Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement

• URL: http://arxiv.org/abs/2609.16800v1
• Date: Tue, 15 Sep 2026 08:06:17 GMT
• Title: Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement
• Abstract summary: We propose Dynamic Retrieval-based Policy Generation (DRPG), a framework that integrates memory-based retrieval with a dynamic policy generator.<n>We evaluate DRPG across six benchmarks spanning text-to-answer, question answering, medical diagnosis, and Python programming.<n>We find that DRPG's policy generation is robust to retrieval strategy, operates effectively without prior policy continuity, and can leverage smaller or cross-family models as cost-efficient policy generators.
• Score: 22.481667463025214
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have achieved remarkable progress across diverse domains, but continual adaptation to evolving tasks and environments remains a key challenge. Existing memory-augmented approaches retrieve individual past examples as direct references, but do not explicitly synthesize actionable strategies from them, causing the same types of errors to recur. We propose Dynamic Retrieval-based Policy Generation (DRPG), a framework that integrates memory-based retrieval with a dynamic policy generator, leveraging historical data and environment feedback to produce task-specific policies for continual LLM improvement. We evaluate DRPG across six benchmarks spanning text-to-SQL, question answering, medical diagnosis, and Python programming, using seven LLMs from both proprietary and open-weight families. DRPG outperforms strong baselines across most datasets and models. Further analysis demonstrates that DRPG's policy generation is robust to retrieval strategy, operates effectively without prior policy continuity, and can leverage smaller or cross-family models as cost-efficient policy generators. We also find that the benefit of policy-level guidance depends on task characteristics, offering practical insights into when and under what conditions this mechanism is most effective.

Related papers

• OpenLoopEvolve: A Verifiable Self-Evolution Framework for Loop Policies in Long-Horizon Complex Tasks [17.773038952370865]
  This paper presents OpenLoopEvolve (OLE), a self-evolution framework centered on the Loop Policy.<n>OLE represents an agent's observation, planning, memory, action, verification, recovery, stopping, and budget control as portable policy assets with versions and lineages.<n>Online mode triggers candidate generation based on feedback from continuous operation, whereas the offline mode searches for candidate policies from archived traces and failure evidence.
  arXiv  Detail & Related papers  (2026-08-10T09:57:26Z)
• LLM-Guided Evolutionary Search for Constraint Model Reformulation to Improve Solver Efficiency [5.774119507201688]
  Large Language Models (LLMs) can produce correct models from natural language, but even a correct model can be expensive to solve.<n>We use an evolutionary framework in which an LLM proposes candidate reformulations that are verified and benchmarked against the user-defined baseline model.<n>Existing retention strategies prioritize recency or performance, but do not explicitly diversify the context.<n>We systematically evaluate the strategies on eight CSPLib problems using validation-based final model selection.
  arXiv  Detail & Related papers  (2026-07-30T14:21:55Z)
• Policy-Conditioned Policies for Multi-Agent Task Solving [53.67744322553693]
  In this work, we propose a paradigm shift that bridges the gap by representing policies as human-interpretable source code.<n>We reformulate the learning problem by utilizing Large Language Models (LLMs) as approximate interpreters.<n>We formalize this process as textitProgrammatic Iterated Best Response (PIBR), an algorithm where the policy code is optimized by textual gradients.
  arXiv  Detail & Related papers  (2025-12-24T07:42:10Z)
• EXPO: Stable Reinforcement Learning with Expressive Policies [74.30151915786233]
  We propose a sample-efficient online reinforcement learning algorithm to maximize value with two parameterized policies.<n>Our approach yields up to 2-3x improvement in sample efficiency on average over prior methods.
  arXiv  Detail & Related papers  (2025-07-10T17:57:46Z)
• Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models [79.2162092822111]
  We systematically evaluate reinforcement learning (RL) and control-based methods on a suite of navigation tasks.<n>We employ a latent dynamics model using the Joint Embedding Predictive Architecture (JEPA) and employ it for planning.<n>Our results show that model-free RL benefits most from large amounts of high-quality data, whereas model-based planning generalizes better to unseen layouts.
  arXiv  Detail & Related papers  (2025-02-20T18:39:41Z)
• IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation [3.7584322469996896]
  IMLE Policy is a novel behaviour cloning approach based on Implicit Maximum Likelihood Estimation (IMLE)<n>It excels in low-data regimes, effectively learning from minimal demonstrations and requiring 38% less data on average to match the performance of baseline methods in learning complex multi-modal behaviours.<n>We validate our approach across diverse manipulation tasks in simulated and real-world environments, showcasing its ability to capture complex behaviours under data constraints.
  arXiv  Detail & Related papers  (2025-02-17T23:22:49Z)
• Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs [23.357843519762483]
  Recent studies have demonstrated that leveraging the Retrieval-Augmented Generation framework, combined with Knowledge Graphs, robustly enhances the reasoning capabilities of Large language models.<n>We introduce a Multi-objective Multi-Armed Bandit enhanced RAG framework, supported by multiple retrieval methods with diverse capabilities.<n>Our method significantly outperforms baseline methods in non-stationary settings while achieving state-of-the-art performance in stationary environments.
  arXiv  Detail & Related papers  (2024-12-10T15:56:03Z)
• DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation [53.62727171363384]
  We introduce a novel reasoning principle: Dynamic Reflection with Divergent Thinking. Our methodology is dynamic reflection, a process that emulates human learning through probing, critiquing, and reflecting. We evaluate our approach on three datasets using six pre-trained LLMs.
  arXiv  Detail & Related papers  (2023-12-18T16:41:22Z)
• Reparameterized Policy Learning for Multimodal Trajectory Optimization [61.13228961771765]
  We investigate the challenge of parametrizing policies for reinforcement learning in high-dimensional continuous action spaces. We propose a principled framework that models the continuous RL policy as a generative model of optimal trajectories. We present a practical model-based RL method, which leverages the multimodal policy parameterization and learned world model.
  arXiv  Detail & Related papers  (2023-07-20T09:05:46Z)
• Latent-Variable Advantage-Weighted Policy Optimization for Offline RL [70.01851346635637]
  offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. In practice, offline datasets are often heterogeneous, i.e., collected in a variety of scenarios. We propose to leverage latent-variable policies that can represent a broader class of policy distributions. Our method improves the average performance of the next best-performing offline reinforcement learning methods by 49% on heterogeneous datasets.
  arXiv  Detail & Related papers  (2022-03-16T21:17:03Z)
• Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning [83.66080019570461]
  We propose two environment-agnostic, algorithm-agnostic quantitative metrics for task difficulty. We show that these metrics have higher correlations with normalized task solvability scores than a variety of alternatives. These metrics can also be used for fast and compute-efficient optimizations of key design parameters.
  arXiv  Detail & Related papers  (2021-03-23T17:49:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.