Title: Accepted Papers | ICLR 2026 Workshop RSI
Domain: recursive-workshop.github.io
Links:
| Back to Home | https://recursive-workshop.github.io/index.html |
| Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning | https://openreview.net/forum?id=hYYeOl58xi |
| Contextual Drag: How Errors in the Context Affect LLM Reasoning | https://openreview.net/forum?id=zpiYsPVDlV |
| Learning to Continually Learn via Meta-learning Agentic Memory Designs | https://openreview.net/forum?id=sOq52KnJmR |
| PostTrainBench: Can LLM Agents Automate LLM Post-Training? | https://openreview.net/forum?id=FJKOIxkUxo |
| Language Self-Play For Data-Free Training | https://openreview.net/forum?id=uB8YQHNsh6 |
| SimpleMem: Efficient Lifelong Memory for LLM Agents | https://openreview.net/forum?id=oYHelQ3Edd |
| Towards Execution-Grounded Automated AI Research | https://openreview.net/forum?id=gpLJamvbsK |
| Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation | https://openreview.net/forum?id=D93migx9av |
| Can Language Models Discover Scaling Laws? | https://openreview.net/forum?id=Nj6VGY4dej |
| Self-Improving World Models via Asymmetric Forward-Inverse Consistency | https://openreview.net/forum?id=ajcjip0yFR |
| Tiny Autoregressive Recursive Models | https://openreview.net/forum?id=aY5kmaNrwB |
| From Growing to Looping: A Unified View of Iterative Computation in LLMs | https://openreview.net/forum?id=yIDgVx3OoN |
| Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework | https://openreview.net/forum?id=q5qN3oQ4D1 |
| Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations | https://openreview.net/forum?id=d40v7Qcpi4 |
| ACE: Self-Evolving LLM Coding Framework Adversarial Unit Test Generation and Preference Optimization | https://openreview.net/forum?id=ecKAmz5vlO |
| Can Current Language Models Close the Discovery to Application Loop? | https://openreview.net/forum?id=BAdK20xfqj |
| CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad | https://openreview.net/forum?id=14jSctSh0D |
| Self-Improving Vision-Language-Action Models with Data Generation via Residual RL | https://openreview.net/forum?id=shqo2VPfc7 |
| VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model | https://openreview.net/forum?id=Ro0eQ0ly3q |
| Test-Time Self-Distillation | https://openreview.net/forum?id=iEmRSwdzyw |
| Self-Evolving Rubrics: Interpretable Instance-Level Criteria for Scalable RL | https://openreview.net/forum?id=aA2PXFH2Cp |
| Anchored Self-Play for Code Repair | https://openreview.net/forum?id=lTbBFAoPSA |
| Interestingness as an Inductive Heuristic for Future Compression Progress | https://openreview.net/forum?id=6GTlSlWW9C |
| GASP: Guided Asymmetric Self-Play For Coding LLMs | https://openreview.net/forum?id=NYrOkAfDkP |
| Adaptive Meta-Curriculum for Test-Time Self-Improvement | https://openreview.net/forum?id=GjoUJTfXiW |
| Self-Improving Clinical Reasoning via Textual Gradients | https://openreview.net/forum?id=VOa0lDJ5Ui |
| Federated Agent Reinforcement Learning | https://openreview.net/forum?id=h4iPWHGapI |
| Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning | https://openreview.net/forum?id=JKx0zkUBsQ |
| OMEGA: Optimizing Machine learning by Evaluating Generated Algorithms | https://openreview.net/forum?id=4TUzVEzVdu |
| Intelligent Robot Manipulation Requires Self-Directed Learning | https://openreview.net/forum?id=hCjgh8jxKl |
| Correct Reasoning Paths Visit Shared Decision Pivots | https://openreview.net/forum?id=OlMSrldTNe |
| RFTF: Reinforcement Fine-tuning for Vision-language-action Models with Temporal Feedback | https://openreview.net/forum?id=mBgcG43j7a |
| VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use | https://openreview.net/forum?id=l5QPYxMEaH |
| TangramSR: A Benchmark for Recursive Self-Improvement In Continuous Geometric Reasoning | https://openreview.net/forum?id=5XGfbXlFmA |
| SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning | https://openreview.net/forum?id=56D2hjARkn |
| A Framework for Prompt Optimization and Translation Across Foundation Models | https://openreview.net/forum?id=gOTCn5uZeE |
| Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence | https://openreview.net/forum?id=YzDC5hjGUM |
| LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers | https://openreview.net/forum?id=KbGkWv7VEk |
| Contrastive Self-Refinement for Low-Cost Adaptation in Real-World Text-to-SQL | https://openreview.net/forum?id=tgnbgt3Ctr |
| Simple Baselines are Competitive with Code Evolution | https://openreview.net/forum?id=QSWFqDcveB |
| Rethinking Machine Unlearning: Models Designed to Forget via Key Deletion | https://openreview.net/forum?id=gGH3Xp1lHR |
| Self-CriTeach: LLM Self-Teaching and Self-Critiquing for Improving Robotic Planning via Automated Domain Generation | https://openreview.net/forum?id=8I0n20ufAy |
| Unlocking Intrinsic Self-Reflection for LLM Preference Policy Optimization | https://openreview.net/forum?id=0ZGL40jRKE |
| TextBO: Bayesian Optimization in Language Space for Eval-Efficient Self-Improving AI | https://openreview.net/forum?id=h0XYERyeL6 |
| POLARIS: A GODEL AGENT FRAMEWORK FOR SMALL LANGUAGE MODELS THROUGH EXPERIENCE ABSTRACTED POLICY REPAIR | https://openreview.net/forum?id=wlwkLVvB0W |
| Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks | https://openreview.net/forum?id=Oc5R3D2TfE |
| Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search | https://openreview.net/forum?id=TnjlvLY30w |
| Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability | https://openreview.net/forum?id=HuLoDnvC29 |
| Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents? | https://openreview.net/forum?id=0DyJeJ3iia |
| Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision | https://openreview.net/forum?id=WA6q2pNQhj |
| Theory-Driven Modeling and LLM-Guided Evolution for Power System Scheduling | https://openreview.net/forum?id=djdSNvWpJ7 |
| Differentiable Evolutionary Reinforcement Learning | https://openreview.net/forum?id=uXTXcZ615k |
| Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning | https://openreview.net/forum?id=rL0GEyoMvE |
| Unrolled Policy Iteration for Tiny Recursive Models | https://openreview.net/forum?id=rIzREKws05 |
| Reasoning Cache: Learning to Extrapolate to Long Lengths via Short-Length RL | https://openreview.net/forum?id=DROMQyqM52 |
| ESDAE: Evaluating Synthetic Data for Agent Evaluation | https://openreview.net/forum?id=DlhLLVhrZB |
| Actor-Curator: Scalable Policy-driven Curriculum Learning for RL Post-Training | https://openreview.net/forum?id=JYJXWnujvR |
| Reward Hacking in Self-Improving Code Agents | https://openreview.net/forum?id=ikrQWGgxYg |
| Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping | https://openreview.net/forum?id=sSwXGq1RRI |
| Learning What to Learn: Curriculum Curation for Test-Time Agent Learning | https://openreview.net/forum?id=TRQLuxgxBN |
| Beyond Solving: A Closer Look at LLMs as Solution Verifiers | https://openreview.net/forum?id=Hv5hDfbhuB |
| Aligned but Stereotypical? Understanding and Mitigating Social Bias in LLM-Driven Text-to-Image Models | https://openreview.net/forum?id=RvgoRhan6d |
| Do Depth-Grown Models Overcome the Curse of Depth? An In-Depth Analysis | https://openreview.net/forum?id=Enqas0eZF6 |
| CoT-Seg: Rethinking Segmentation with Chain-of-Thought Reasoning and Self-Correction | https://openreview.net/forum?id=BtHRvwzJj8 |
| AlphaApollo: A System for Deep Agentic Reasoning | https://openreview.net/forum?id=UcIFJPXqrB |
| Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space | https://openreview.net/forum?id=fWrhAOQZ5A |
| Leveraging Suboptimal and Noisy Trajectories for Goal-Conditional Offline RL | https://openreview.net/forum?id=jfi88XbVsn |
| AUTOHARNESS: IMPROVING LLM AGENTS BY AUTOMATICALLY SYNTHESIZING A CODE HARNESS | https://openreview.net/forum?id=g9rEYVNn5T |
| One-Step Video Depth Estimation via Self-Distillation | https://openreview.net/forum?id=ucRjPd9HVU |
| Discover the distinguishing and effective reasoning patterns among LLMs via an LLM | https://openreview.net/forum?id=z9MOHU8RjL |
| Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models | https://openreview.net/forum?id=f1eKYFvMNu |
| Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback | https://openreview.net/forum?id=KCcpSuocz0 |
| Learning to Evolve: Scaling Open-Ended Discovery with Relative-Progress RL | https://openreview.net/forum?id=WnZHbe1Gu0 |
