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
856 results for “keyword:"agentic"” in ICLR 2027. 201 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA▼1.2k1.67
[PDF]ASIR: An Agent-Structure-Aware Indexer with Block-Local Reuse for Native Sparse Attention▼4.3k2.00
[PDF]DWELL: Persist or Wrap Up? Measuring and Governing Dynamical Instability in LLM Multi-Agent Orchestration▼1.2k1.67
[PDF]Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement▲5103.00
[PDF]ORGWorld: Benchmarking AI Agents as Collaborative Coworkers in Realistic Company Environments▼1.2k3.00
[PDF]When Does Feedback Help? Evaluating Feedback for Iterative Refinement in Coding Agents▼1.2k1.67
[PDF]Learning to Search and Searching to Learn: Joint Knowledge Internalization via Reinforcement Learning▼1.2k1.67
[PDF]The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory▲5.4k3.00
[PDF]KernelGenBench: Can LLMs and Agents Write Efficient Kernels Across Operator Sources and Hardware Platforms?▼1.2k3.00
[PDF]SimPersona: Learning Discrete Buyer Personas from Raw Clickstreams for Grounded E-commerce Agents▲5.4k3.00
[PDF]ANTE: Anticipate, Then Execute - Learning Internal World Models for Code Agents from Verified Beliefs▼5.8k2.33
[PDF]DeltaPRM: Rollout-Free Automatic Process Rewards via Answer Likelihood Gain for Retrieval Agents▲5.4k3.00
[PDF]RecoAtlas: A Benchmark and RL Environment for LLM Recommendation Agents Optimizing Set-Level Utility▼4.3k2.00
Withdrawn or desk rejected (201)
[PDF]WorldMirror: Agentic Real-to-Sim Generation of Interactive Worlds from In-the-Wild Robot DemonstrationsWithdrawn1.67
[PDF]Auditing Reward-Model Selection on Tool Trajectories: Identification, Policy Utility, and Natural TransferWithdrawn1.67