LLM-Guided RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

This field studies how large language models can help reinforcement-learning agents learn useful behavior, and how reinforcement learning can improve language models’ reasoning and tool use. Common approaches use models to propose or refine rewards, provide selective hints or curricula, generate plans and reusable skills, or supply semantic knowledge that is distilled into policies. Work spans sparse-reward robotics and game environments, multi-agent coordination, autonomous driving, and language-model reasoning tasks. A central challenge is making guidance reliable and transferable: changing or inaccurate rewards can destabilize learning, and gains against model-based judges may reflect reward hacking rather than better real-world behavior.

Latest papers

140 papers19 papers in the last four weeks, up 46% on the four weeks before. 0.1% of all new papers.

May 5, 2026

Discovering Reinforcement Learning Interfaces with Large Language Models

Reinforcement learning systems rely on environment interfaces that specify observations and reward functions, yet constructing these interfaces for new tasks often requires substantial manual effort. While recent work has automated reward design using large language models (LLMs), these approaches assume fixed observations and do not address the broader challenge of synthesizing complete task interfaces. We study RL task interface discovery from raw simulator state, where both observation mappings and reward functions must be generated. We propose LIMEN (Code available at https://github.com/Lossfunk/LIMEN), a LLM guided evolutionary framework that produces candidate interfaces as executable programs and iteratively refines them using policy training feedback. Across novel discrete gridworld tasks and continuous control domains spanning locomotion and manipulation, joint evolution of observations and rewards discovers effective interfaces given only a trajectory-level success metric, while optimizing either component alone fails on at least one domain. These results demonstrate that automatic construction of RL interfaces from raw state can substantially reduce manual engineering and that observation and reward components often benefit from co-design, as single-component optimization fails catastrophically on at least one domain in our evaluation suite.

Akshat Singh Jaswal, Ashish Baghel, Paras Chopra

Lossfunk

Reinforcement Learning LLM-Guided RL Reward Design for RL

May 4, 2026

ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring

Online advertising governance faces significant challenges due to the non-stationary nature of regulatory policies, where emerging mandates (e.g., restrictions on education or aesthetic anxiety) create severe label inconsistencies and reasoning ambiguities in historical datasets. In this paper, we propose ARGUS, a policy-adaptive governance system that enables evolving reinforcement through multi-agent adversarial umpiring. ARGUS addresses the sparsity of new policy data by employing a three-stage framework: (1) Policy Seeding for initial perception; (2) Adversarial Label Rectification, which utilizes a

Prosecutor-Defender-Umpire'' architecture to resolve conflicts between stale labels and new mandates; and (3) Latent Knowledge Discovery, which employs a tripartite dialectical discussion to unearth sophisticated,

gray-area'' violations. By leveraging RAG-enhanced policy knowledge and Chain-of-Thought synthesis as dynamic rewards for reinforcement learning, ARGUS synchronizes its reasoning pathways with evolving regulations. Extensive experiments on both industrial and public datasets demonstrate that ARGUS significantly outperforms traditional fine-tuning baselines, achieving superior policy-adaptive learning with minimal gold data.

Deyi Ji, Junyu Lu, Xuanyi Liu +7

Tencent · Dalian University of Technology · Peking University +2

Non-Stationary RL Online Advertising LLM-Guided RL

May 2, 2026

Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data

Learning constraint-satisfying policies from offline data without risky online interaction is crucial for safety-critical decision making. Conventional methods typically learn cost value functions from abundant unsafe samples to define safety boundaries and penalize violations. However, in high-stakes scenarios, risky trial-and-error is infeasible, yielding datasets with few or no unsafe samples. Under this limitation, existing approaches often treat all data as uniformly safe, overlooking safe-but-infeasible states - states that currently satisfy constraints but inevitably violate them within a few steps - leading to deployment failures. Drawing inspiration from the concept of knowledge-data integration, we leverage large language models (LLMs) to incorporate natural language knowledge into the policy to address this challenge. Specifically, we propose PROCO, a model-based offline safe reinforcement learning (RL) framework tailored to datasets largely free of violations. PROCO first learns a dynamics model from offline data and constructs a conservative cost function by grounding natural-language knowledge of unsafe states in LLMs, enabling risk estimation even without observed violations. Using the cost function and learned model, PROCO performs model-based rollouts to synthesize diverse counterfactual unsafe samples, supporting reliable feasibility identification and feasibility-guided policy learning. Across a range of Safety-Gymnasium tasks with exclusively safe or minimally risky training data, PROCO integrates seamlessly with a variety of offline safe RL algorithms and consistently demonstrates reduced constraint violations and improved safety performance compared to both the original methods and other behavior cloning baselines.

