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

2026-03-08 · Yeahia Sarker, Md Rahmat Ullah, Musa Molla, Shafiq Joty 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.

📄 PDF Abstract BibTeX arXiv:2605.13848

Code (0)

등록된 구현이 없습니다.

GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning

2018-06-01 · CVPR 2018 6 · Yueqi Duan, Ziwei Wang, Jiwen Lu, Xudong Lin 외

In this paper, we propose a GraphBit method to learn deep binary descriptors in a directed acyclic graph unsupervisedly, representing bitwise interactions as edges between the nodes of bits. Conventional binary represent…

Binarization Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+2

Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning

2026-06-22 · Yunan Wang, Minghui Song, Zihan Zhang, Shaohan Huang 외 arxiv

Group-based Reinforcement Learning (RL) has significantly enhanced Large Language Models (LLMs) in agentic scenarios. To achieve finer-grained policy updates, recent agentic RL frameworks have shifted from trajectory-lev…

Reinforcement Learning

MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism

2026-06-05 · Cong Chen, Guo Gan, Kaixiang Ji, ZhaoYang Zhang 외 arxiv

Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to deco…

Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization

2026-06-24 · Long Chen, Ryan Razkenari, Yuxuan Zhou, Yuan Tian 외 arxiv

As advanced RAG variants like GraphRAG and Agentic RAG emerge, one leading question is when and how to use them. Here, we introduce a framework for different RAG scenarios evaluation and comparison on semi-structured kno…

Knowledge Graphs

Hippocampus: An Efficient and Scalable Memory Module for Agentic AI

2026-02-14 · Yi Li, Lianjie Cao, Faraz Ahmed, Puneet Sharma 외 arxiv

Agentic AI require persistent memory to store user-specific histories beyond the limited context window of LLMs. Existing memory systems use dense vector databases or knowledge-graph traversal (or hybrid), incurring high…