Cover Image

Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hara, Rahaf Abu, Murarri, Vaibbhav, Zito, Claudio
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Modeling Saliency Dataset Bias
by: Kümmerer, Matthias, et al.
Published: (2025)

Reflective Policy Optimization
by: Gan, Yaozhong, et al.
Published: (2024)

Trajectory-Oriented Policy Optimization with Sparse Rewards
by: Wang, Guojian, et al.
Published: (2024)

Interactive Prompt Debugging with Sequence Salience
by: Tenney, Ian, et al.
Published: (2024)

Energy-Gated Attention: Spectral Salience as an Inductive Bias for Transformer Attention
by: Zeris, Athanasios
Published: (2026)

Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization
by: Gritsaev, Timofei, et al.
Published: (2024)

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models
by: Gumbsch, Christian, et al.
Published: (2026)

Reflective Preference Optimization (RPO): Enhancing On-Policy Alignment via Hint-Guided Reflection
by: Zhao, Zihui, et al.
Published: (2025)

When Data Falls Short: Grokking Below the Critical Threshold
by: Singh, Vaibhav, et al.
Published: (2025)

Dual-Phase Continual Learning: Supervised Adaptation Meets Unsupervised Retention
by: Singh, Vaibhav, et al.
Published: (2024)

Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics
by: Yang, Heng
Published: (2026)

P^2O: Joint Policy and Prompt Optimization
by: Lu, Xinyu, et al.
Published: (2026)

Flow-based Policy With Distributional Reinforcement Learning in Trajectory Optimization
by: Hao, Ruijie, et al.
Published: (2026)

SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies
by: Samadi, Amir, et al.
Published: (2024)

ReflectivePrompt: Reflective evolution in autoprompting algorithms
by: Zhuravlev, Viktor N., et al.
Published: (2025)

How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control
by: Kim, Dongseok, et al.
Published: (2025)

On the Reuse Bias in Off-Policy Reinforcement Learning
by: Ying, Chengyang, et al.
Published: (2022)

STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization
by: Chen, Yuhan, et al.
Published: (2025)

Enhancing PPO with Trajectory-Aware Hybrid Policies
by: Liu, Qisai, et al.
Published: (2025)

Saliency-Aware Regularized Graph Neural Network
by: Pei, Wenjie, et al.
Published: (2024)

On the Convergence of Experience Replay in Policy Optimization: Characterizing Bias, Variance, and Finite-Time Convergence
by: Zheng, Hua, et al.
Published: (2021)

AutoPDL: Automatic Prompt Optimization for LLM Agents
by: Spiess, Claudio, et al.
Published: (2025)

SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization
by: Wang, Zhengcheng, et al.
Published: (2025)

Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance
by: Guan, Yunchuan, et al.
Published: (2025)

Reusing Trajectories in Policy Gradients Enables Fast Convergence
by: Montenegro, Alessandro, et al.
Published: (2025)

Best Policy Learning from Trajectory Preference Feedback
by: Agnihotri, Akhil, et al.
Published: (2025)

Neural at ArchEHR-QA 2025: Agentic Prompt Optimization for Evidence-Grounded Clinical Question Answering
by: Bogireddy, Sai Prasanna Teja Reddy, et al.
Published: (2025)

Provable Robust Saliency-based Explanations
by: Chen, Chao, et al.
Published: (2022)

Can We Optimize Deep RL Policy Weights as Trajectory Modeling?
by: Tang, Hongyao
Published: (2025)

TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT
by: Khan, Rana Muhammad Shahroz, et al.
Published: (2026)

Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach
by: Poiani, Riccardo, et al.
Published: (2024)

Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL
by: Suau, Miguel, et al.
Published: (2023)

Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning
by: Daley, Brett, et al.
Published: (2023)

Info-CELS: Informative Saliency Map Guided Counterfactual Explanation
by: Li, Peiyu, et al.
Published: (2024)

A Minimalist Prompt for Zero-Shot Policy Learning
by: Song, Meng, et al.
Published: (2024)

Trajectory First: A Curriculum for Discovering Diverse Policies
by: Braun, Cornelius V., et al.
Published: (2025)

Bias after Prompting: Persistent Discrimination in Large Language Models
by: Sivakumar, Nivedha, et al.
Published: (2025)

Pareto optimal proxy metrics
by: Zito, Alessandro, et al.
Published: (2023)

T2IBias: Uncovering Societal Bias Encoded in the Latent Space of Text-to-Image Generative Models
by: Sufian, Abu, et al.
Published: (2025)

Offline Reinforcement Learning with Generative Trajectory Policies
by: Feng, Xinsong, et al.
Published: (2025)