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
138 results for “keyword:"experience"” in ICLR 2027. 22 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]VersionShift: Evaluating and Adapting Prior Experience Across Software Versions for GUI Agents▼1.2k3.00
[PDF]Evolution Only When Needed: Triggered Evolutionary Data Injection for Off-Policy Reinforcement Learning▲3.0k2.33
[PDF]WHETHER VS. WHEN: SEPARATING SHORTCUT FORMATION FROM EVIDENCE-TIMING SENSITIVITY IN VALUE-BASED ONLINE REINFORCEMENT LEARNING▼1611.50
[PDF]Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills▲3952.67
[PDF]Learning What to Practice Next: Experience-Adaptive Self-Evolution for Multi-Turn Empathetic Dialogue▼1.2k3.00
[PDF]From Discovery to Mastery: Reallocating the Replay Budget in Massively Parallel Reinforcement Learning▼1.2k3.00
[PDF]SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?▲3.8k2.50
[PDF]Skill-Forming Evidence for LLM Agents: Joint Selection and Target-Model-Aware Compilation▼1.2k1.67
[PDF]When Is Reuse Superiority Licensed? Evidence Separation for Heterogeneous Offline Experience Reuse▼1.2k1.67
Withdrawn or desk rejected (22)
[PDF]Policy Improvement as Decision Revision: Preserving the Incumbent under Executable FeedbackWithdrawn1.33
[PDF]EvoCompile: Bridging the Compilation Effectiveness Gap through Experience-Adaptive Agentic OptimizationWithdrawn2.00
[PDF]RAM-CIL: Reliability-Aware Multimodal Class-Incremental Learning under Modality Reliability ShiftWithdrawn
[PDF]CORE-Flow: Counterfactual Observation and Retrieval-Guided Exploration for Efficient Agentic Workflow EvolutionWithdrawn1.33