Ruiqi Xue, Lei Yuan, Kainuo Cheng +2

National Key Laboratory for Novel Software Technology, Nanjing University · School of Artificial Intelligence, Nanjing University · Polixir Technologies +2

LLM-Guided RL Offline RL Safe RL Model-Based RL

May 1, 2026

PPO guided Agentic Pipeline for Adaptive Prompt Selection and Test Case Generation

Developing effective test cases capable of thoroughly exercising large-scale software systems is inherently difficult, especially if such systems have voluminous, complex, and deeply nested source codes. In this work, we present a novel approach for generating test cases using a reinforcement learning-driven agentic framework where Proximal Policy Optimization (PPO) is coupled with an LLM engine to guide prompt selection during test generation. Our approach consists of two phases. In Phase I, the ToT-guided optimization agent partitions and minimizes the source code by removing redundancies without changing the functional behavior of the source code. In Phase II, a PPO-based policy network is trained to solve the problem of selecting prompts among eight different prompting techniques, such as Boundary Value Analysis, Random Fuzzing, etc., based on the inputted 11-dimensional state vector representing the source code complexity metrics and live coverage metrics to direct the LLM engine towards exploring unvisited paths in the program. The PPO agent receives rewards based on a combination of increases in line and branch coverages, penalties for unexplored branches, and rewards for reducing source code length. From experiments conducted on twenty benchmark programs, it is evident that the proposed approach, PPO-LLM, outperforms CBMC, kS-LLM, and kS-LLM++ in terms of branch and line coverage in almost all cases, for various loop bound values ranging from BOUND~~1 to BOUND~~2000. While at BOUND~1, the coverage of branches is 100% using PPO-LLM on the PALS suite, in comparison, it is around 86.8% using kS-LLM++. This confirms that adaptive prompt selection driven by PPO substantially outperforms static prompting strategies on PALS type programs.

Gourisetty Venkata Sai Koushik, Dama Aditya, Mahankali Harish Sai +3

Department of Computer Science and Engineering, SRM University AP

Automated Software Testing LLM-Guided RL Automated Test Generation

Apr 30, 2026

RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses

Large language models (LLMs) make reward design in reinforcement learning substantially more scalable, but generated rewards are not automatically reliable training objectives. Existing work has focused primarily on generating, evolving, or selecting reward candidates, while paying less attention to when such candidates can be verified and deployed during policy optimization. We study this deployment-time problem by treating generated rewards as reward hypotheses whose utility depends on the competence of the current policy and the phase of training. We propose RHyVE, a competence-aware verification and phase-aware deployment protocol that compares small sets of reward hypotheses from shared policy checkpoints using short-horizon fork verification. Our experiments show that reward rankings are unreliable at low competence but become informative after task-dependent thresholds. On a sparse manipulation task, phase-aware deployment improves peak and retained performance under a locked protocol. Updated LLM-generated reward-candidate experiments show candidate-family-dependent behavior: generated pools can exhibit phase-dependent winner changes, but no fixed warm-up schedule is universally optimal. Held-out schedule selection, conservative selector baselines, compute-matched controls, and scale controls further show that RHyVE is best understood as a verification-informed deployment protocol rather than a universal scheduler. Dense and all-failure boundary experiments delimit the scope of the method. Together, these results suggest that reward generation and reward deployment should be studied as coupled problems: generated rewards must be verified and deployed under changing policy competence.

Feiyu Wu, Xu Zheng, Zhuocheng Wang +2

School of Cyber Engineering, Xidian University

Reinforcement Learning LLM-Guided RL Robotic RL Reward Design for RL

Apr 25, 2026

Bridging Reasoning and Action: Hybrid LLM-RL Framework for Efficient Cross-Domain Task-Oriented Dialogue

Cross-domain task-oriented dialogue requires reasoning over implicit and explicit feasibility constraints while planning long-horizon, multi-turn actions. Large language models (LLMs) can infer such constraints but are unreliable over long horizons, while Reinforcement learning (RL) optimizes long-horizon behavior yet cannot recover constraints from raw dialogue. Naively coupling LLMs with RL is therefore brittle: unverified or unstructured LLM outputs can corrupt state representations and misguide policy learning. Motivated by this, we propose Verified LLM-Knowledge empowered RL (VLK-RL), a hybrid framework that makes LLM-derived constraint reasoning usable for RL. VLK-RL first elicits candidate constraints with an LLM and then verifies them via a dual-role cross-examination procedure to suppress hallucinations and cross-turn inconsistencies. The verified constraints are mapped into ontology-aligned slot-value representations, yielding a structured, constraint-aware state for RL policy optimization. Experiments across multiple benchmarks demonstrate that VLK-RL significantly improves generalization and robustness, outperforming strong single-model baselines on long-horizon tasks.

Yangyang Zhao, Linfan Dai, Li Cai +2

School of Computer Science and Technology, Changsha University of Science and Technology · School of Computer Science and Engineering, Central South University · Text Computing and Cognitive Intelligence MOE Engineering Research Center, Guizhou University +2

Constrained RL LLM-Guided RL Conversational Agents Long-Horizon LLM Agents

Apr 22, 2026

Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning

We introduce SuperIgor, a framework for instruction-following tasks. Unlike prior methods that rely on predefined subtasks, SuperIgor enables a language model to generate and refine high-level plans through a self-learning mechanism, reducing the need for manual dataset annotation. Our approach involves iterative co-training: an RL agent is trained to follow the generated plans, while the language model adapts and modifies these plans based on RL feedback and preferences. This creates a feedback loop where both the agent and the planner improve jointly. We validate our framework in environments with rich dynamics and stochasticity. Results show that SuperIgor agents adhere to instructions more strictly than baseline methods, while also demonstrating strong generalization to previously unseen instructions.

