Data to 14 Oct 2026

Adaptive Consistency Graph for Long-Horizon Agents

arXiv 2609.32754 ↗First posted 26 Sep 2026cs.AI cs.CLcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks also fits: Reinforcement learning for LLM agents

Abstract (arXiv)

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 https://github.com/yunsaijc/Adaptive-Consistency-Graph.

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 26 of its 30 references that are in the map. First posted on arXiv 26 Sep 2026.

Builds on

26 of 30 references.

Closest ancestors · 5

Same direction, newest first

Other references · 21

2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839

9 more

2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
2019Compressive Transformers for Long-Range Sequence Modellingcited by 726
2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
2022Memorizing Transformerscited by 226
2025BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agentcited by 200
2023Augmenting Language Models with Long-Term Memorycited by 189
2025ACON: Optimizing Context Compression for Long-horizon LLM Agentscited by 136
2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Modelcited by 106

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way