GraphFlow uses a unified wGraph to dynamically instantiate workflows and manage KV caches for LLM agents, reporting 4.95 pp average gains and 4x memory reduction on five benchmarks.
Flows: Building Blocks of Reasoning and Collaborating AI
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Recent advances in artificial intelligence (AI) have produced highly capable and controllable systems. This creates unprecedented opportunities for structured reasoning as well as collaboration among multiple AI systems and humans. To fully realize this potential, it is essential to develop a principled way of designing and studying such structured interactions. For this purpose, we introduce the conceptual framework Flows. Flows are self-contained building blocks of computation, with an isolated state, communicating through a standardized message-based interface. This modular design simplifies the process of creating Flows by allowing them to be recursively composed into arbitrarily nested interactions and is inherently concurrency-friendly. Crucially, any interaction can be implemented using this framework, including prior work on AI-AI and human-AI interactions, prompt engineering schemes, and tool augmentation. We demonstrate the potential of Flows on competitive coding, a challenging task on which even GPT-4 struggles. Our results suggest that structured reasoning and collaboration substantially improve generalization, with AI-only Flows adding +21 and human-AI Flows adding +54 absolute points in terms of solve rate. To support rapid and rigorous research, we introduce the aiFlows library embodying Flows. The aiFlows library is available at https://github.com/epfl-dlab/aiflows. Data and Flows for reproducing our experiments are available at https://github.com/epfl-dlab/cc_flows.
citation-role summary
background 1
other 1
citation-polarity summary
representative citing papers
Strong LLM optimizers act as local refiners with incremental improvements and semantic localization, while weaker ones show large drift and stagnation; solution novelty predicts success only when searches stay localized around high-performing regions.
AIRA₂ improves AI research agents via asynchronous multi-GPU workers, hidden consistent evaluation, and interactive ReAct agents, reaching 81.5-83.1% percentile rank on MLE-bench-30 and exceeding human SOTA on 6 of 20 AIRS-Bench tasks.
A conceptual model proposes representing LLM workflow definitions, instances, and inference records as persistent typed objects in a shared knowledge substrate, distinguishing deterministic derive from LLM-mediated infer.
A literature survey that collects and categorizes 124 papers on LLM-based agents for software engineering from SE and agent perspectives.
The paper surveys key large language models, their training methods, datasets, evaluation benchmarks, and future research directions in the field.
citing papers explorer
-
GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving
GraphFlow uses a unified wGraph to dynamically instantiate workflows and manage KV caches for LLM agents, reporting 4.95 pp average gains and 4x memory reduction on five benchmarks.
-
What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search
Strong LLM optimizers act as local refiners with incremental improvements and semantic localization, while weaker ones show large drift and stagnation; solution novelty predicts success only when searches stay localized around high-performing regions.
-
AIRA_2: Overcoming Bottlenecks in AI Research Agents
AIRA₂ improves AI research agents via asynchronous multi-GPU workers, hidden consistent evaluation, and interactive ReAct agents, reaching 81.5-83.1% percentile rank on MLE-bench-30 and exceeding human SOTA on 6 of 20 AIRS-Bench tasks.
-
Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows
A conceptual model proposes representing LLM workflow definitions, instances, and inference records as persistent typed objects in a shared knowledge substrate, distinguishing deterministic derive from LLM-mediated infer.
-
Large Language Model-Based Agents for Software Engineering: A Survey
A literature survey that collects and categorizes 124 papers on LLM-based agents for software engineering from SE and agent perspectives.
-
Large Language Models: A Survey
The paper surveys key large language models, their training methods, datasets, evaluation benchmarks, and future research directions in the field.