Zoya Volovikova, Nikita Sorokin, Dmitriy Lukashevskiy +2

1AXXX · 2MIRAI

Reinforcement Learning LLM-Guided RL Goal-Conditioned RL LLM Agent Planning

Apr 22, 2026

Scaling Self-Play with Self-Guidance

LLM self-play algorithms are notable in that, in principle, nothing bounds their learning: a Conjecturer model creates problems for a Solver, and both improve together. However, in practice, existing LLM self-play methods do not scale well with large amounts of compute, instead hitting learning plateaus. We argue this is because over long training runs, the Conjecturer learns to hack its reward, collapsing to artificially complex problems that do not help the Solver improve. To overcome this, we introduce Self-Guided Self-Play (SGS), a self-play algorithm in which the language model itself guides the Conjecturer away from degeneracy. In SGS, the model takes on three roles: Solver, Conjecturer, and a Guide that scores synthetic problems by their relevance to unsolved target problems and how clean and natural they are, providing supervision against Conjecturer collapse. Our core hypothesis is that language models can assess whether a subproblem is useful for achieving a goal. We evaluate the scaling properties of SGS by running training for significantly longer than prior works and by fitting scaling laws to cumulative solve rate curves. Applying SGS to formal theorem proving in Lean4, we find that it surpasses the asymptotic solve rate of our strongest RL baseline in fewer than 80 rounds of self-play and enables a 7B parameter model, after 200 rounds of self-play, to solve more problems than a 671B parameter model pass@4.

Luke Bailey, Kaiyue Wen, Kefan Dong +2

Stanford University

Self-Play RL Automated Theorem Proving LLM-Guided RL Language Model Self-Improvement

Apr 19, 2026

Do LLM-derived graph priors improve multi-agent coordination?

Multi-agent reinforcement learning (MARL) is crucial for AI systems that operate collaboratively in distributed and adversarial settings, particularly in multi-domain operations (MDO). A central challenge in cooperative MARL is determining how agents should coordinate: existing approaches must either hand-specify graph topology, rely on proximity-based heuristics, or learn structure entirely from environment interaction; all of which are brittle, semantically uninformed, or data-intensive. We investigate whether large language models (LLMs) can generate useful coordination graph priors for MARL by using minimal natural language descriptions of agent observations to infer latent coordination patterns. These priors are integrated into MARL algorithms via graph convolutional layers within a graph neural network (GNN)-based pipeline, and evaluated on four cooperative scenarios from the Multi-Agent Particle Environment (MPE) benchmark against baselines spanning the full spectrum of coordination modeling, from independent learners to state-of-the-art graph-based methods. We further ablate across five compact open-source LLMs to assess the sensitivity of prior quality to model choice. Our results provide the first quantitative evidence that LLM-derived graph priors can enhance coordination and adaptability in dynamic multi-agent environments, and demonstrate that models as small as 1.5B parameters are sufficient for effective prior generation.

Nikunj Gupta, Rajgopal Kannan, Viktor Prasanna

University of Southern California, Los Angeles, California, United States · DEVCOM ARL Army Research Oﬀice, Los Angeles, California, United States

Multi-Agent Coordination LLM-Guided RL Multi-Agent Systems Cooperative MARL

Apr 18, 2026

GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning

Neuro-symbolic Reinforcement Learning (NeSy-RL) combines symbolic reasoning with gradient-based optimization to achieve interpretable and generalizable policies. Relational concepts, such as "left of" or "close by", serve as foundational building blocks that structure how agents perceive and act. However, conventional approaches require human experts to manually define these concepts, limiting adaptability since concept semantics vary across environments. We propose GRAIL (Grounding Relational Agents through Interactive Learning), a framework that autonomously grounds relational concepts through environmental interaction. GRAIL leverages large language models (LLMs) to provide generic concept representations as weak supervision, then refines them to capture environment-specific semantics. This approach addresses both sparse reward signals and concept misalignment prevalent in underdetermined environments. Experiments on the Atari games Kangaroo, Seaquest, and Skiing demonstrate that GRAIL matches or outperforms agents with manually crafted concepts in simplified settings, and reveals informative trade-offs between reward maximization and high-level goal completion in the full environment.

Hikaru Shindo, Henri Rößler, Quentin Delfosse +1

Technical University of Darmstadt · Google Intrinsic · German Research Center for Artificial Intelligence (DFKI) +1

Reinforcement Learning LLM-Guided RL Neuro-Symbolic RL

Apr 15, 2026

Chain of Uncertain Rewards with Large Language Models for Reinforcement Learning

Designing effective reward functions is a cornerstone of reinforcement learning (RL), yet it remains a challenging and labor-intensive process due to the inefficiencies and inconsistencies inherent in traditional methods. Existing methods often rely on extensive manual design and evaluation steps, which are prone to redundancy and overlook local uncertainties at intermediate decision points. To address these challenges, we propose the Chain of Uncertain Rewards (CoUR), a novel framework that integrates large language models (LLMs) to streamline reward function design and evaluation in RL environments. Specifically, our CoUR introduces code uncertainty quantification with a similarity selection mechanism that combines textual and semantic analyses to identify and reuse the most relevant reward function components. By reducing redundant evaluations and leveraging Bayesian optimization on decoupled reward terms, CoUR enables a more efficient and robust search for optimal reward feedback. We comprehensively evaluate CoUR across nine original environments from IsaacGym and all 20 tasks from the Bidexterous Manipulation benchmark. The experimental results demonstrate that CoUR not only achieves better performance but also significantly lowers the cost of reward evaluations.

