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
5,246 results for “keyword:"agent"” in ICLR 2027. 1,220 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]BIND BEFORE YOU BUYCANDIDATE-CONSISTENT CONSTRAINT LEARNINGFOR INTERACTIVE SHOPPING AGENTS▼1.3k1.75
[PDF]Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval▼4.3k2.00
[PDF]COMPASS: Routing via Capability-Oriented Model Profiling with Adaptive Search, Selection, and Tool Use▼1.2k1.67
[PDF]Are Small Language Models Ready for On-Device Agents? Benchmarking Small Language Models as Smart-Home Agents▼1.2k1.67
[PDF]Does Reward Select Interaction? Identifying and Steering Information Pathways in Multi-Agent Policies▼1.2k1.67
[PDF]Quantize the Team: Joint Quantization and Topology Adaptation for Multi-Agent LLM Systems▼1.2k1.67
[PDF]Multi-Level Semantic Skills for Transfer: Exploration, Control, and Adaptation across Discrete and Continuous Domains▼4.3k2.00
[PDF]Toward User-centered Agentic Recommendation: When Does Platform Competition Benefit Users?▼4.3k2.00
[PDF]Beyond Query-Memory Matching: Path-Aware Anchor-Guided Retrieval for Long-Term Agent Memory▼1.2k1.67
[PDF]Let Minstrel Tell Your Story: Reconstructing Character Profiles from Descriptions for Role Playing▲3.8k2.50
[PDF]TrajPD: Constructing Trajectory-Aware Targets for On-Policy Distillation in Tool-Integrated Reasoning▲8.9k2.75
[PDF]LLM-SemanticLAN: Anchored Public Latent Communication via KV Caches across Heterogeneous Large Language Models▲3.0k2.33
[PDF]A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution▼5.9k2.50
Withdrawn or desk rejected (1,220)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]Population Contracts for Scalable Language-Guided Multi-Robot Planning and ControlDesk rejected
[PDF]When to Act, Not What to Act: Prospective Authorization for Tool-Using Language ModelsWithdrawn1.33
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00