ICLR 2026

5,370 papers

Top Research Directions

Research directions most represented by ICLR 2026 papers.

Scaling Language Model Reasoning Beyond Verifiable Rewards 88
Group Relative Policy Optimization for Large Reasoning Models 81
General Purpose Reasoning from Specialized Reinforcement Learning 79
Shifting from Static Benchmarks to Dynamic Evaluation 66
The Decoupling of Visual Perception and Logical Reasoning 51
Mitigating the Inference Latency of Chain of Thought 50
Activation Steering for Inference Time Model Control 41
Preventing Entropy Collapse in Reinforcement Learning 41
Inference Time Compute Scaling for Complex Reasoning 38
Reinforcement Learning with Verifiable Rewards 38
Autonomous Code Refinement via Execution Feedback Loops 38
Mitigating Computational Overthinking in Large Reasoning Models 37
Resolving Superposition with Sparse Autoencoders 34
Role Specialization in Multi-Agent Architectures 34
The Spatial Reasoning Bottleneck in Multimodal Models 33

Top Authors

AuthorPapers
Fei Huang20
Ge Zhang19
Jianye HAO19
Dahua Lin17
Junchi Yan17
Michael M. Bronstein17
Yejin Choi17
James Y. Zou16
James Zou16
Bo Han15
Jingren Zhou15
Min Zhang15
Tat-Seng Chua15
Caiming Xiong14
Dawn Song14
Pengfei Wan14
Yi Yang14
Jiaheng Liu13
Kai Chen13
Pengjun Xie13

Impactful Papers

Papers from ICLR 2026 that shaped research clusters.

Foundational

Papers

Title
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models
Agentic Reinforced Policy Optimization
Agentic Reinforcement Learning with Implicit Step Rewards
AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
AgentPO: Enhancing Multi-Agent Collaboration via Reinforcement Learning
AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents
Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models
Agnostics: Learning to Synthesize Code in Any Programming Language with a Universal Reinforcement Learning Environment
A Graph Meta-Network for Learning on Kolmogorov–Arnold Networks
A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
A Hidden Semantic Bottleneck in Conditional Embeddings of Diffusion Transformers
A Hierarchical Circuit Symbolic Discovery Framework for Efficient Logic Optimization
A High Quality Dataset and Reliable Evaluation for Interleaved Image-Text Generation
AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework
A.I.R.: Enabling Adaptive, Iterative, and Reasoning-based Frame Selection For Video Question Answering
AIRE-Prune: Asymptotic Impulse-Response Energy for State Pruning in State Space Models
AirQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation
A Joint Diffusion Model with Pre-Trained Priors for RNA Sequence-Structure Co-Design
A Law of Data Reconstruction for Random Features (And Beyond)
Algorithmic Guarantees for Distilling Supervised and Offline RL Datasets
Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems
Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
Aligner, Diagnose Thyself: A Meta-Learning Paradigm for Fusing Intrinsic Feedback in Preference Alignment
AlignFlow: Improving Flow-based Generative Models with Semi-Discrete Optimal Transport
Aligning Collaborative View Recovery and Tensorial Subspace Learning via Latent Representation for Incomplete Multi-View Clustering
Aligning Deep Implicit Preferences by Learning to Reason Defensively
Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models
Alignment-Enhanced Integration of Connectivity and Spectral Sparsity in Dynamic Sparse Training of LLM
Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
Align-SAM: Seeking Flatter Minima for Better Cross-Subset Alignment
AlignSep: Temporally-Aligned Video-Queried Sound Separation with Flow Matching
Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance
Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges
Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics
All Code, No Thought: Language Models Struggle to Reason in Ciphered Language
All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker Adaptation
All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning
All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning
All That Glitters Is Not Gold: Key-Secured 3D Secrets within 3D Gaussian Splatting
ALM-MTA: Front-Door Causal Multi-Touch Attribution Method for Creator-Ecosystem Optimization
Almost Bayesian: Dynamics of SGD Through Singular Learning Theory
AlphaAgentEvo: Evolution-Oriented Alpha Mining via Self-Evolving Agentic Reinforcement Learning
AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
AlphaBench: Benchmarking Large Language Models in Formulaic Alpha Factor Mining
AlphaFlow: Understanding and Improving MeanFlow Models

« prev Page 4/108 next »