ICML 2025PastOther
The Exploration in AI Today Workshop at ICML 2025
EXAIT@ICML 2025
- Submission deadline
- Jun 1, 2025, 12:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (51)
Fetched from OpenReview (v2) on 2026-06-10.
A Diffusion Model to Shrink Proteins While Maintaining their Function
Active Advantage-Aligned Online Reinforcement Learning with Offline Data
Align While Search: Belief-Guided Exploratory Inference for Test-Time World Alignment
Automated Data Selection for Efficient Cost Model Training to Optimize Sparse Matrix Kernels on Emerging Hardware Accelerators
Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames
Branched Schrödinger Bridge Matching
Central Path Proximal Policy Optimization
Diffusion-Based Maximum Entropy Reinforcement Learning
Direct Regret Optimization in Bayesian Optimization
DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
Distances for Markov chains from sample streams
Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization
e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
EVOLvE: Evaluating and Optimizing LLMs ForIn-Context Exploration
Exploration by Exploitation: Curriculum Learning for Reinforcement Learning Agents through Competence-Based Curriculum Policy Search
Fleet of Agents: Coordinated Problem Solving with Large Language Models
Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning
From Words to Rewards: Leveraging Natural Language for Reinforcement Learning
G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
Greed is Good: A Unifying Perspective on Guided Generation
Improved Exploration in GFlownets via Enhanced Epistemic Neural Networks
Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM
In-Context Learning for Pure Exploration
Instance-Dependent Fixed-Budget Pure Exploration in Reinforcement Learning
Intent Factored Generation: Unleashing the Diversity in Your Language Model
Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Exploration in Reinforcement Learning towards Higher Moment Regularisations
Kevin: Multi-Turn RL for Generating CUDA Kernels
Llama-Nemotron: Efficient Reasoning Models
LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities
No-Regret Safety: Balancing Tests and Misclassification in Logistic Bandits
Oracle-Efficient Adversarial Reinforcement Learning via Max-Following
Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors
Provably Learning from Language Feedback
Reimagining Parameter Space Exploration with Diffusion Models
Reinforcement Learning with Action Chunking
Reinforcement Learning with Thompson Sampling: No-Regret Performance over Finite Horizons
Rethinking Exploration In Asynchronous Bayesian Optimization: Standard Acquisition Is All You Need
Retrospective and Structurally Informed Exploration via Cross-task Successor Feature Similarity
Scalable and Efficient Exploration via Intrinsic Rewards in Continuous-time Dynamical Systems
See it to Place it: Evolving Macro Placements with Vision Language Models
SOAPIA: Siamese-Guided Generation of Off Target-Avoiding Protein Interactions with High Target Affinity
Sparse Optimistic Information Directed Sampling
Stabilizing protein fitness predictors via the PCS framework
StemCell-GPT: A Specialized AI Agent For Human Stem Cell Engineering
Strategic Vantage Selection for Learning Viewpoint-Agnostic Manipulation Policies
Testing LLM Understanding of Scientific Literature through Expert-Driven Question Answering: Insights from High-Temperature Superconductivity
The Effective Horizon Challenge
The Road Not Taken: Hindsight Exploration for LLMs in Multi-Turn RL
Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
Toward Efficient Exploration by Large Language Model Agents
Towards Unsupervised Multi-Agent Reinforcement Learning via Task-Agnostic Exploration