Shentong Mo

Carnegie Mellon University

Reward Design for RL LLM-Guided RL Robotic RL

Apr 14, 2026

KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance

RLVR improves reasoning in large language models, but its effectiveness is often limited by severe reward sparsity on hard problems. Recent hint-based RL methods mitigate sparsity by injecting partial solutions or abstract templates, yet they typically scale guidance by adding more tokens, which introduce redundancy, inconsistency, and extra training overhead. We propose KnowRL (Knowledge-Guided Reinforcement Learning), an RL training framework that treats hint design as a minimal-sufficient guidance problem. During RL training, KnowRL decomposes guidance into atomic knowledge points (KPs) and uses Constrained Subset Search (CSS) to construct compact, interaction-aware subsets for training. We further identify a pruning interaction paradox -- removing one KP may help while removing multiple such KPs can hurt -- and explicitly optimize for robust subset curation under this dependency structure. We train KnowRL-Nemotron-1.5B from OpenMath-Nemotron-1.5B. Across eight reasoning benchmarks at the 1.5B scale, KnowRL-Nemotron-1.5B consistently outperforms strong RL and hinting baselines. Without KP hints at inference, KnowRL-Nemotron-1.5B reaches 70.08 average accuracy, already surpassing Nemotron-1.5B by +9.63 points; with selected KPs, performance improves to 74.16, establishing a new state of the art at this scale. The model, curated training data, and code are publicly available at https://github.com/Hasuer/KnowRL.

Linhao Yu, Tianmeng Yang, Siyu Ding +8

TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China · Baidu Inc. · Institute of Information Engineering, Chinese Academy of Sciences.

RL for Language Model Reasoning LLM Reasoning RL for Language Models LLM-Guided RL

Apr 13, 2026

When Valid Signals Fail: Regime Boundaries Between LLM Features and RL Trading Policies

Can large language models (LLMs) generate continuous numerical features that improve reinforcement learning (RL) trading agents? We build a modular pipeline where a frozen LLM serves as a stateless feature extractor, transforming unstructured daily news and filings into a fixed-dimensional vector consumed by a downstream PPO agent. We introduce an automated prompt-optimization loop that treats the extraction prompt as a discrete hyperparameter and tunes it directly against the Information Coefficient - the Spearman rank correlation between predicted and realized returns - rather than NLP losses. The optimized prompt discovers genuinely predictive features (IC above 0.15 on held-out data). However, these valid intermediate representations do not automatically translate into downstream task performance: during a distribution shift caused by a macroeconomic shock, LLM-derived features add noise, and the augmented agent under-performs a price-only baseline. In a calmer test regime the agent recovers, yet macroeconomic state variables remain the most robust driver of policy improvement. Our findings highlight a gap between feature-level validity and policy-level robustness that parallels known challenges in transfer learning under distribution shift.

Zhengzhe Yang

Independent Researcher

LLM-Guided RL Reinforcement Learning Robust RL Prompt Optimization

Apr 10, 2026

C $^2$ T: Captioning-Structure and LLM-Aligned Common-Sense Reward Learning for Traffic--Vehicle Coordination

State-of-the-art (SOTA) urban traffic control increasingly employs Multi-Agent Reinforcement Learning (MARL) to coordinate Traffic Light Controllers (TLCs) and Connected Autonomous Vehicles (CAVs). However, the performance of these systems is fundamentally capped by their hand-crafted, myopic rewards (e.g., intersection pressure), which fail to capture high-level, human-centric goals like safety, flow stability, and comfort. To overcome this limitation, we introduce C2T, a novel framework that learns a common-sense coordination model from traffic-vehicle dynamics. C2T distills "common-sense" knowledge from a Large Language Model (LLM) into a learned intrinsic reward function. This new reward is then used to guide the coordination policy of a cooperative multi-intersection TLC MARL system on CityFlow-based multi-intersection benchmarks. Our framework significantly outperforms strong MARL baselines in traffic efficiency, safety, and an energy-related proxy. We further highlight C2T's flexibility in principle, allowing distinct "efficiency-focused" versus "safety-focused" policies by modifying the LLM prompt.

Yuyang Chen, Kaiyan Zhao, Yiming Wang +3

The State Key Laboratory of Internet of Things for Smart City, University of Macau · Wuhan University · Computer and Information Science, University of Macau +1

Traffic Signal Control Multi-Agent Coordination Cooperative MARL LLM-Guided RL

Apr 9, 2026

ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer

Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer, they are often constrained by predefined, discrete class systems, limiting their adaptability to novel or compositional task variations. We propose a significantly more generalized approach, replacing discrete latent variables with natural language conditioning via a text-conditioned Variational Autoencoder (VAE). Our core innovation utilizes a Large Language Model (LLM) as a dynamic semantic operator at test time. Rather than relying on rigid rules, our agent queries the LLM to semantically remap the description of the current observation to align with the source task. This source-aligned caption conditions the VAE to generate an imagined state compatible with the agent's original training, enabling direct policy reuse. By harnessing the flexible reasoning capabilities of LLMs, our approach achieves zero-shot transfer across a broad spectrum of complex and truly novel analogous tasks, moving beyond the limitations of fixed category mappings. Code and videos are available here.

