DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space
Summary
Introduces DecoEvo, a score-decoupled co-evolution method for LLM optimization in text space that jointly improves solver and rubric-generator skills without gold rubrics, achieving 2.8–5.0% relative gains over baselines across five benchmarks.
View Cached Full Text
Cached at: 07/30/26, 05:46 AM
Paper page - DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space
Source: https://huggingface.co/papers/2607.25675
Abstract
Text-spaceoptimizationadaptslargelanguagemodels(LLMs)byeditingexternalnatural-languageartifactsratherthanmodelweights,sotheoptimizedartifactsremaininspectableandthemodelcanbetreatedasablackbox.However,mostexistingtext-spacemethodskeepevaluationfixed.Onopen-endedtasks,thiscanbecomeabottleneck:oncethesolverimprovesonthecriteriaarubricmeasures,omitteddimensionsremaininvisibletotheoptimizationsignal.Simplyevolvingtherubricisalsounreliablewhenupdatesareselectedbythecurrentsolver’sscore,becauseapparentprogresscancomefrommakingtherubriceasiertosatisfy.WeintroduceDecoEvo(DecoupledCo-Evolution),whichco-evolvesasolverskillandarubric-generatorskillunderdecoupledobjectiveswithoutusinggoldrubricsduringoptimization.Thesolverskillisupdatedusingcriterion-levelfeedback,whiletherubric-generatorskillisrevisedthroughcomplementaryauditsofrequirementcoverageandresponsediscriminationthatareindependentofaggregatesolverscore.Thisseparationfocusesgeneratorupdatesonnewlyexposedsolverweaknesses,reducingrepeatedemphasisoncriteriathesolveralreadysatisfies.Undereachbenchmark’sofficialevaluation,DecoEvooutperformsallcomparedmethodsacrossfivebenchmarksandthreeLLMbackbones,yielding2.8--5.0\%relativegainsoverSkillOptinthefive-benchmarkaverage.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2607\.25675
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2607.25675 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2607.25675 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2607.25675 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Self-Evolving Deep Research via Joint Generation and Evaluation
Researchers from HKUST, ByteDance, and UCL propose SCORE, a co-evolutionary training framework that jointly trains an LLM as both a deep research report generator and an evaluator, using a meta-harness to dynamically adjust evaluation difficulty and prevent reward saturation. Experiments show consistent improvement in open-ended research report quality.
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
This paper proposes a method for co-evolving evaluation metrics and skills in self-improving LLM agent systems, demonstrating that metrics can be evolved and that a co-evolution approach recovers most of the performance of a ground-truth-driven oracle across code generation, text-to-SQL, and report generation tasks.
Learnable Assessment Skills for LLM-based Automated Scoring: Rubric Construction via Iterative Optimization
This paper proposes learning assessment skills for LLMs to automate rubric construction for scoring tasks, achieving performance comparable to expert-written rubrics without requiring human-written examples.
Beyond Score Prediction: LLM-Based Essay Scoring and Feedback Generation via Reinforcement Learning with Rubric Rewards
This paper proposes RLAES, a unified LLM framework that jointly optimizes essay scoring and feedback generation via reinforcement learning with rubric-based rewards, achieving state-of-the-art scoring performance on the ASAP benchmark while maintaining high-quality feedback.
MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution
MetaEvo proposes a two-stage framework for continual evolution of LLM-based agents, using preference-based optimization to enhance principle abstraction and modular architecture for experience reuse, outperforming strong baselines on reasoning benchmarks.