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

arXiv: https://arxiv.org/abs/2610.19439 · HTML: https://mlsanity.com/paper/2610.19439/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 32 of its 40 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 32)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [Large Language Models Are Reasoning Teachers](https://mlsanity.com/paper/2212.10071/) (2022)
- [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [Distilling Reasoning Capabilities into Smaller Language Models](https://mlsanity.com/paper/2212.00193/) (2022)
- [SCOTT: Self-Consistent Chain-of-Thought Distillation](https://mlsanity.com/paper/2305.01879/) (2023)
- [WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents](https://mlsanity.com/paper/2509.06501/) (2025)
- [Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization](https://mlsanity.com/paper/2410.08847/) (2024)
- [Distilling LLM Agent into Small Models with Retrieval and Code Tools](https://mlsanity.com/paper/2505.17612/) (2025)
- [DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models](https://mlsanity.com/paper/2505.13975/) (2025)
- [OAgents: An Empirical Study of Building Effective Agents](https://mlsanity.com/paper/2506.15741/) (2025)
- [Wait, Wait, Wait... Why Do Reasoning Models Loop?](https://mlsanity.com/paper/2512.12895/) (2025)
- [Keypoint-based Progressive Chain-of-Thought Distillation for LLMs](https://mlsanity.com/paper/2405.16064/) (2024)

## Abstract (arXiv)

While LLM-based agent systems have demonstrated remarkable proficiency in reasoning and solving complex real-world tasks, they also come with substantial token consumption and inference latency, limiting their practical deployment. To enhance the efficiency of agent systems, recent efforts have focused on transferring agentic capabilities from large-scale models to small language models (SLMs) via supervised fine-tuning-based distillation. Nevertheless, as interaction trajectories grow longer, involving extended reasoning-action chains and extensive environmental feedback, distilled student agents tend to experience progress stagnation: becoming trapped in unproductive loops characterized by persistent failed strategies and difficulty making meaningful progress. Our systematic analysis shows that this phenomenon consistently occurs across diverse SLMs and task domains. To address this issue, we propose Progress-Aware Distillation (ProD), which explicitly detects and penalizes stagnation in student-generated trajectories. ProD encodes the stagnation gap between student and teacher into an adaptive margin for dynamically penalizing possible stagnation. By iteratively applying this procedure, ProD enables student agents to progressively approximate teacher behavior. Extensive experiments involving 8 SLMs, ranging from 0.6B to 8B parameters, on both in-domain and out-of-domain benchmarks, demonstrate that ProD substantially mitigates progress stagnation while enhancing both the success rates and task-completion efficiency of distilled SLM agents.