Localize Control for Structured One-Sided Search▼1.3k1.75
[PDF]On Delayed Learning in Reinforcement Learning with Verifiable Rewards: Provable Laws of Feedback and Recovery
[PDF]Deep Message-Passing GNNs Have a Backward Problem: Kronecker-Aligned Feedback Training▲3.0k2.33
[PDF]Planning Before and After Feedback: Allocating Five Complete Planner Calls with Frozen Visual World Models▲6.1k2.00
[PDF]Faster Last-Iterate Convergence for Zero-Sum Games with Stochastic Feedback via Anchor-Regularized Learning▼1.2k3.00
Withdrawn or desk rejected (62)
[PDF]DAGLoop: Aligning Method Design with Experimental Feedback in Automated AI ResearchDesk rejected2.33