CAIRN: Dynamic Fact-Intent DAGs for Multi-Agent Exploration

Zuyao Xu; Yuyang Jia; Junwei Guan; Xiang Li; Kaiwen Shen; Zhiqiang Dong

cs.AISep 26, 2026

CAIRN: Dynamic Fact-Intent DAGs for Multi-Agent Exploration

Authors: Zuyao Xu, Yuyang Jia, Junwei Guan, Xiang Li, Kaiwen Shen, Zhiqiang Dong

Organizations: Nankai University · Tencent Security Yunding Lab · Tsinghua University

Abstract

LLM-powered autonomous systems have demonstrated promising capabilities in mathematical reasoning, engineering, and cybersecurity. Yet how to organize these systems for effective, reliable, and sustained performance remains an open question. In this paper, we present CAIRN, a fact-intent-driven multi-agent paradigm for goal-directed exploration. CAIRN represents observations and planned investigations as a dynamic directed acyclic graph (DAG). A reasoner interprets facts to propose intents, which workers execute to produce new facts. Each intent references its supporting facts and defines a potential exploration branch. The persistent graph preserves goals, dependencies and findings across workers, supporting knowledge reuse and parallel exploration. The graph also makes execution trajectories traceable and auditable, providing a basis for human verification and intervention. We evaluate CAIRN across cybersecurity and mathematical reasoning tasks, examining task success, time to solution, and token consumption. DAG-based coordination can incur higher token costs with no observable performance gains on tasks that require little effort. However, on high-effort tasks (at least 1M tokens), we observe faster solutions in 76.5% of cases, with speedups of up to 3.08x. Moreover, as task effort increases, these time gains become more pronounced while relative token overhead declines, highlighting the potential of DAG-guided parallel exploration.

Figures & tables

Panel of Figure 1 — Figure 1: Exploration over a shared fact – intent DAG. The reasoner reads graph state and proposes intent s citing source fact s ( 1 Propose). The dashed dispatcher receives candidate intent s and assigns eligible candidates ( 2 Assign). worker s execute assigned intent s using a graph snapshot and record outcome fact s ( 3 Record). In the illustrated graph, $f_{1}$ and $f_{2}$ support $i_{4}$ . The reasoner drops $i_{5}$ when new evidence contradicts its underlying premise.

Panel of Figure 2 — Figure 2: Two approaches to the same credential-recovery task. (a) A sequential action–observation trajectory. (b) Cairn ’s fact – intent DAG. Three investigations start from the origin and examine the portal, API, and session tokens. The API and token findings jointly motivate a subsequent investigation toward the goal .

Figure 3: Cairn execution architecture. The dispatcher starts reasoner and worker sessions with graph snapshots. Sessions submit changes through the graph service; worker s also use task tools. Accepted updates persist for later sessions and notify the dispatcher . Solid arrows show assignments, updates, and task actions; dashed links show graph state and snapshots.

Figure 4: General agent behavior design factors. Cairn focuses on task architecture as a multi-agent coordination paradigm, while other factors are held constant as the basis for comparison in the evaluation. The examples in each area illustrate representative design choices.

Table 5

Figure 5: Time–token trade-offs across the 52 tasks. Arrows run from Direct to Cairn ; labels on the right name the tasks on which Cairn finishes sooner than Direct ; lines connect each label to its Cairn endpoint. Shading shows where Cairn endpoints cluster within each outcome group.

Panel of Figure 6 — Figure 6: Task-level performance by effort and benchmark. In (a,b), points show tasks in the three baseline-token effort groups of Table 2 ; lines connect arithmetic means, light and dark boxes span the 10th–90th and 25th–75th percentiles, and $n$ gives group size. In (c,d), circles denote FrontierMath and triangles Cybench tasks; shaded contours show task density.

Figure 7: Time advantage versus task effort. The vertical axis shows

T_{D}/T_{C}

, where

T_{D}

is the solving time of Direct and

T_{C}

is Cairn ; values above one favor Cairn . The line shows a pooled log–log linear fit with a pointwise 95% task-bootstrap confidence band. The horizontal line marks equal time (

T_{D}/T_{C}=1

), and the vertical dotted line marks the fitted crossing at 1.24M tokens.

Panel of Figure 8 — Figure 8: Active worker s in three Cairn runs on the same FrontierMath problem (fm-02). Each execution slot runs one agent session at a time; reasoner and worker sessions share the available slots. Colored bands count simultaneously active worker s; blank intervals may include reasoner activity or tool execution.

Figure 9: Execution timeline for fm-02. The 26.47-minute timestamp measures submission from the first model request; 26.51-minute solving time includes initialization and verification. Squares mark intent starts, circles mark fact s, and charcoal spans mark reasoner activity. Pale streams lack recorded completion before submission.

