Cover Image

DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Che, Lirong, yang, Yuzhe, lin, Peiwen, wang, Chuang, wang, Xueqian, su, Jian
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks
by: Che, Lirong, et al.
Published: (2026)

Harnessing Agentic Evolution
by: Zhang, Jiayi, et al.
Published: (2026)

Position: Agentic Evolution is the Path to Evolving LLMs
by: Lin, Minhua, et al.
Published: (2026)

Eliminating Agentic Workflow for Introduction Generation with Parametric Stage Tokens
by: Zhang, Meicong, et al.
Published: (2025)

Design Conditions for Intra-Group Learning of Sequence-Level Rewards: Token Gradient Cancellation
by: Ding, Fei, et al.
Published: (2026)

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
by: Lin, Minhua, et al.
Published: (2026)

DemoShapley: Valuation of Demonstrations for In-Context Learning
by: Xie, Shan, et al.
Published: (2024)

MINT-Demo: Membership Inference Test Demonstrator
by: DeAlcala, Daniel, et al.
Published: (2025)

PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding
by: Che, Lirong, et al.
Published: (2026)

Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models
by: He, Wei, et al.
Published: (2024)

RewardHarness: Self-Evolving Agentic Post-Training
by: Zhang, Yuxuan, et al.
Published: (2026)

sprofing the DLSCA
by: wang
Published: (2025)

HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
by: Jiang, Dongming, et al.
Published: (2026)

Auto-Demo Prompting: Leveraging Generated Outputs as Demonstrations for Enhanced Batch Prompting
by: Feng, Longyu, et al.
Published: (2024)

CRPE: Expanding The Reasoning Capability of Large Language Model for Code Generation
by: Gui, Ningxin, et al.
Published: (2025)

Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents
by: Ma, SHengjie, et al.
Published: (2025)

Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation
by: Chen, Wei, et al.
Published: (2026)

A dynamical clipping approach with task feedback for Proximal Policy Optimization
by: Zhang, Ziqi, et al.
Published: (2023)

Live-Evo: Online Evolution of Agentic Memory from Continuous Feedback
by: Zhang, Yaolun, et al.
Published: (2026)

SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation
by: Li, Long, et al.
Published: (2026)

Tools as Continuous Flow for Evolving Agentic Reasoning
by: Huang, Tairan, et al.
Published: (2026)

Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations
by: Zuo, Bowen, et al.
Published: (2026)

Observation-Frame Reconstruction via Dynamical Synchronization: A Conceptual Research Framework
by: wang, pu
Published: (2026)

Single-cell RNA-seq Analysis of Chicken
by: wang, fei
Published: (2026)

The Relationship between Fat Talk and Body Image in Chinese Female Nursing Students: The Mediating Role of Self-Acceptance
by: fengxia, wang
Published: (2026)

Topology of a Straight Line and Cosmic Closure: The 4D Conical Growth Model and Theory of Logical Origin (1.2)
by: wang, Zhenmin
Published: (2026)

wang201111/hybrid-intelligence-framework: v1.0.2
by: wang201111
Published: (2026)

End the global economic crisis
by: wang, junbin
Published: (2026)

Spiral-Fractal Unified Theory 3: Emergent Space-Time from Entropy Flow
by: wang, xuerui
Published: (2025)

HaJAK2/STAT5B mediate the post-mating switch of reproductive behavior in Helicoverpa armigera female
by: wang, yilin
Published: (2025)

Beyond Inversion: Rapid Physics-Based Moment Magnitude Estimation from P-Wave Amplitudes and Source Durations
by: wang, dun
Published: (2025)

AP60
by: hailiang wang
Published: (2023)

Spatial Transcriptomic Reconstruction of Human SCN
by: haifang, wang
Published: (2025)

Cuentos / Wang Meng ; prefacio de Flora Botton Beja ; traducción de Duan Ruochuan... [y otros.]
by: Meng, wang

Agentic Harness for Real-World Compilers
by: Zheng, Yingwei, et al.
Published: (2026)

AgenticRed: Evolving Agentic Systems for Red-Teaming
by: Yuan, Jiayi, et al.
Published: (2026)

Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning
by: Ding, Fei, et al.
Published: (2026)

MambaEVT: Event Stream based Visual Object Tracking using State Space Model
by: Wang, Xiao, et al.
Published: (2024)

AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
by: Wang, Yixu, et al.
Published: (2025)

Spatial Imputation Drives Cross-Domain Alignment for EEG Classification
by: Liu, Hongjun, et al.
Published: (2025)