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
[PDF]When can test-time search be skipped? Successor-Channel Criticality for Action-Chunked Policies▲3972.67
[PDF]Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures▲6.1k2.00
[PDF]Allocate, Don't Just Rank: Reducing Redundancy in Test-Time Search for Scientific Discovery▼4.5k2.25