跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-17AI 評分34

Progress-Aware Distillation:緩解小型語言模型智能體的進展停滯

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

AI 導讀

Progress-Aware Distillation(ProD)透過偵測及懲罰蒸餾小型語言模型智能體的進展停滯,提升其推理效率和任務成功率。它把學生模型與教師模型之間的停滯差距編碼為自適應邊際,以動態懲罰可能的停滯。涵蓋 8 個、參數規模由 0.6B 至 8B 的小型語言模型實驗顯示,ProD 能減輕停滯,並提升成功率及任務完成效率。

正文

Published on Oct 17

Authors:

,

,

,

,

Abstract

Progress-Aware Distillation detects and penalizes stagnation in distilled small language model agents to improve reasoning efficiency and success rates.

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.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.19439

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.19439 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.19439 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.19439 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co