Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems

Hongyuan Su, Y. Zheng, Yuan Yuan, Yuming Lin, Depeng Jin +1 more
2/14/2026

No official code found. Best implementation: tsinghua-fib-lab/AdaReMo (8 stars, MIT, last commit 2025-07-09).

Semantic Scholar

Code Implementations(1)

tsinghua-fib-lab/AdaReMoCommunity71%
MIT

[ICML25] Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems

80Shell, PythonJul 9, 20251 years agoMIT

Similar Papers

GPS: A Probabilistic Distributional Similarity with Gumbel Priors for Set-to-Set Matching

99% match1 repo12026

FlexControl: Computation-Aware Conditional Control with Differentiable Router for Text-to-Image Generation

96% match2026

Enhancing Cross-Subject fMRI-to-Video Decoding with Global-Local Functional Alignment

94% match2026

DreamDiffusion: High-Quality EEG-to-Image Generation with Temporal Masked Signal Modeling and CLIP Alignment

94% match2026

Modularized Self-Reflected Video Reasoner for Multimodal LLM with Application to Video Question Answering

94% match1 repo2026

Quantum 3D Graph Learning with Applications to Molecule Embedding

93% match2026

Cite this paper

@article{su2026reinforcement,
  title  = {Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems},
  author = {Hongyuan Su and Y. Zheng and Yuan Yuan and Yuming Lin and Depeng Jin and Yong Li},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:1d35faaab62a53685ce59452e5ff64442fe16887},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1d35faaab62a53685ce59452e5ff64442fe16887.svg)](https://codeofpaper.com/paper/1d35faaab62a53685ce59452e5ff64442fe16887)

Discussion