GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration

arXiv 2605.13848 ↗First posted 8 Mar 2026cs.AI cs.CL cs.DCcited by 0

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer from hallucinated routing, infinite loops, and non-reproducible execution. We introduce GraphBit, an engine-orchestrated framework that defines workflows explicitly and deterministically as a directed acyclic graph (DAG). Unlike prompted orchestration, agents in GraphBit operate as typed functions, while a Rust-based engine governs routing, state transitions, and tool invocation, ensuring reproducibility and auditability. The engine supports parallel branch execution, conditional control flow over structured state predicates, and configurable error recovery. A three-tier memory architecture consisting of ephemeral scratch space, structured state, and external connectors isolates context across stages, preventing cascading context bloat that degrades reasoning in long-running pipelines. Across GAIA benchmark tasks spanning zero-tool, document-augmented, and web-enabled workflows, GraphBit outperforms six existing frameworks, achieving the highest accuracy (67.6 percent), zero framework-induced hallucinations, the lowest latency (11.9 ms overhead), and the highest throughput. Ablation studies demonstrate that each memory tier contributes measurably to performance, with deterministic execution providing the greatest gains on tool-intensive tasks representative of real-world deployments.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 17 of its 33 references that are in the map. First posted on arXiv 8 Mar 2026.

Builds on

17 of 33 references.

References · 17

2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
2023GAIA: a benchmark for General AI Assistantscited by 1,084
2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 424
2023An LLM Compiler for Parallel Function Callingcited by 170
2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 164
2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 108
2021Directed Acyclic Graph Neural Networkscited by 70

5 more

2024Exploration of LLM Multi-Agent Application Implementation Based on LangGraph+CrewAIcited by 35
2024Exploring Autonomous Agents through the Lens of Large Language Models: A Reviewcited by 30
2024Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Surveycited by 19
2025Blueprint First, Model Second: A Framework for Deterministic LLM Workflowcited by 11
2019Type Safety with JSON Subschemacited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way