cs.LGMay 8, 2026

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

Authors: Rahaf Abu Hara, Vaibbhav Murarri, Claudio Zito

Organizations: Laboratory of AI and Robotics Research (LAIRR) Heriot-Watt University Dubai, United Arab Emirates

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Existing LLM-based policy optimizers see only scalar rewards: that a policy scored 0.45, but not whether the agent got stuck in a loop, fell into a hole on the third step, or performed well on 19 out of 20 rollouts and failed catastrophically on one. We propose Reflective Prompted Policy Optimization (R2PO), a two-stage LLM framework for policy search over compact policy classes that augments scalar reward feedback with trajectory-level behavioral evidence. A Search-LLM proposes candidate policy parameters; the environment executes them; a Critic-LLM inspects the resulting rollouts and proposes targeted revisions grounded in observed states, actions, and rewards. Across ten environments, ablations show R2PO's gains require separating global search from behavior-grounded revision and using selection to filter high-variance edits. We further identify a dominant failure mode, salience bias: when presented with multiple rollouts, the Critic-LLM fixates on improving a single failure even when most trajectories succeed. In a three-trajectory variant where the Critic-LLM sees the best, worst, and median rollout, this behavior explains 76.6% of regressions on CartPole. R2PO mitigates this by reasoning over aggregate rollout statistics, median-trajectory selection, and a revision rule. Using a 20B open-weight model, R2PO achieves the highest mean best reward across all ten environments, reaches near-optimal performance substantially earlier (e.g., near-maximum CartPole reward within ~500 episodes), and trains far more stably than both deep RL and prior LLM-based methods. These results show that treating trajectories as first-class in-context evidence, rather than artifacts reduced to scalar returns, changes how even comparatively small LLMs search over policy spaces, enabling them to learn faster, diagnose more precisely, and reliably improve external controllers.

Explore similar work

CardsList
May 29, 2026cs.LG

When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?

We study when large language models (LLMs) can serve as effective black-box policy optimizers for reinforcement learning (RL) tasks, i.e., when can we replace classical RL algorithms with an LLM? We explore this question by introducing Prompted Policy Optimization (PromptPO), an iterative method that prompts an LLM with Python descriptions of the state space, action space, and reward function, then has it generate and refine executable policies based on rollout feedback. Across hard exploration environments, Meta-World robotics tasks, and several real-world control problems, PromptPO often matches or exceeds the performance of standard RL baselines while using substantially fewer environment interactions. To maximize expected return, and without further explicit prompting, the policies PromptPO outputs range from tuned proportional controllers or rule-based plans to policies that run planning algorithms like value iteration. Our results demonstrate that LLM-based policy optimization is sufficient when the LLM can leverage prior knowledge about the environment or optimization strategy. PromptPO underperforms standard RL baselines in MuJoCo domains. This demonstrates possible limitations of LLM-based policy optimization to settings that requiring fine-grained continuous control.
Stephane Hatgis-Kessell, Emma Brunskill
Multi-Objective Policy OptimizationDeep Reinforcement LearningPrompt Engineering
AskPDF
Jun 15, 2026cs.AI

A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions

Policy gradient algorithms for language models optimize the same objective J(θ)=E∗τ∼p∗θ(τ)[R(τ)]J(θ) = \mathbb{E}*{τ\sim p*θ(τ)}[R(τ)], which has exactly two factors: the trajectory probability pθ(τ)p_θ(τ) and the reward R(τ)R(τ). Every method from REINFORCE to PPO to GRPO and their descendants modifies one or both factors to address a specific failure in the preceding formulation. Existing surveys organize these methods by domain or chronology, which obscures the rationale behind each design choice and the precise location of its intervention within the gradient estimator. This survey revisits the landscape of LLM policy optimization from J(θ)J(θ) on first principles and uses the trajectory side, induced by pθ(τ)p_θ(τ), and the reward side, induced by R(τ)R(τ), as the two axes along which methods are located. It covers the path from REINFORCE and PPO to GRPO, as well as post-GRPO variants, Agentic RL, and GRPO-OPD. The resulting framework is unified, diagnostic, and extensible: it analyzes methods from a shared objective, identifies which side each method modifies and why, and applies the same trajectory and reward axes across these settings. Across these settings, the framework also exposes compound failures that no single-side fix resolves and that therefore require joint design of the trajectory side and the reward side. The boundary cases and coupled failures identified by this map mark where existing solutions run out and provide a principled starting point for designing the next generation of LLM policy optimization algorithms.
Jianghan Shen, Siqi Luo, Yue Li +9
Group Relative Policy OptimizationExtended VersionFirst-Principles Calculation
AskPDF
Jan 17, 2026cs.LG

R2^2PO: Decoupling Rollout and Inference Policies for LLM Reasoning

Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide with the one producing inference responses. We argue that this is a misleading inductive bias: the optimization-optimal trajectory distribution favors informative gradients, whereas the inference-optimal response distribution emphasizes accuracy and consistency. Forcing both into a single policy entangles their gradients and suppresses exploration. We propose R2^2PO (Residual Rollout Policy Optimization), which attaches a lightweight Residual Rollout-Head atop the policy to decouple training trajectories from inference responses, diversifying rollouts during training while keeping inference generation intact. Experiments show that R2^2PO consistently outperforms baselines, with average accuracy gains of 3.4% on MATH-500 and 1.3% on APPS, alongside more diverse rollouts and reduced length bias. Our code is available at https://github.com/RRPO-ARR/Code.
Jingchu Wang, Bingbing Xu, Yige Yuan +4
Large Language Model ReasoningAutoregressive RolloutRolloutInference EngineInferringTrajectory Optimization
AskPDF