Pith. sign in

REVIEW 6 cited by

ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2502.04306 v1 pith:V4DEETW7 submitted 2025-02-06 cs.CL

Yinjie Wang , Ling Yang , Guohao Li , Mengdi Wang , Bryon Aragam This is my paper
classification cs.CL
keywords optimizationscoreflowagentexistingmethodspreferenceaccountsachieves
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent research has leveraged large language model multi-agent systems for complex problem-solving while trying to reduce the manual effort required to build them, driving the development of automated agent workflow optimization methods. However, existing methods remain inflexible due to representational limitations, a lack of adaptability, and poor scalability when relying on discrete optimization techniques. We address these challenges with ScoreFlow, a simple yet high-performance framework that leverages efficient gradient-based optimization in a continuous space. ScoreFlow incorporates Score-DPO, a novel variant of the direct preference optimization method that accounts for quantitative feedback. Across six benchmarks spanning question answering, coding, and mathematical reasoning, ScoreFlow achieves an 8.2% improvement over existing baselines. Moreover, it empowers smaller models to outperform larger ones with lower inference costs. Project: https://github.com/Gen-Verse/ScoreFlow

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

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

  1. CONTRA: Red-Teaming Configurations of Personalizable Agents

    cs.CR 2026-07 conditional novelty 7.0 of 10

    An LLM-assisted configuration tree search finds benign agent setups that trigger malicious actions for 75% of popular skills, showing personalization itself is a major safety risk.

  2. 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.

  3. Rethinking Query Optimization for Multi-Agent Systems [Vision]

    cs.DB 2025-12 conditional novelty 6.0 of 10

    Agentic data pipelines are built by hand today; this paper sets a research agenda for automatically optimizing their structure, model choices, and execution engines jointly as a new query-optimization problem.

  4. Reward-Free Evolving Agents via Pairwise Validator

    cs.AI 2026-07 conditional novelty 5.0 of 10

    A frozen LLM making binary parent-vs-child comparisons can replace the scalar reward in self-evolving agent loops, matching or beating reward-gated evolution on most settings.

  5. 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.

  6. 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.

Pith tools