智能体
arxiv.org ·
面向长时程智能体的自适应一致性图
论文提出 Adaptive Consistency Graph（ACG），用于缓解 LLM 智能体在长序列依赖动作与工具调用中目标漂移的问题。ACG 将执行证据及其来源增量组织为持久图，并在受限上下文预算下为每次决策构建临时的、以需求为中心的视图，不替换基础智能体的规划器或工具执行器。匹配评测中，GPT-5.6-luna 的平均成功率由 ReAct 的 44.5% 提升至 50.2%，BrowseComp-Plus 上为 73.5% 对 62.4%；作者进一步分析了轨迹结构与推理成本。
AI推荐理由 arXiv 新论文，提出 Adaptive Consistency Graph（ACG），在不替换基础 agent 规划器/工具执行器的前提下，为长时程执行的每次决策构建以需求为中心、可追溯的上下文视图。摘要给出匹配评测结果：GPT-5.6-luna 平均成功率从 ReAct 的 44.5% 提升到 50.2%，BrowseComp-Plus 上 73.5% 对 62.4%，并分析了轨迹结构与推理成本。信息密度较高、有具体数字，但仅凭摘要无法核实实验设置与可复现性，且模型名 GPT-5.6-luna 需读者自行判断。
72
正文
Computer Science > Artificial Intelligence
arXiv:2609.32754 (cs)
[Submitted on 26 Sep 2026]
Title:Adaptive Consistency Graph for Long-Horizon Agents
Authors:Jiecong Wang, Hao Peng, Zhanyi Wang
View a PDF of the paper titled Adaptive Consistency Graph for Long-Horizon Agents, by Jiecong Wang and 2 other authors
View PDF
HTML (experimental)
Abstract:Large language model agents can often make reasonable local decisions on short tasks, yet their performance degrades when success requires long sequences of dependent actions and tool calls. During execution, task requirements, historical evidence, and the current execution state may gradually become disconnected, so later decisions can drift from the original objective. We study this problem by introducing the Adaptive Consistency Graph (ACG) for long-horizon execution. ACG incrementally organizes execution evidence and its provenance in a persistent graph, then constructs a temporary requirement-centered view for each decision under a bounded context budget. Rather than replacing the base agent's planner or tool executor, ACG provides a structured and traceable context view for each decision. In the matched evaluation, ACG improves GPT-5.6-luna's average success from 44.5\% with ReAct to 50.2\%, with the largest gain on BrowseComp-Plus (73.5\% versus 62.4\%). We further analyze trajectory structure and inference cost to characterize this improvement.
Subjects:
Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as:
arXiv:2609.32754 [cs.AI]
(or
arXiv:2609.32754v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.32754
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Jiecong Wang [view email]
[v1]
Sat, 26 Sep 2026 16:19:40 UTC (373 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Adaptive Consistency Graph for Long-Horizon Agents, by Jiecong Wang and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
cs.CL
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?)