Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization

arXiv:2610.01017 · cs.AI, cs.CL · Submitted 2026-10-01 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-10-01

Updated: 2026-10-02

Project page: https://xhguo7.github.io/InFlowOp

Terminology

• Accuracy — 27× in this paper · explained in 1 episode
• Benchmark — 23× in this paper · explained in 2 episodes
• Task Decomposition — 6× in this paper · explained in 2 episodes
• Adam — 5× in this paper · explained in 2 episodes
• Core — 5× in this paper · explained in 2 episodes
• Multi-Agent System — 5× in this paper · explained in 6 episodes
• Trace — 5× in this paper · explained in 2 episodes
• Topological Order — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Agentic System — 3× in this paper · explained in 2 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Elias — 2× in this paper · explained in 2 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Adaptive Selection — 1× in this paper · explained in 1 episode
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Analyzer — 1× in this paper · explained in 1 episode
• Credit assignment — 1× in this paper · explained in 3 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Multi-agent Collaborative Framework — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Training-Free Framework — 1× in this paper · explained in 2 episodes
• Two-Stage Framework — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
• AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use
• Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems
• Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
• Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
• Multi-Agent Collaboration via Evolving Orchestration
• LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating
• HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference
• SwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators?
• Anagent For Enhancing Scientific Table & Figure Analysis
• FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing
• Measuring Mathematical Problem Solving With the MATH Dataset
• Who is the Agent to Blame? Localizing Faithfulness and Citation Mistakes in Agentic Deep Research
• MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
• EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems
• Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents
• The Illusion of Multi-Agent Advantage
• PRInTS: Reward Modeling for Long-Horizon Information Seeking
• Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection