HuggingFace Daily Papers（社区热门论文）· HuggingFace Daily Papers（社区热门论文）·· 10 天前AI 评分33
Adaptive Consistency Graph：面向长程智能体的自适应一致性图
AI 导读
针对 LLM 智能体在长序列依赖任务中决策漂移的问题，研究者提出 Adaptive Consistency Graph（ACG），将执行证据及其来源增量组织进持久图，并在有限上下文预算下为每次决策构建以需求为中心的临时视图。
正文
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. Our code is available at this https URL.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2609.32754 [cs.AI] |
| (or arXiv:2609.32754v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.32754 arXiv-issued DOI via DataCite |
Submission history
From: Jiecong Wang [view email]
[v1]
Sat, 26 Sep 2026 16:19:40 UTC (373 KB)
[v2]
Tue, 29 Sep 2026 06:28:56 UTC (373 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org