REVIEW 15 cited by
AutoFlow: Automated Workflow Generation for Large Language Model Agents
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
AutoFlow: Automated Workflow Generation for Large Language Model Agents
read the original abstract
Recent advancements in Large Language Models (LLMs) have shown significant progress in understanding complex natural language. One important application of LLM is LLM-based AI Agent, which leverages the ability of LLM as well as external tools for complex-task solving. To make sure LLM Agents follow an effective and reliable procedure to solve the given task, manually designed workflows are usually used to guide the working mechanism of agents. However, manually designing the workflows requires considerable efforts and domain knowledge, making it difficult to develop and deploy agents on massive scales. To address these issues, we propose AutoFlow, a framework designed to automatically generate workflows for agents to solve complex tasks. AutoFlow takes natural language program as the format of agent workflow and employs a workflow optimization procedure to iteratively optimize the workflow quality. Besides, this work offers two workflow generation methods: fine-tuning-based and in-context-based methods, making the AutoFlow framework applicable to both open-source and closed-source LLMs. Experimental results show that our framework can produce robust and reliable agent workflows. We believe that the automatic generation and interpretation of workflows in natural language represent a promising paradigm for solving complex tasks, particularly with the rapid development of LLMs. The source code of this work is available at https://github.com/agiresearch/AutoFlow.
Forward citations
Cited by 15 Pith papers
-
DRFLOW: A Deep Research Benchmark for Personalized Workflow Prediction
DRFLOW is a benchmark with 100 tasks, 1246 reference workflow steps from over 3900 sources, and seven diagnostic metrics; the introduced DRFA agent improves baselines by up to 10% F1 but leaves substantial room for im...
-
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.
-
Inference-Time Budget Control for LLM Search Agents
A VOI-based controller for dual inference budgets improves multi-hop QA performance by prioritizing search actions and selectively finalizing answers.
-
Exploration and Exploitation Errors Are Measurable for Language Model Agents
A policy-agnostic metric and controllable 2D grid environments with task DAGs enable measurement of exploration and exploitation errors in language model agents from observed actions.
-
Automated Design of Agentic Systems
Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across...
-
MemoHarness: Agent Harnesses That Learn from Experience
MemoHarness learns from past executions to adapt an LLM agent's control layer per test case, improving task success over fixed harnesses on shell, code, and reasoning benchmarks.
-
Coupled Hierarchical Search over Topology and Execution for Agentic Workflow Synthesis
HierFlow couples search over task topologies and executable sub-workflows at test time, with an adaptive gate, and reports state-of-the-art results on QA, math, and code benchmarks without training.
-
AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows
AgentCo-op retrieves and assembles existing agents and tools into interoperable workflows for open-world scientific tasks, showing effectiveness in genomics case studies and competitive benchmark results with lower costs.
-
Small Model as Master Orchestrator: Learning Unified Agent-Tool Orchestration with Parallel Subtask Decomposition
ParaManager is a lightweight orchestrator that learns unified parallel agent-tool orchestration through a two-stage SFT and RL pipeline, achieving strong benchmark performance and generalization.
-
BLAST: Blockchain-based LLM-powered Agentic Spectrum Trading
BLAST combines LLM agents with blockchain for decentralized spectrum trading, where Vickrey auctions achieve up to 71% of theoretical social welfare surplus and outperform non-LLM baselines in competition and efficiency.
-
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
DataFlow-Harness builds editable data pipelines as validated DAGs via an LLM agent, hitting 93.3% task pass rate with 72.5% lower cost than vanilla script generation.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environm...
-
A Sober Look at Agentic Misalignment in Automated Workflows
Agentic misalignment in multi-agent systems arises from generic utilities causing posterior collapse; Agentic Evidence Attribution using self-reflection or weak-to-strong generalization provides context-specific evide...
-
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.
-
Designing for Error Recovery in Human-Robot Interaction
Position paper calls for designing robotic AI to detect and recover from its own errors in continuous interactions, using nuclear glovebox operations as an illustrative case.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.