Ajsal Shereef Palattuparambil, Thommen George Karimpanal, Santu Rana

Applied Artificial Intelligence Initiative, Deakin University, Waurn Ponds, Geelong · School of IT, Deakin University, Waurn Ponds, Geelong

Zero-Shot RL Zero-Shot Policy Transfer Reinforcement Learning Transfer Learning Generalization in RL LLM-Guided RL

Apr 9, 2026

3DrawAgent: Teaching LLM to Draw in 3D with Early Contrastive Experience

Sketching in 3D space enables expressive reasoning about shape, structure, and spatial relationships, yet generating 3D sketches through natural language remains a major challenge. In this work, we introduce 3DrawAgent, a training-free, language-driven framework for 3D sketch generation that leverages large language models (LLMs) to sequentially draw 3D Bezier curves under geometric feedback. Unlike prior 2D sketch agents, our method introduces a relative experience optimization strategy that adapts the recently proposed Group Reward Policy Optimization (GRPO) paradigm. Instead of relying on explicit ground-truth supervision, we construct pairwise comparisons among generated sketches, with each pair consisting of a relatively better and a worse result based on CLIP-based perceptual rewards and LLM-based fine-grained qualitative assessment. These experiences are then used to iteratively refine the prior knowledge of 3D drawing, enabling black-box reinforcement of the model's 3D awareness. This design allows our model to self-improve its spatial understanding and drawing quality without parameter updates. Experiments show that 3DrawAgent can generate complex and coherent 3D Bezier sketches from diverse textual prompts, exhibit emergent geometric reasoning, and generalize to novel shapes, establishing a new paradigm for advancing the field of training-free 3D sketch intelligence.

Hongcan Xiao, Xinyue Xiao, Yilin Wang +2

Beijing University of Posts and Telecommunications · Jiangnan University · HaoHan Data

3D Spatial Reasoning RL for Generative Models LLM-Guided RL

Apr 7, 2026

CuraLight: Debate-Guided Data Curation for LLM-Centered Traffic Signal Control

Traffic signal control (TSC) is a core component of intelligent transportation systems (ITS), aiming to reduce congestion, emissions, and travel time. Recent approaches based on reinforcement learning (RL) and large language models (LLMs) have improved adaptivity, but still suffer from limited interpretability, insufficient interaction data, and weak generalization to heterogeneous intersections. This paper proposes CuraLight, an LLM-centered framework where an RL agent assists the fine-tuning of an LLM-based traffic signal controller. The RL agent explores traffic environments and generates high-quality interaction trajectories, which are converted into prompt-response pairs for imitation fine-tuning. A multi-LLM ensemble deliberation system further evaluates candidate signal timing actions through structured debate, providing preference-aware supervision signals for training. Experiments conducted in SUMO across heterogeneous real-world networks from Jinan, Hangzhou, and Yizhuang demonstrate that CuraLight consistently outperforms state-of-the-art baselines, reducing average travel time by 5.34 percent, average queue length by 5.14 percent, and average waiting time by 7.02 percent. The results highlight the effectiveness of combining RL-assisted exploration with deliberation-based data curation for scalable and interpretable traffic signal control.

Qing Guo, Xinhang Li, Junyu Chen +4

School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China · Beijing Big Data Center, Beijing, China

Traffic Signal Control Language Model-Based Control Training Data Curation LLM-Guided RL

Apr 4, 2026

When Adaptive Rewards Hurt: Causal Probing and the Switching-Stability Dilemma in LLM-Guided LEO Satellite Scheduling

Adaptive reward design for deep reinforcement learning (DRL) in multi-beam LEO satellite scheduling is motivated by the intuition that regime-aware reward weights should outperform static ones. We systematically test this intuition and uncover a switching-stability dilemma: near-constant reward weights (342.1 Mbps) outperform carefully-tuned dynamic weights (103.3+/-96.8 Mbps) because PPO requires a quasistationary reward signal for value function convergence. Weight adaptation-regardless of quality-degrades performance by repeatedly restarting convergence. To understand why specific weights matter, we introduce a single-variable causal probing method that independently perturbs each reward term by +/-20% and measures PPO response after 50k steps. Probing reveals counterintuitive leverage: a +20% increase in the switching penalty yields +157 Mbps for polar handover and +130 Mbps for hot-cold regimes-findings inaccessible to human experts or trained MLPs without systematic probing. We evaluate four MDP architect variants (fixed, rule-based, learned MLP, finetuned LLM) across known and novel traffic regimes. The MLP achieves 357.9 Mbps on known regimes and 325.2 Mbps on novel regimes, while the fine-tuned LLM collapses to 45.3+/-43.0 Mbps due to weight oscillation rather than lack of domain knowledge-output consistency, not knowledge, is the binding constraint. Our findings provide an empirically-grounded roadmap for LLM-DRL integration in communication systems, identifying where LLMs add irreplaceable value (natural language intent understanding) versus where simpler methods suffice.

Yuanhang Li

Reward Design for RL LLM-Guided RL LEO Satellite Networks Non-Stationary RL

Apr 2, 2026

When to ASK: Uncertainty-Gated Language Assistance for Reinforcement Learning

Reinforcement learning (RL) agents often struggle with out-of-distribution (OOD) scenarios, leading to high uncertainty and random behavior. While language models (LMs) contain valuable world knowledge, larger ones incur high computational costs, hindering real-time use, and exhibit limitations in autonomous planning. We introduce Adaptive Safety through Knowledge (ASK), which combines smaller LMs with trained RL policies to enhance OOD generalization without retraining. ASK employs Monte Carlo Dropout to assess uncertainty and queries the LM for action suggestions only when uncertainty exceeds a set threshold. This selective use preserves the efficiency of existing policies while leveraging the language model's reasoning in uncertain situations. In experiments on the FrozenLake environment, ASK shows no improvement in-domain, but demonstrates robust navigation in transfer tasks, achieving a reward of 0.95. Our findings indicate that effective neuro-symbolic integration requires careful orchestration rather than simple combination, highlighting the need for sufficient model scale and effective hybridization mechanisms for successful OOD generalization.

