Pith. sign in

REVIEW 8 cited by

FlowReasoner: Reinforcing Query-Level Meta-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

arxiv 2504.15257 v1 pith:UOMA4LXD submitted 2025-04-21 cs.AI

classification cs.AI
keywords flowreasonermulti-agentquery-levelbenchmarkscodeexecutionexternalfeedback
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper proposes a query-level meta-agent named FlowReasoner to automate the design of query-level multi-agent systems, i.e., one system per user query. Our core idea is to incentivize a reasoning-based meta-agent via external execution feedback. Concretely, by distilling DeepSeek R1, we first endow the basic reasoning ability regarding the generation of multi-agent systems to FlowReasoner. Then, we further enhance it via reinforcement learning (RL) with external execution feedback. A multi-purpose reward is designed to guide the RL training from aspects of performance, complexity, and efficiency. In this manner, FlowReasoner is enabled to generate a personalized multi-agent system for each user query via deliberative reasoning. Experiments on both engineering and competition code benchmarks demonstrate the superiority of FlowReasoner. Remarkably, it surpasses o1-mini by 10.52% accuracy across three benchmarks. The code is available at https://github.com/sail-sg/FlowReasoner.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Workflow-Aware Serving Layer for Agentic Applications

    cs.DC 2026-07 conditional novelty 6.5 of 10

    A workflow-aware serving layer compiles per-node model-verifier-backend plans with an ILP and adapts only uncommitted work via pre-solved pressure rungs and residual re-solves.

  2. Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems

    cs.CR 2026-07 conditional novelty 6.0 of 10

    AgentLocate localizes multi-agent LLM failures to a responsible agent and earliest decisive step via judge hypotheses, confidence-weighted multi-evaluator verification, and LoRA refinement.

  3. Aime: Towards Fully-Autonomous Multi-Agent Framework

    cs.AI 2025-07 reject novelty 6.0 of 10

    Aime, a dynamic multi-agent framework, reports outperforming specialized baselines on GAIA (77.6%), SWE-bench Verified (66.4%), and WebVoyager (92.3%), but without code, error bars, or a specified LLM.

  4. FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills

    cs.AI 2026-04 conditional novelty 5.0 of 10

    FlowEvo compiles successful agent workflows into executable skill records and reuses them at inference time, reporting the best accuracy-cost tradeoff across ALFWorld, HumanEval, and GSM8K among tested baselines.

  5. MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Encoding LLM agent workflows as statically checked Mermaid graphs and evolving them with constrained mutations improves solve rates on GSM8K, MATH, HumanEval, and MBPP.

  6. UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs

    cs.LG 2025-02 conditional novelty 5.0 of 10

    A single pre-trained model, UniGraph2, creates a unified embedding space for multimodal graphs by combining CLIP encoders, a mixture-of-experts alignment layer, and a GNN, and it beats existing graph pre-training base...

  7. Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects

    cs.AI 2025-07 conditional novelty 3.0 of 10

    A survey that categorizes Graph-augmented LLM Agent research into planning, memory, tool management, and multi-agent design, and outlines open directions.

  8. Mathematical methods of reinforcement learning

    math.OC 2026-07 accept

    A survey unifying the operator-theoretic, probabilistic, and optimization-based mathematical structures underlying modern reinforcement learning algorithms.

Pith tools