智能体
arxiv.org ·
面向 LLM 智能体的轮次级多尺度密度比估计
阿里巴巴团队提交 arXiv 论文，提出 tlm-DRE（Turn-level Multiscale Density Ratio Estimation），针对 PPO、DPO、DIL、GRPO 等对齐方法多聚焦单轮任务的问题，为多轮任务的不同轮次分配不同权重，并基于多轮正负样本空间差距做非对称 token 级训练。摘要称在多个 agent benchmark 上与传统对齐方法相比具有竞争力，并在域内和域外多轮推理任务中表现稳健。
AI推荐理由 arXiv 新提交论文（2026-09-15），作者来自阿里巴巴，提出 tlm-DRE 方法，针对多轮 LLM 智能体任务在 PPO/DPO/DIL/GRPO 等对齐方法上的不足，按轮次分配权重并做非对称 token 级训练。摘要称在多个 agent benchmark 上表现有竞争力，并覆盖域内与域外多轮推理。局限：仅有摘要，无具体指标、数据集和代码链接，效果无法独立验证；属方法类论文，对做 agent 后训练的研究与工程团队有参考价值。
72
正文
Computer Science > Artificial Intelligence
arXiv:2609.16760 (cs)
[Submitted on 15 Sep 2026]
Title:Turn-level Multiscale Density Ratio Estimation for LLM Agents
Authors:Zishuo Zhao (Alibaba Group), Kai Chen (Alibaba Group), Ao Li (Alibaba Group), Yuan Liu (Alibaba Group)
View a PDF of the paper titled Turn-level Multiscale Density Ratio Estimation for LLM Agents, by Zishuo Zhao (Alibaba Group) and 3 other authors
View PDF
HTML (experimental)
Abstract:With the rapid development of Large language model (LLM), agent systems enhanced by LLMs show huge potential in being able to deal with complex tasks, especially involving multi-step thinking or interaction with tools. For applying LLM techniques with a well-designed agent paradigm, post-training of LLM in multiple agent scenarios is necessary to achieve better performance. Among the variable post-training techniques, alignment methods such as PPO, DPO, DIL, and GRPO become popular because many papers show a significant positive impact on the model's performance by punishing negative samples while keeping acceptable training complexity. However, most alignment methods address simple single-turn tasks, and there remains room for improvement for complex multi-turn tasks. We propose Turn-level Multiscale Density Ratio Estimation (tlm-DRE), which assigns different weights on corresponding turns and proposes asymmetric token-level training based on the positive-negative space gaps across multiple turns of tasks. The results of the experiment on a wide range of agent benchmarks show that the proposed method performs competitively compared to traditional alignment methods. The proposed training method enables LLMs to perform robustly in multi-turn reasoning tasks with both in-domain and out-of-domain conditions.
Comments:
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.16760 [cs.AI]
(or
arXiv:2609.16760v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.16760
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Zishuo Zhao [view email]
[v1]
Tue, 15 Sep 2026 07:36:23 UTC (2,226 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Turn-level Multiscale Density Ratio Estimation for LLM Agents, by Zishuo Zhao (Alibaba Group) and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)