Juarez Monteiro, Nathan Gavenski, Gianlucca Zuin +1

Kunumi Institute Belo Horizonte, MG, Brazil · King’s College London London, England, UK

Uncertainty Estimation in RL Reinforcement Learning LLM-Guided RL Generalization in RL Robust RL

Apr 1, 2026

Learning to Hint for Reinforcement Learning

Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a group receive the same reward, the group yields zero relative advantage and thus no learning signal. For example, if a question is too hard for the reasoner, all sampled rollouts can be incorrect and receive zero reward. Recent work addresses this issue by adding hints or auxiliary scaffolds to such hard questions so that the reasoner produces mixed outcomes and recovers a non-zero update. However, existing hints are usually fixed rather than adapted to the current reasoner, and a hint that creates learning signal under the hinted input does not necessarily improve the no-hint policy used at test time. To this end, we propose Hint Learning for Reinforcement Learning (HiLL), a framework that jointly trains a hinter policy and a reasoner policy during RL. For each hard question, the hinter generates hints online conditioned on the current reasoner's incorrect rollout, allowing hint generation to adapt to the reasoner's evolving errors. We further introduce hint reliance, which measures how strongly correct hinted trajectories depend on the hint. We derive a transferability result showing that lower hint reliance implies stronger transfer from hinted success to no-hint success, and we use this result to define a transfer-weighted reward for training the hinter. Therefore, HiLL favors hints that not only recover informative GRPO groups, but also produce signals that are more likely to improve the original no-hint policy. Experiments across multiple benchmarks show that HiLL consistently outperforms GRPO and prior hint-based baselines, demonstrating the value of adaptive and transfer-aware hint learning for RL. The code is available at https://github.com/Andree-9/HiLL.

Yu Xia, Canwen Xu, Zhewei Yao +2

University of California, San Diego · Snowflake AI Research

Reinforcement Learning RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards LLM-Guided RL

Mar 31, 2026

Learning to Play Blackjack: A Curriculum Learning Perspective

Reinforcement Learning (RL) agents often struggle with efficiency and performance in complex environments. We propose a novel framework that uses a Large Language Model (LLM) to dynamically generate a curriculum over available actions, enabling the agent to incorporate each action individually. We apply this framework to the game of Blackjack, where the LLM creates a multi-stage training path that progressively introduces complex actions to a Tabular Q-Learning and a Deep Q-Network (DQN) agent. Our evaluation in a realistic 8-deck simulation over 10 independent runs demonstrates significant performance gains over standard training methods. The curriculum-based approach increases the DQN agent's average win rate from 43.97% to 47.41%, reduces the average bust rate from 32.9% to 28.0%, and accelerates the overall workflow by over 74%, with the agent's full training completing faster than the baseline's evaluation phase alone. These results validate that LLM-guided curricula can build more effective, robust, and efficient RL agents.

Amirreza Alasti, Efe Erdal, Yücel Celik +1

Leibniz University Hannover, Hannover, Germany · Leibniz AI Academy, Hannover, Germany

Curriculum RL LLM-Guided RL

Mar 31, 2026

Generalizable Dense Reward for Long-Horizon Robotic Tasks

Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilities, they often struggle with long-horizon tasks due to distribution shift and error accumulation. While reinforcement learning (RL) can finetune these models, it cannot work well across diverse tasks without manual reward engineering. We propose VLLR, a dense reward framework combining (1) an extrinsic reward from Large Language Models (LLMs) and Vision-Language Models (VLMs) for task progress recognition, and (2) an intrinsic reward based on policy self-certainty. VLLR uses LLMs to decompose tasks into verifiable subtasks and then VLMs to estimate progress to initialize the value function for a brief warm-up phase, avoiding prohibitive inference cost during full training; and self-certainty provides per-step intrinsic guidance throughout PPO finetuning. Ablation studies reveal complementary benefits: VLM-based value initialization primarily improves task completion efficiency, while self-certainty primarily enhances success rates, particularly on out-of-distribution tasks. On the CHORES benchmark covering mobile manipulation and navigation, VLLR achieves up to 56% absolute success rate gains over the pretrained policy, up to 5% gains over state-of-the-art RL finetuning methods on in-distribution tasks, and up to

10\%

gains on out-of-distribution tasks, all without manual reward engineering. Additional visualizations can be found in https://silongyong.github.io/vllr_project_page/

Silong Yong, Stephen Sheng, Carl Qi +6

Carnegie Mellon University · Amazon Robotics · UT Austin

Reinforcement Learning Long-Horizon Robotic Manipulation Robot Skill Learning Dense Reward RL Intrinsic Motivation LLM-Guided RL+3

Mar 30, 2026

Evolutionary Discovery of Reinforcement Learning Algorithms via Large Language Models

Reinforcement learning algorithms are defined by their learning update rules, which are typically hand-designed and fixed. We present an evolutionary framework for discovering reinforcement learning algorithms by searching directly over executable update rules that implement complete training procedures. The approach builds on REvolve, an evolutionary system that uses large language models as generative variation operators, and extends it from reward-function discovery to algorithm discovery. To promote the emergence of nonstandard learning rules, the search excludes canonical mechanisms such as actor--critic structures, temporal-difference losses, and value bootstrapping. Because reinforcement learning algorithms are highly sensitive to internal scalar parameters, we introduce a post-evolution refinement stage in which a large language model proposes feasible hyperparameter ranges for each evolved update rule. Evaluated end-to-end by full training runs on multiple Gymnasium benchmarks, the discovered algorithms achieve competitive performance relative to established baselines, including SAC, PPO, DQN, and A2C.

