STRETCH the Boundaries: A Unified Self-Taught Framework for Progressive LLM Evolution

arXiv:2609.18642 · cs.CL · Submitted 2026-09-16 · Read on arXiv

cs.CL

Submitted: 2026-09-16

Updated: 2026-09-16

Code: https://github.com/GuanNiPiShi123/STRETCH

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 19× in this paper · explained in 1 episode
• Scaffolding — 17× in this paper · explained in 3 episodes
• Accuracy — 14× in this paper · explained in 1 episode
• Benchmark — 12× in this paper · explained in 2 episodes
• GRPO — 12× in this paper · explained in 6 episodes
• Operation Research — 9× in this paper
• Cognitive Scaffolding — 7× in this paper · explained in 3 episodes
• Generalization — 5× in this paper · explained in 13 episodes
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Verifier — 4× in this paper · explained in 2 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Catastrophic Forgetting — 3× in this paper · explained in 5 episodes
• Execution Rate — 3× in this paper
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Mixed-Integer Linear Programming — 3× in this paper
• Price Gap — 3× in this paper
• Solving Accuracy — 3× in this paper
• Zone of Proximal Development — 3× in this paper
• Ablation study — 2× in this paper · explained in 1 episode
• Adversarial Co-evolution — 2× in this paper · explained in 1 episode
• Average Turn — 2× in this paper
• Cognitive Load — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Decoupling — 2× in this paper · explained in 2 episodes
• GRPO Objective — 2× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Supervised Fine-Tuning — 2× in this paper
• Supervised Fine-Tuning (SFT) — 2× in this paper · explained in 8 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Unified Framework — 2× in this paper · explained in 5 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Absolute Zero Reasoner — 1× in this paper
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Agent Memory — 1× in this paper · explained in 1 episode
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Alternation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Dual-Mind Negotiation Agent — 1× in this paper
• Generalizability — 1× in this paper · explained in 6 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Information Gain — 1× in this paper · explained in 2 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Reward Hacking — 1× in this paper · explained in 8 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Verifiability — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
• G-Zero: Self-Play for Open-Ended Generation from Zero Data
• R-Zero: Self-Evolving Reasoning LLM from Zero Data
• LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages
• GPT-4 Technical Report
• Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences
• Advancing Reasoning in Large Language Models: Promising Methods and Approaches
• Guiding Reasoning in Small Language Models with LLM Assistance
• Evolving Deeper LLM Thinking
• Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
• AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions
• The Llama 3 Herd of Models
• From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game
• LLMs and the ZPD
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering