Read original ↗
paperarXivTrust 82 · PrimaryPublished 4d agoLive · 3d ago

ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs

Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative reasoning among specialized LLM agents, but they incur substantial operating costs due to repeated LLM invocations and long-horizon context accumulation. Existing cascade routing methods make one-shot, query-level decisions and cannot adapt to the dynamic, state-dependent nature of multi-step workflows, in which the right LLM at each step depends on evolving task progress, remaining task difficulty, and cost-efficiency requirements. We present ProgRou

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

  • FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B

    Fuzzy title match (0.73): “ProgRouter: Online Progress-Guided Orchestration for Multi-A” ≈ “AgentCore-8B”

  • PossiblePossibly related (embedding) · 30%deepset-ai/haystack

    Possibly related via embedding similarity 0.65 (not asserted). Timestamp check: artifact slightly before paper (-55d).

  • PossiblePossibly related (embedding) · 28%neuml/txtai

    Possibly related via embedding similarity 0.61 (not asserted). Timestamp check: artifact slightly before paper (-44d).

  • FuzzySimilar title/name (fuzzy) · 87%SWE-agent/SWE-agent

    Fuzzy title match (0.94): “ProgRouter: Online Progress-Guided Orchestration for Multi-A” ≈ “SWE-agent/SWE-agent”

  • FuzzySimilar title/name (fuzzy) · 87%zhayujie/CowAgent

    Fuzzy title match (0.94): “ProgRouter: Online Progress-Guided Orchestration for Multi-A” ≈ “zhayujie/CowAgent”

  • FuzzySimilar title/name (fuzzy) · 66%open-multi-agent/open-multi-agent

    Fuzzy title match (0.78): “ProgRouter: Online Progress-Guided Orchestration for Multi-A” ≈ “open-multi-agent/open-multi-agent”

  • FuzzyOverlapping authors or contributors · 62%ray-project/ray

    Shared author/contributor keys: wang

  • FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow

    Shared author/contributor keys: wang

Has model

Related to

Implements (incoming)

authored (incoming)

Related across the graph

Topics