Alkis Sygkounas, Amy Loutfi, Andreas Persson

Machine Perception and Interaction Lab, Örebro University, Sweden

Automated Algorithm Discovery Evolutionary RL LLM-Guided RL Large Language Model-Guided Optimization Evolutionary Optimization

Mar 30, 2026

COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game

A central challenge in building continually improving agents is that training environments are typically static or manually constructed. This restricts continual learning and generalization beyond the training distribution. We address this with COvolve, a co-evolutionary framework that leverages large language models (LLMs) to generate both environments and agent policies, expressed as executable Python code. We model the interaction between environment and policy designers as a two-player zero-sum game, ensuring adversarial co-evolution in which environments expose policy weaknesses and policies adapt in response. This process induces an automated curriculum in which environments and policies co-evolve toward increasing complexity. To guarantee robustness and prevent forgetting as the curriculum progresses, we compute the mixed-strategy Nash equilibrium (MSNE) of the zero-sum game, thereby yielding a meta-policy. This MSNE meta-policy ensures that the agent does not forget to solve previously seen environments while learning to solve previously unseen ones. Experiments in urban driving, symbolic maze-solving, and geometric navigation showcase that COvolve produces progressively more complex environments. Our results demonstrate the potential of LLM-driven co-evolution to achieve open-ended learning without predefined task distributions or manual intervention.

Alkis Sygkounas, Rishi Hazra, Andreas Persson +2

Machine Perception and Interaction Lab, Örebro University, Sweden

Lifelong Learning Agents Self-Evolving Agents LLM-Guided RL Curriculum RL Reinforcement Learning

Mar 27, 2026

Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for multimodal large language models (MLLMs) have mainly focused on improving final answer correctness and strengthening visual grounding. However, a critical bottleneck remains: although models can attend to relevant visual regions, they often fail to effectively incorporate visual evidence into subsequent reasoning, leading to reasoning chains that are weakly grounded in visual facts. To address this issue, we propose Trajectory-Guided Reinforcement Learning (TGRL), which guides the policy model to integrate visual evidence into fine-grained reasoning processes using expert reasoning trajectories from stronger models. We further introduce token-level reweighting and trajectory filtering to ensure stable and effective policy optimization. Extensive experiments on multiple multimodal reasoning benchmarks demonstrate that TGRL consistently improves reasoning performance and effectively bridges the gap between visual perception and logical reasoning.

Jinda Lu, Junkang Wu, Jinghan Li +6

University of Science and Technology of China · Pecking University · Institute of Software, Chinese Academy of Sciences

RL for VLMs Multimodal Reasoning Visually Grounded Reasoning Reinforcement Learning with Verifiable Rewards LLM-Guided RL

Mar 25, 2026

LATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Control

Adaptive Traffic Signal Control (ATSC) aims to optimize traffic flow and minimize delays by adjusting traffic lights in real time. Recent advances in Multi-agent Reinforcement Learning (MARL) have shown promise for ATSC, yet existing approaches still suffer from limited representational capacity, often leading to suboptimal performance and poor generalization in complex and dynamic traffic environments. On the other hand, Large Language Models (LLMs) excel at semantic representation, reasoning, and analysis, yet their propensity for hallucination and slow inference speeds often hinder their direct application to decision-making tasks. To address these challenges, we propose a novel learning paradigm named LATS that integrates LLMs and MARL, leveraging the former's strong prior knowledge and inductive abilities to enhance the latter's decision-making process. Specifically, we introduce a plug-and-play teacher-student learning module, where a trained embedding LLM serves as a teacher to generate rich semantic features that capture each intersection's topology structures and traffic dynamics. A much simpler (student) neural network then learns to emulate these features through knowledge distillation in the latent space, enabling the final model to operate independently from the LLM for downstream use in the RL decision-making process. This integration significantly enhances the overall model's representational capacity across diverse traffic scenarios, thus leading to more efficient and generalizable control strategies. Extensive experiments across diverse traffic datasets empirically demonstrate that our method enhances the representation learning capability of RL models, thereby leading to improved overall performance and generalization over both traditional RL and LLM-only approaches. [...]

Yifeng Zhang, Peizhuo Li, Tingguang Zhou +2

Department of Mechanical Engineering, National University of Singapore

Traffic Signal Control LLM-Guided RL Multi-Agent Reinforcement Learning

Mar 25, 2026

Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning

Designing effective auxiliary rewards for cooperative multi-agent systems remains challenging, as misaligned incentives can induce suboptimal coordination, particularly when sparse task rewards provide insufficient grounding for coordinated behavior. This study introduces an autonomous reward design framework that uses large language models (LLMs) to synthesize executable reward programs from environment instrumentation. The procedure constrains candidate programs within a formal validity envelope and trains policies from scratch using Multi-Agent Proximal Policy Optimization (MAPPO) under a fixed computational budget. The candidates are then evaluated on the basis of their performance, and selection across generations solely based on the sparse task returns. The framework is evaluated in four Overcooked-AI layouts characterized by varying levels of corridor congestion, handoff dependencies, and structural asymmetries. The proposed reward design approach consistently yields higher task returns and delivery counts, with the most pronounced gains observed in environments dominated by interaction bottlenecks. Diagnostic analysis of the synthesized shaping components reveals stronger interdependence in action selection and improved signal alignment in coordination-intensive tasks. These results demonstrate that the proposed LLM-guided reward search framework mitigates the need for manual engineering while producing shaping signals compatible with cooperative learning under finite budgets.