| Improved Iterative Refinement for Chart-to-Code Generation via Structured Instruction | https://openreview.net/forum?id=KgkMSbYoL1 |
| Language-Guided Expertise Evolution for Protein Optimization | https://openreview.net/forum?id=NeNWeyfUJj |
| A Task-Centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula | https://openreview.net/forum?id=EEc4Pn2GSa |
| Adaptive Decoding via Test-Time Policy Learning for Self-Improving Generation | https://openreview.net/forum?id=7fIqKZ92Fy |
| Dynamic Noise Preference Optimization: Self-Improvement of Large Language Models with Self-Synthetic Data | https://openreview.net/forum?id=nT1gTSAf07 |
| Vision-Guided Iterative Refinement for Frontend Code Generation | https://openreview.net/forum?id=gF6jmAsbpZ |
| MAPPA: Scaling Multiagent Systems with Process Rewards | https://openreview.net/forum?id=s06wgoO65a |
| Residual Off-Policy RL for Finetuning Behavior Cloning Policies | https://openreview.net/forum?id=9m4kM3bK2b |
| SAGE: Self-play Adversarial Games Enhance Large Language Model Reasoning Capabilities | https://openreview.net/forum?id=b3dPMokQki |
| Soft Mellowmax Monte Carlo Planning | https://openreview.net/forum?id=SeZCSEGZTq |
| Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation | https://openreview.net/forum?id=32xd2HdB9m |
| Self-Improving VLM Judges Without Human Annotations | https://openreview.net/forum?id=8hYSvUpJBA |
| Duel-Evolve: Pairwise Preference Black-Box Optimization of LLM Responses | https://openreview.net/forum?id=38t39AFZPE |
| MimicAgent: Learning Quadruped Skills via Text-to-Trajectory Generation | https://openreview.net/forum?id=1iAEFtFQ9M |
| Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison | https://openreview.net/forum?id=A0dlCcZ4hT |
| CircuitBuilder: From Polynomials to Circuits via Reinforcement Learning | https://openreview.net/forum?id=JNsTWIukjQ |
| Generative Recursive Reasoning Models | https://openreview.net/forum?id=Vxu6kcIjwV |
| Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning | https://openreview.net/forum?id=5UbKomO77O |
| Refining Large Language Models with Self-Generated Data Through Iterative Training | https://openreview.net/forum?id=81P20Qg44P |
| Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement | https://openreview.net/forum?id=QopjICzGwr |
| In-Context Adaptation | https://openreview.net/forum?id=f58uDOwLaq |
| SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement | https://openreview.net/forum?id=OAFPpQO0H9 |
| Structure Enables Effective Self-Localization of Errors in LLMs | https://openreview.net/forum?id=QbL99Fyqsl |
| Self-Improvement via Fast Tree-search | https://openreview.net/forum?id=wZMNXHPYcO |
| Self-Adapting Agents for Automating Research Coding Workflows | https://openreview.net/forum?id=ihcRmUkXHF |
| Verifying the Verifiers: Failure Attribution for Agentic Benchmark Diagnostics and Training Data Curation | https://openreview.net/forum?id=iRhaK8PsuB |
| Just Enough Learning: GRPO-Guided Controllers for Hyperparameter Sweeps | https://openreview.net/forum?id=kKWSQsYgpa |
| Real-Time Procedural Learning From Experience for AI Agents | https://openreview.net/forum?id=MKG4BaSieN |
| Reference-Guided Machine Unlearning | https://openreview.net/forum?id=0IbjWHRGMC |
| Test-Time Adaptation via Many-Shot Prompting: Benefits, Limits, and Pitfalls | https://openreview.net/forum?id=Ne0s3UOzdB |
| Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models | https://openreview.net/forum?id=7dNjMllnWe |
| Depth vs Recursion: Outperforming Transformers in Jigsaw Reconstruction | https://openreview.net/forum?id=1zDG1o16xB |
| Test-Time Meta-Adaptation with Self-Synthesis | https://openreview.net/forum?id=G0GE1xbR0w |
| Federation over Text | https://openreview.net/forum?id=gh7aCT73cq |
| TamperBench: A Systematic Framework to Stress-Test LLM Safety Under Fine-Tuning and Tampering | https://openreview.net/forum?id=smLtz7WID0 |
| Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants | https://openreview.net/forum?id=FySoHBWmt9 |
| Orthogonal Gradient Projection for Continual LLM Unlearning | https://openreview.net/forum?id=lb6Ce20kl5 |
Viewport: width=device-width, initial-scale=1