Panel of Figure 10 — Figure 10: Complete coordination traces for two FrontierMath Cairn runs: fm-05 (top) and fm-01 (bottom). Left: fact – intent DAGs. Right: execution flows with elapsed time in minutes. Red highlights answer-related paths, and stars mark accepted submissions.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Field	Role	Supplied content
graph_yaml	Reasoner, worker	Instructions to read a YAML snapshot file stored in the project container.
fact_ids	Reasoner	Identifiers of available fact s, excluding the terminal goal .
open_intents	Reasoner	Open intent identifiers, source identifiers, descriptions, assigned workers, and priorities.
max_intents	Reasoner	Per-invocation creation limit, or the literal value unlimited .
worker_capacity	Reasoner	Execution limits and slot availability at dispatch, including the reasoner’s slot.
intent_progress	Reasoner	Timestamped progress summary supplied at dispatch.

Appendix

Table 3: Fields used to instantiate the role prompts.

Tool	Role	Principal arguments	Result or effect
submit_fact	W	Description	Adds a fact linked to the assigned intent ; returns its identifier.
finish_intent	W	fact identifier	Concludes the assigned intent with a fact submitted by this execution.
create_intent	R	Source fact s, description, priority	Adds an intent supported by existing fact s; returns its identifier.
set_intent_priority	R	intent identifier, priority	Updates the scheduling priority of an open intent .
drop_intent	R	intent identifier, reason	Retires an open intent and revokes its worker’s access.
finish_reason	R	Description, outcome	Ends the review as planned or incomplete; acknowledges the reviewed revision.

Appendix

Table 4: Agent-facing MCP tools. R denotes the reasoner; W denotes workers. Every state-changing call also requires a submission_key . Arguments are summarized; pagination options are omitted.

Multi-Agent LLM Systems

Multi-agent large language model systems coordinate multiple AI agents to solve tasks through communication, specialization, shared tools, and memory.

See all 1,050 papers

Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph Systems
Jul 26, 2026Mingzhou Fan, Siyuan Xu, Mingxuan YuanMulti-Agent System Optimization LLM Agent Orchestration
DAGent: Evaluate-then-Grow Planning for Deep Research Agents
Sep 30, 2026Hanwen Liu, Yuanfu Sun, Qiaoyu TanMulti-Agent LLM Systems Deep Research Agents
New York University · New York University Shanghai
Inference-Time Graph Engineering for Multi-Agent LLM Workflows
Sep 4, 2026Katherine Tieu, Dongqi Fu, Yinglong Xia +3Multi-Agent LLM Systems Multi-Agent Orchestration
Meta · University of Illinois Urbana-Champaign · Work done at Meta

Jul 26, 2026J/K move · Enter open · S save

Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph Systems

Mingzhou Fan, Siyuan Xu, Mingxuan Yuan

Multi-Agent System Optimization LLM Agent Orchestration LLM Agent Workflow Optimization Multi-Agent Systems Multi-Agent LLMs

Open paper AskPDF arXiv

Large language models (LLMs) enable autonomous agents for reasoning, planning, and tool use. Recent systems increasingly organize these agents as graphs of specialized, interconnected nodes. Although graph-based orchestration supports flexible decomposition and coordination, it creates a key challenge: attention allocation. As workflows grow, existing approaches often execute graph components uniformly, wasting resources on irrelevant or low-impact tasks. We introduce Attention Orchestration, a paradigm that extends Transformer-style attention from token representations to workflow-level agent coordination. Our framework, Adaptive Goal-aware Attention Orchestration (AGAO), dynamically estimates agent importance based on user objectives, graph dependencies, and computational constraints. AGAO combines three components: (1) goal-aware attention, measuring semantic relevance between user goals and agent capabilities; (2) topology-aware attention, modeling structural dependencies in agent graphs; and (3) resource-aware attention, allocating budgets and execution priorities across heterogeneous agents. Together, these mechanisms transform static agent graphs into adaptive systems that focus computation on goal-critical reasoning paths. Experiments across diverse multi-agent workloads show that AGAO improves task effectiveness while reducing unnecessary computation, latency, and token consumption compared with existing graph-based execution strategies. Our work establishes Attention Engineering as a direction for scalable, intelligent multi-agent systems. Code: https://github.com/MingzhouFan97/AGAO.

Abstract

Multi-Agent LLM Systems

Explore similar work

Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph Systems

DAGent: Evaluate-then-Grow Planning for Deep Research Agents

Inference-Time Graph Engineering for Multi-Agent LLM Workflows