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
65 results for “keyword:"agentic systems"” in ICLR 2027. 14 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Slides2MindMap: Reconstructing Cognitively Grounded Knowledge Hierarchies from Lecture Slides▲3972.67
[PDF]MUSE: A Multilevel User Feedback Learning Framework for Self-Enhancement in Personalized Multimodal Agents▼5.8k2.33
[PDF]When Global Grades Fail Locally: Learning Local Supervision from Aggregate Feedback and Hindsight▼1.2k1.67
[PDF]Multi-Level Semantic Skills for Transfer: Exploration, Control, and Adaptation across Discrete and Continuous Domains▼4.3k2.00
[PDF]Gödel Ecology: Productivity-Guided Continuous Co-Evolution of Agents and Evaluators for Collective Recursive Self-Improvement▼4.3k2.00
[PDF]From Self-Correction to Self-Evolution: Agentic Test-Time Learning for Mathematical Reasoning▼4.3k2.00
[PDF]LiteEvo: Automated, Cost-Efficient Harness Evolution for Generalization to Unseen Tasks▲3.0k2.33
[PDF]Scaling Feedback Alone Is Not Scaling Supervision: From Prediction Quality to Decision Quality in Reward Learning▼1361.33
[PDF]From Evidence to Effect: Authority Semantics and Runtime Infrastructure for Stateful Agents▼1.2k1.67
[PDF]Attribution Is a Propagation Problem: End-to-End Causal Evidence Attribution in Multi-Agent Systems▲11.00
[PDF]OptiGen: A Physics-Grounded Agentic Framework for Deep-Ultraviolet Laser Diode Design and Optimization▼1361.33
[PDF]Global Latent Workspace: Shaping the Workspace for Multi-Agent Latent Communication via Reinforced Attention▼5.8k2.33
[PDF]ASIR: An Agent-Structure-Aware Indexer with Block-Local Reuse for Native Sparse Attention▼4.3k2.00
[PDF]KernelGenBench: Can LLMs and Agents Write Efficient Kernels Across Operator Sources and Hardware Platforms?▼1.2k3.00
[PDF]Closing the Loop in Formal Theorem Proving: Coordinated and Revisable Proof Construction▼1.2k1.67
[PDF]WHAT IS ONE SEARCH OPERATION WORTH? EVALUATING ITS DOWNSTREAM VALUE IN AUTOMATIC AGENT DESIGN▼1361.33
[PDF]Graph Program Synthesis: Adaptive Execution and Evolution for Long-Horizon Multi-Agent Systems▼4.3k2.00
[PDF]An Agent Is More Than Its Model: Controlled Safety Measurement Across CLI Model–Harness Configurations▲3.0k2.33
[PDF]FIELD: A Prospective Cross-Sport Benchmark for Language-Model Forecasting and Information Use▲6.1k2.00
[PDF]Learning When to Reconsider: Adequacy-Guided Inference-Time Interventions for Histopathology VLM Agents▲14k3.00
[PDF]AgenticGNN: A Spectral-Inspired Agentic Framework for Automated Graph Learning Algorithm Design▼1611.50
[PDF]Embodied Skill Bench: Benchmarking How Well Agents with Embodied Skills Perform on Physical Tasks▲14k3.00
[PDF]Performance and Energy Implications of Designing Efficient Agentic Workflows: Pitfalls and Opportunities▲3.0k2.50
[PDF]Can the Evidence Reach the Answer? Diagnostic Reachability over Uncertain Evidence Graphs for Agentic Whole-Slide Reasoning.▲5.4k3.00
[PDF]From Agent Failures to Faulty Directives: Attribution-Based Aggregate Analysis of Skill Files▼4.3k2.00
[PDF]TSOrchestra: Time Series Agentic Orchestration Framework towards Dynamic and Faithful Forecasting▲5.4k3.00
Withdrawn or desk rejected (14)
[PDF]ChurnMAS: Adaptive Role-Model Routing for LLM-based Multi-Agent Systems with Evolving Model PoolsWithdrawn1.67