Dogan Urgun, Gokhan Gungor

Department of Electrical and Electronics Engineering, Karabuk University, 78050 Karabuk, Türkiye · Department of Mechatronics Engineering, Karabuk University, 78050 Karabuk, Türkiye

Reward Design for RL Cooperative MARL Multi-Agent Reinforcement Learning LLM-Guided RL

Mar 19, 2026

Bridging Network Fragmentation: A Semantic-Augmented DRL Framework for UAV-aided VANETs

Urban Vehicular Ad-Hoc Networks (VANETs) can become fragmented because buildings obstruct wireless links and vehicle mobility continuously changes the network topology. Unmanned Aerial Vehicles (UAVs) can serve as mobile relays, but Deep Reinforcement Learning (DRL)-based deployment often suffers from inefficient exploration because it lacks road-topology guidance. To address this problem, we propose Semantic-Augmented DRL (SA-DRL), which models network fragmentation over the road topology and aligns a pretrained Large Language Model (LLM) to generate a topology-dependent action prior from dynamic traffic states. The resulting Semantic-Augmented PPO (SA-PPO) algorithm combines this prior with the PPO policy through Logit Fusion, guiding exploration toward promising intersections while retaining adaptation through environmental returns. Simulations driven by real-world urban trajectories show that SA-PPO reaches the final converged reward of Vanilla PPO using only 28.6% of its training episodes. It improves the average number of vehicles in connected components and the average connected-component size by 7.9% and 8.7%, respectively, while reducing UAV energy consumption by 21.3%.

Gaoxiang Cao, Wenke Yuan, Huasen He +4

Department of Automation, University of Science & Technology of China

Intelligent Transportation Systems Wireless Communications V2X Communication LLM-Guided RL Proximal Policy Optimization

Mar 18, 2026

DriveVLM-RL: Neuroscience-Inspired Reinforcement Learning with Vision-Language Models for Safe and Deployable Autonomous Driving

Traditional reinforcement learning (RL) methods rely on manually engineered rewards or sparse collision signals, which fail to capture the rich contextual understanding required for safe driving and make unsafe exploration unavoidable in real-world settings. Recent vision-language models (VLMs) offer promising semantic understanding capabilities; however, their high inference latency and susceptibility to hallucination hinder direct application to real-time vehicle control. To address these limitations, this paper proposes DriveVLM-RL, a neuroscience-inspired framework that integrates VLMs into RL through a dual-pathway architecture for safe and deployable autonomous driving. Inspired by the human brain's habitual and deliberative visual processing, DriveVLM-RL decomposes semantic reward learning into a Static Pathway for continuous spatial safety assessment via CLIP-based contrasting language goals, and a Dynamic Pathway for attention-gated multi-frame semantic risk reasoning via a lightweight detection model and large VLM (LVLM). A hierarchical reward synthesis mechanism fuses these signals with vehicle state information, while an asynchronous training pipeline decouples expensive LVLM inference from environment interaction. Critically, all VLM components operate exclusively during offline training and are completely removed at deployment, eliminating inference latency at test time. Extensive experiments in the CARLA simulator demonstrate that DriveVLM-RL significantly outperforms state-of-the-art baselines in collision avoidance and task success, attaining the highest success rate while reducing collision severity from 10.09 to 1.75 km/h relative to the strongest VLM-based baseline. The demo video, code, and model checkpoints are available at: https://zilin-huang.github.io/DriveVLM-RL-website/

Zilin Huang, Zihao Sheng, Zhengyang Wan +4

Department of Civil and Environmental Engineering, University of Wisconsin-Madison, Madison, WI, 53706, USA · Lyles School of Civil and Construction Engineering, Purdue University, West Lafayette, IN 47907, USA · Department of Civil Engineering, McGill University, Montreal, QC, H3A 0C3, Canada

VLMs for Autonomous Driving LLM-Guided RL Multimodal Reward Modeling RL for Autonomous Driving Safe RL

Mar 18, 2026

Efficient Soft Actor-Critic with LLM-Based Action-Level Guidance for Continuous Control

We present GuidedSAC, a novel reinforcement learning (RL) algorithm that facilitates efficient exploration in vast state-action spaces. GuidedSAC leverages large language models (LLMs) as intelligent supervisors that provide action-level guidance for the Soft Actor-Critic (SAC) algorithm. The LLM-based supervisor analyzes the most recent trajectory using state information and visual replays, offering action-level interventions that enable targeted exploration. Furthermore, we provide a theoretical analysis of GuidedSAC, proving that it preserves the convergence guarantees of SAC while improving convergence speed. Through experiments in both discrete and continuous control environments, including toy text tasks and complex MuJoCo benchmarks, we demonstrate that GuidedSAC consistently outperforms standard SAC and state-of-the-art exploration-enhanced variants (e.g., RND, ICM, and E3B) in terms of sample efficiency and final performance.

Hao Ma, Zhiqiang Pu, Xiaolin Ai +1

School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · JD.com, Beijing, China

LLM-Guided RL RL Exploration Sample-Efficient RL Soft Actor-Critic Continuous Control