Self-Taught Self-Correction for Small Language Models
Paper • 2503.08681 • Published • 16
Self correction
-
-
Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
Paper • 2605.14539 • Published • 5 -
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2607.14777 • Published • 105 -
Self-Improvements in Modern Agentic Systems: A Survey
Paper • 2607.13104 • Published • 31 -
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
Paper • 2607.18754 • Published • 24 -
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Paper • 2607.21461 • Published • 153 -
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
Paper • 2607.22529 • Published • 48 -
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
Paper • 2607.23802 • Published • 95 -
SPADE: Self-Play in Adaptive Synthetic Executable Environments
Paper • 2608.19197 • Published • 61 -
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
Paper • 2608.26530 • Published • 36 -
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Paper • 2608.31100 • Published • 148 -
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Paper • 2609.14858 • Published • 334 -
Recursive self-improvement of AI research agents
Paper • 2609.26457 • Published • 28 -
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Paper • 2609.38288 • Published • 117 -
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
Paper • 2609.39045 • Published • 91 -
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
Paper • 2610.08621 • Published • 98 -
Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement
Paper • 2610.12369 • Published • 28 -
Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
Paper • 2610.11794 • Published • 48 -
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
Paper • 2610.14118 • Published • 35 -
Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine
Paper • 2610.22192 • Published • 41 -
AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning
Paper • 2610.22194 • Published • 42 -
Self-Evaluating Recursive Agents
Paper • 2610.04902 • Published • 16 -
On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models
Paper • 2610.32770 • Published • 8