Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents

arXiv:2610.19439 · cs.LG · Submitted 2026-10-14 · Read on arXiv

cs.LG

Submitted: 2026-10-14

Updated: 2026-10-17

Comments: Accepted to NeurIPS 2026

Code: https://github.com/huggingface/smolagents

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

Terminology

• Distillation — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• FireAct: Toward Language Agent Fine-tuning
• The Llama 3 Herd of Models
• DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• Distilling LLM Agent into Small Models with Retrieval and Code Tools
• CTRL: A Conditional Transformer Language Model for Controllable Generation
• WebThinker: Empowering Large Reasoning Models with Deep Research Capability
• WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents
• Large Language Model Agent: A Survey on Methodology, Applications and Challenges
• Wait, Wait, Wait... Why Do Reasoning Models Loop?
• Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
• Gemma 3 Technical Report
• Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting
• Qwen3 Technical Report

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks