Reinforcement learning from verifiable rewards (RLVR) drives chain-of-thought reasoning in large language models, yet its binary outcome reward cannot distinguish among correct trajectories. Existing dense reward alternatives, from surface heuristics to process reward models, either ignore the expert solutions already present in training corpora or require expensive offline annotation. We propose Gradient-Aligned Reward (GAR), which operates in the policy's own gradient space: truncated backpropagation through the output projection layer extracts a compact gradient vector for each rollout, and cosine similarity with an expert-anchor gradient yields a dense, reasoning-aware reward with less than 9% wall-clock overhead. We prove that this cosine admits a multiplicative decomposition into prediction-error and activation-pattern factors, providing a concrete characterization of what the alignment signal measures. On Qwen3-4B and Qwen3-8B, GAR consistently improves over GRPO and other baselines on competition-level math benchmarks and transfers to GPQA Diamond and MMLU-Pro without domain-specific data. Code and data are available at https://github.com/LQgdwind/GAR.
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for large language model (LLM) post-training, but its reliance on coarse outcome rewards leads to limited guidance on intermediate reasoning processes. Existing approaches such as process reward modeling and on-policy distillation introduce additional constraints, such as reliance on a specialized reward model or assuming identical reasoning patterns between teacher and student. Nevertheless, we observe that once a reasoning process first goes wrong, evaluating the subsequent reasoning provides limited additional information, as it is already conditioned on an invalid prefix. Therefore, we propose Cliff, a reward shaping strategy that utilizes an off-the-shelf LLM as a teacher to identify the first mistake in each rollout. As a result, the rollout is naturally decomposed into two parts: a correct prefix and an incorrect suffix. Cliff then converts this signal into token-level advantages, assigning positive advantages for the correct prefix and negative feedback afterward. Experiments across 12 different scenarios demonstrate that Cliff consistently improves reasoning performance, outperforming on-policy distillation by 15% and standard GRPO by 7%, even with teachers of modest capability. Furthermore, we analyse the role of ``ground truth'' in Cliff and investigate its training dynamics. These results establish Cliff as a simple, general and effective approach for improving RLVR with richer, fine-grained supervision.
Chenyu Zhou, Qiliang Jiang, Shuning Wu +1cs.LG cs.AI
Multi-turn agentic RL increasingly treats credit assignment as a targeting problem: given a terminal verifiable reward, per-turn methods localize credit onto the turns that mattered. We identify the structural quantity that predicts when this is the right move, the verifier information density V_d = k/C (the fraction of an agent's C-step causal chain whose per-turn correctness the verifier exposes), and show that terminal-state verifiers sit deep in a low-V_d regime where targeting is the wrong axis. In controlled shared-rollout comparisons on tau^2-bench that separate reward density from credit geometry, a continuous dense reward spread uniformly beats the sparse binary outcome reward (net-harmful on 4/5 seeds), while concentrating the same advantage on progress turns or on random turns is equally harmful: targeting is second-order. The mechanism is coverage: terminal-state verification collapses the observable signal to a single final-write turn (k=1 in 98% of rollouts) while success requires a 5-8 step chain of prerequisite tool calls. A synthetic phase boundary places the crossover at V_d* ~ 0.8, whereas measured V_d is ~0.15 on tau^2-bench and ~0.4 on BFCL V3; uniform also wins on BFCL, where a matched-concentration shuffled control is negative on 8/8 seeds. The effect reproduces across model families on ToolACE-2-8B (Delta = -0.048 over 32 pre-registered seeds; an independent 20-seed replication is itself significant), and a pre-registered matched-budget breadth sweep traces a monotone dose-response whose deficit vanishes only at full chain coverage, with a reward-to-go arm reaching full-coverage parity. Uniform redistribution is the zero-information coverage default that per-turn schemes must beat; we contribute the matched-concentration shuffled control that any targeting claim should clear.
Goal-conditioned reinforcement learning struggles with long horizons when rewards are sparse. While a planner can provide subgoals to guide a low-level policy, its use at test time may introduce practical subgoal management difficulties. An alternative paradigm utilizes a high-level planner to assist learning, while the policy remains conditioned only on the final goal, enabling planner-free deployment. Among these methods, Reinforcement Learning with Imagined Subgoals (RIS) introduces a regularization term that encourages the policy to take the same actions for the final goal as it does for an intermediate goal. This regularization, however, may lead to goal-chaining issues when intermediate goals are low-dimensional. Potential-based reward shaping (PBRS) translates plans into an additional reward while ensuring that the optimal policy remains unchanged. Yet, it can generate deceptive rewards in terminal states. We study these failure cases and first propose an alternative reward shaping method (RS) that removes these deceptive rewards at the expense of theoretical guarantees of PBRS. Similar to this RS variant, we then propose another method named Locally-Guided Actor Critic (LG-AC) that rewards the agent for reaching intermediate goals. Unlike RS, where intermediate rewards are implicit in the shaping signal, we explicitly condition a value estimator on the full sequence of intermediate goals but represent the value function as a sum of subgoal-conditioned value functions, enabling dense hindsight relabeling. We evaluate all these methods in tasks with challenging goal-chaining requirements and empirically highlight specific cases in which either action regularization or reward shaping yield low performance, while LG-AC achieves the best overall performance across tasks.
Reinforcement learning from verifiable rewards (RLVR) has emerged as a pivotal technique for enhancing the code generation capabilities of Large Language Models (LLMs). However, the efficacy of RLVR in coding implementations is fundamentally limited by the comprehensiveness of test cases, because insufficient test coverage in code validation often causes false positives, further leading to reward hacking and policy degradation. To mitigate the reward bias stemming from the suboptimal quality of current automated generation methods, we propose the RobustTests framework, which introduces a faulty-code-driven test case synthesis strategy that leverages "near correct" faulty codes to guide the model in precisely capturing latent logical discrepancies and further integrates validator agents with behavioral feature clustering to facilitate the granular filtering of invalid and redundant test cases. To address false negatives caused by inherent hallucination noise in synthetic test cases, RobustTests also incorporates a stepwise dense reward function based on pass rates, bolstering training robustness through fine-grained feedback. By employing this pipeline, we construct a high-quality dataset that augmented the test cases in CodeContests, encompassing a broader spectrum of faulty code scenarios and significantly enhances diagnostic utility. Experimental results demonstrate that, by leveraging a moderately challenging subset of problems from CodeContests for training, RL fine-tuning of Qwen3-32B via RobustTests achieves an absolute 3% performance gain on the LiveCodeBench benchmark compared to baseline methods, confirming the effectiveness of the RobustTests framework in advancing the code generation proficiency of LLMs.
Mehdi Azarafza, Faezeh Pasandideh, Ali Ehteshami Bejnordi +2cs.MA cs.CL cs.CV
Autonomous vehicles require robust perception and decision-making capabilities to operate in diverse and unseen scenarios. While reinforcement learning and rule-based methods can provide effective control and safety mechanisms, their performance may degrade in situations requiring contextual reasoning. Large Language Models (LLMs) have demonstrated strong capabilities in understanding multimodal information and generating contextual reasoning, however, their use for direct vehicle control can introduce latency and hallucination risks. To address these limitations, a hybrid framework is proposed. This system uses an orchestrator to coordinate PPO-trained reinforcement learning and PID control, with LLM common-sense reasoning applied throughout the framework. LLM reasoning is further employed iteratively to refine the RL reward function for dynamic driving environments. The proposed framework is evaluated in highly randomized CARLA scenarios under diverse environmental and traffic conditions. The results demonstrate the potential of integrating LLM-based reasoning with conventional autonomous driving methods while retaining structured control and safety mechanism.
Active geo-localization enables low-altitude UAVs to search for specified targets from limited local aerial observations, supporting time-sensitive applications such as search and rescue and emergency inspection. However, multimodal target cues, restricted views, and sparse feedback make it difficult to balance exploration with target convergence. Existing curiosity-driven methods assign a fixed intrinsic-reward weight throughout search, which can continue rewarding novelty after the agent nears the target and induce detours. We propose DynCur-Geo, a dynamic curiosity framework that adjusts prediction-error intrinsic reward according to remaining target distance. A distance-aware gate encourages early exploration and shifts the policy toward goal-directed behavior near the target, while potential-based reward shaping supplies dense progress guidance. Experiments across multimodal, cross-scene, disaster-affected, and long-range settings show consistent gains over active geo-localization baselines.
Christophe D. Hounwanou, John Emeka Eze, Yaé U. Gabacs.LG cs.AI
Combining large language models with reinforcement learning is increasingly explored, yet the theoretical status of LLM-derived reward signals is often left implicit. We formalize the hybrid LLM-planner and RL-controller architecture as a Goal-Augmented Markov Decision Process and show that when the LLM per-state progress score is used as a bounded potential function, the resulting shaping term preserves the optimal policy set even when the LLM scores are inaccurate. This guarantee is stronger than what general LLM-as-reward approaches provide. We verify the result numerically on a small MDP under four potential configurations, including an adversarial one scaled to twenty times the base reward magnitude.
Reinforcement learning is promising for autonomous urban driving, but long-horizon goal-directed navigation asks a policy to acquire several competing behaviors at once--reaching a distant goal, tracking a route, avoiding obstacles, obeying signals--and a fixed objective gives no order in which to learn them. This paper presents CORAL, which advances two schedules together: a five-stage curriculum that progressively lengthens routes and tightens behavioral constraints, and a stage-aware reward whose component weights shift emphasis from mission progress toward route following, safety, smoothness, and rule compliance as the task hardens. The policy is a multi-stream actor-critic network trained with Proximal Policy Optimization (PPO) in CARLA on a compact 99-dimensional state pairing a polar LiDAR histogram with vehicle telemetry, ego-frame route geometry, and traffic-rule indicators--no point-cloud encoder, no bird's-eye-view rasterization. Against two PPO baselines under an identical protocol, CORAL reaches the goal in all twenty evaluation episodes on the longest routes under the full set of behavioral constraints, where the baselines reach 5% and 10%; a factorial ablation shows that neither schedule alone matches their combination: removing either lowers both success and route completion, and disabling both drops success to 55%. Trained in one town, the policy transfers zero-shot to seven unseen towns, succeeding in 68-98% of episodes on routes of the same 100-150 m length, with mean lateral deviation below 0.35 m.
Takieddine Soualhi, Jacques Saraydaryan, Laetitia Matignoncs.LG cs.RO
Developing effective robot navigation methods in crowded environments is essential for real-world applications. Although recent deep reinforcement learning (DRL) methods have improved navigation performance in crowded environments, they often focus primarily on task-centric objectives and underrepresent social compliance objectives. In this paper, we introduce a novel proxemics-based reward formulation for DRL social navigation that provides a dense, interpretable social learning signal while maintaining navigation efficiency. Our approach models each human's personal space as a radial Gaussian-mixture field derived from Hall's proxemics theory and computes a robot-centric local cost over the robot's field of view. We integrate the proposed reward into established DRL navigation methods and evaluate it in simulation across multiple crowd scenarios, reward baselines, and crowd densities using both navigation metrics and social metrics. Results show that the proposed reward consistently improves social metrics in simulation while maintaining competitive navigation performance relative to the compared reward models.
Signal temporal logic (STL) provides a formal language for specifying real-time properties of real-valued observations, along with a quantitative robustness score for monitoring satisfaction. Control synthesis from STL specifications is of interest since manual controller design becomes infeasible as real-world systems grow in complexity. Moreover, many modern autonomous and AI-enabled systems lack accurate and complete system models, which makes optimization-based synthesis approaches unsuitable and motivates learning-based control. Prior work uses STL robustness scores as rewards in reinforcement learning (RL) to obtain control policies satisfying given specifications; however, robustness depends on execution history, leading to intractable state space expansion for general long-horizon specifications with arbitrarily nested temporal operators. This work introduces a novel automata-based approach that provides an efficient memory mechanism and associated Markovian rewards suitable for RL frameworks. Our approach constructs a timed alternating automaton from the given STL specifications, augments the state space with automaton locations and clock valuations, and derives rewards from the automaton acceptance condition. We empirically demonstrate that our approach learns policies that achieve higher robustness scores and satisfaction rates than those learned by existing approaches using robustness-based rewards.
Instant delivery platforms have become a critical component of urban logistics, increasingly relying on crowdsourced couriers to fulfill highly dynamic orders. In real-world systems, couriers are not exclusive to a single platform and may concurrently serve multiple platforms, while each platform can only observe its own orders and couriers' interactions due to privacy and operational constraints. This results in a multi-platform dispatch environment with inherent partial observability. However, most existing works on dispatch optimization assume full courier observability and mandatory assignment acceptance, causing substantial performance degradation when deployed in realistic multi-platform settings. In this paper, we propose POLO, a partially observable multi-agent reinforcement learning framework for dispatching optimization in multi-platform instant delivery systems. POLO firstly models each platform-grid pair as an independent agent that learns dispatch policies solely from platform-local observations, aligning the learning process with real-world privacy and operational constraints. To support effective decision-making under incomplete and heterogeneous courier information, POLO introduces a novel attention-based policy representation that selectively aggregates inter-courier information. Moreover, we design a counterfactual reward shaping mechanism to mitigate the non-stationarity induced by joint actions across grids, leading to more stable and scalable learning. We develop a high-fidelity simulator to evaluate dispatch performance under varying numbers of platforms and system scales. Extensive experiments demonstrate that POLO consistently outperforms strong baselines in terms of platform revenue and courier travel efficiency, highlighting its robustness and effectiveness in realistic multi-platform settings.
Sparse, delayed, and weakly informative rewards remain central obstacles to efficient reinforcement learning. Reward shaping addresses these limitations by supplementing the task reward with an auxiliary signal that can accelerate learning while, in the classical setting, the original objective remains the evaluation criterion. Established theory guarantees safety for fixed shaping signals: potential-based reward shaping preserves optimal policies when the auxiliary term is the discounted difference of a time-invariant potential. In contemporary reinforcement learning systems, however, both the learner and the information available for guidance evolve during training: value estimates improve, novelty diminishes, feedback shifts, and predictive models are refined. Adaptive reward mechanisms occur across exploration, Bayesian inference, human-in-the-loop learning, automated reward design, and foundation-model-based approaches. This study introduces a unified analytical framework for comparing dynamic reward shaping and neighbouring adaptive reward mechanisms. The proposed framework distinguishes parametric revision from state-dependent variation, separates additive shaping from reward replacement and reward-adjacent guidance, and organises existing methods along temporal, informational, and theoretical dimensions. Using this framework, twelve method families are comparatively analysed. The framework further highlights the conditions under which optimality guarantees survive contemporary deep reinforcement learning pipelines, replay buffers, bootstrapped critics, and reward normalisation, while exposing the unresolved relationship between adaptation rate and learner stability.
Cooperative multi-agent reinforcement learning often adds social terms to individual rewards, yet the scale of those terms is usually chosen by hand. We ask whether a guilt signal can instead be calibrated from human neural and behavioural data and transferred to artificial agents. Using the public SoDec responsibility fMRI dataset (40 participants), we fit a subject-fixed-effects regression of momentary-happiness changes on outcome-type counts and recover a guilt weight as the Partner-negative minus Social-negative contrast ($\hat{w}=1.118$, Cohen's $d=0.214$). We embed this weight in a two-agent Social Lottery environment and train independent Proximal Policy Optimization actor-critics under four shaping regimes: neurally calibrated, uniform constant, zero (selfish), and a unit-coefficient oracle. Across 1{,}000 evaluation episodes per condition, the calibrated agents track the human Social safe-choice rate most closely ($0.459$ vs.\ human $0.484$; $\mathrm{KL}=0.0012$), while the other three conditions deviate by one to three orders of magnitude in KL. Human neurobehavioural priors can therefore act as quantitative constraints on prosocial reward shaping.
Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit. Training-only privileged skills can provide denser supervision by allowing the same frozen policy snapshot to rescore fixed tokens from skill-free trajectories while conditioned on task-matched procedural skills. Existing methods, however, do not jointly calibrate teacher scores across interaction steps, relate teacher confidence to realized returns, and integrate the resulting signal into native reward-to-advantage construction. We introduce Agentic Reinforcement Learning with Self-Distilled Reward Shaping (ADRS), a framework for constructing return-associated token-level credit for multi-turn language agents. ADRS centers and normalizes privileged token scores within each step, modulates them with a return-associated Teacher Value Advantage (TVA) gate based on within-group confidence--return association, and incorporates the gated token signal into native RL credit construction. Together, these components determine what the teacher prefers, when that preference is return-relevant, and how it enters the native reinforcement-learning credit path, while keeping rollouts and inference skill-free. Finally, experiments across three interactive benchmarks show that ADRS consistently improves performance on long-horizon tasks, with gains persisting across RL backbones, reduced-data settings, unseen tasks, and extended training. For anonymous review, our code is available at the following the link: https://github.com/gitrxh/ADRS-arxiv
Large language models (LLMs) are increasingly extended into deep search agents that solve complex questions through multi-step interaction with external search and browsing tools. However, existing agents often incur substantial computational and interaction costs, generating lengthy trajectories that contain redundant queries, inefficient exploration, and irrelevant observations. Existing efficiency-oriented methods usually encourage agents to use tools less frequently, but treating all tool interactions uniformly may also suppress steps that gather necessary evidence. In this paper, we propose CRISP, a framework for training efficient deep search agents through critical step perception. Unlike prior efficiency methods that uniformly penalize tool use, CRISP distinguishes interactions that gather necessary evidence from redundant ones and shapes the training reward to preserve the former while pruning the latter, improving efficiency without sacrificing the evidence needed for correct answers. Specifically, CRISP first constructs critical-step labels with Backward Evidence Induction: starting from the final answer, a strong model traverses a completed search trajectory backward and judges whether each tool-interaction step provides or preserves evidence for the final answer. We then distill these step-wise judgments into a smaller critical-step recognizer, enabling full-trajectory analysis in a single pass. During policy optimization, an efficiency-aware reward is applied only to successful rollouts. Experiments on BrowseComp and HLE-Verified show that CRISP maintains competitive final-answer accuracy while reducing average interaction turns by 15.1% and 33.2%, respectively, demonstrating substantial improvements in interaction efficiency.
Post-training large language models (LLMs) via reinforcement learning (RL) has significantly advanced code generation capabilities. To bypass the heavy memory footprint of critic networks, current state-of-the-art frameworks leverage critic-free paradigms like Group Relative Policy Optimization (GRPO) tied to rule-based verification sandboxes. However, applying these frameworks to low-level systems programming, such as CUDA kernel generation-presents severe challenges: binary pass/fail rewards introduce severe signal sparsity, while multi-turn environmental feedback loops suffer from prohibitive compilation latencies and reward dilution across trajectories. In this work, we introduce LEAP (Lean Environment-Feedback via Adaptive Pruning), a scalable and computationally efficient multi-turn RL framework optimized for low-level hardware accelerator alignment. LEAP features Difficulty-Conditioned Pruning (DCP), a dynamic gating mechanism that adaptively cuts off simple and overly catastrophic tasks from multi-turn expansion, focusing resource-heavy compilation and hardware exploration exclusively on high-value, complex tasks. To fully operationalize these paths without manual hyperparameter engineering, we propose a Rank-Based Reward formulation. By deriving scale-free relative advantages from pairwise tournament outcomes within the GRPO rollout group, our method inherently penalizes token inefficiency on simple prompts while maximizing learning gradients on challenging distributions. Empirical evaluations show that LEAP achieves superior first-turn proficiency and robust multi-turn debugging resilience while converging faster than unpruned multi-turn baselines, establishing a practical paradigm for low-level code RL.
Reinforcement learning (RL) for document parsing often relies on reference-based rewards rooted in edit distance (e.g., tree edit distance), yet it remains hard to optimize in the high-accuracy regime because such rewards become weakly discriminative: near-correct outputs receive very similar scores, providing limited learning signal for hard cases. We propose Step-Aware Annealing (SAA), a plug-and-play reward sharpening mechanism that progressively increases reward curvature during training, amplifying subtle quality differences among high-scoring samples while preserving stability in early learning. Built on SAA, we introduce DocPO, a document policy optimization framework with element-specific, reference-based rewards anchored by edit-distance signals: normalized string edit distance (NED) for text, tree edit distance similarity (TEDS) for tables, and a hybrid Rubric+edit reward for formulas. Experiments on OmniDocBench and DocElemHard show that SAA consistently improves GRPO-style RL across document elements over non-annealed rewards, without requiring additional human supervision for reward construction.
Multi-turn code agents rely on execution feedback to repair incorrect programs, yet standard reinforcement learning paradigms optimize and evaluate policy performance primarily using single-shot outcome rewards. This misalignment conflates initial code generation with feedback-driven refinement, discards granular execution signals across intermediate turns, and fails to evaluate whether the policy actually acquires self-repair capabilities. We propose Test-aware Policy Refinement (TaPR), a framework that transforms execution feedback into a dense per-turn test-pass-ratio reward under a consistent multi-turn interaction protocol. Across six models on 219 code-generation problems from LiveCodeBench, TaPR improves the pooled three-turn success rate (Pass@3) by 2.44 percentage points. In the predefined 7B/8B high-headroom slice, pooled accuracy increases from 30.25% to 33.56% (+3.31 pp), with 42 improvements and 13 regressions in paired trials. On a matched Qwen3-8B ablation, the dense reward supplies nonzero feedback in all of the first ten steps and reaches a higher Hard-subset peak than outcome-only GRPO within the tested budget, although GRPO nearly matches pooled Pass@3 by step 300. Our primary contribution is a reward-decomposition framework and a turn-aware evaluation protocol that decouple first-shot generation quality from multi-turn repair competence.
Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating risks where plausible-sounding but incorrect derivations mislead users. We characterize this \textit{futile reasoning} phenomenon through systematic analysis, revealing universal capability overreach and systematic miscalibration between capability and behavior. The dominant failure mode is specious reasoning, which outputs look superficially valid but contain subtle errors, escalating with task difficulty. To address this, we introduce \textbf{CaRL} (\textbf{Ca}pability-\textbf{a}ligned \textbf{R}einforcement \textbf{L}earning), which aligns model behavior with capability boundaries through reward shaping that incentivizes refusal over futile reasoning and hindsight refusal augmentation that converts failures into refusal supervision. Experiments demonstrate a substantial reduction in futile reasoning while preserving performance across task difficulties, effectively achieving capability-aligned behavior without sacrificing utility. \footnote{https://github.com/icip-cas/Knowing-When-to-Quit}
Credit assignment is a fundamental challenge in cooperative multi-agent reinforcement learning, particularly in embodied AI settings characterized by limited and delayed feedback as well as dynamically changing numbers of active agents. We propose MARS-RA, a framework that reformulates credit assignment as a rank aggregation problem using contribution-based pairwise comparisons among agents generated by large multimodal models. This shift from absolute to relative estimation ensures robustness against noise and dynamic agent participation, converting comparison results into contribution scores for potential-based reward shaping. We provide theoretical justification for the convergence and robustness of the proposed framework, and show that Shapley values can be used as an interpretive reference. Experimental results on challenging tasks of different types indicate that MARS-RA can guide agents toward effective cooperation.
Reinforcement learning is a natural post-training paradigm for code-oriented large language models because generated programs can be evaluated through parsing, execution, unit tests, and structural analysis. However, existing methods often rely on sparse outcome rewards or statically combine heterogeneous dense signals, even though syntax validity, executability, functional correctness, and structural organization describe different and progressively dependent programming capabilities. We propose DHRCL, a reinforcement learning framework with Dense Hierarchical Rewards and Curriculum Learning. DHRCL decomposes feedback into syntax validation, execution success, unit-test pass rate, and AST-based structural similarity, and organizes these signals through a three-stage Syntax, Execution, Pass & Structural curriculum. Stage duration is determined automatically from recent validation trends rather than manually specified capability thresholds. We further introduce stage-aware probability-based token credit redistribution. The mechanism follows a consolidation-to-refinement principle: it emphasizes established token patterns during syntax-oriented optimization, applies uniform propagation for non-local execution feedback, and allocates more credit or blame to less-established token decisions during final functional optimization. Under a unified Qwen3-8B and KodCode protocol, the experiments compare DHRCL with binary, pass-rate, reward-model-based, and verifiable dense-reward baselines. We further evaluate DHRCL across Qwen3-4B, Qwen3-8B, and Qwen3-14B backbones, showing that its advantage remains consistent as model capacity increases.
Reinforcement Learning from Human Feedback (RLHF) is the standard approach for aligning large language models with human preferences, but its quality is limited by static, task-agnostic reward models. This mismatch leads to sparse learning signals and suboptimal alignment. We introduce MeRLa (Meta-Learned Reward Shaping), a principled framework that meta-learns a task-aware shaping function $Φ(x,y;φ)$ across auxiliary tasks before RLHF training. The learned shaping produces a composite reward that preserves policy optimality while providing task-specific learning signals. Our meta-objective combines task discrimination, entropy regularization, and potential-based conservation for stable convergence. We provide theoretical guarantees for policy invariance, analyze representation drift sensitivity, and formally address incentive misalignment from entropy maximization. Experiments on LLaMA-3-8B across four benchmarks show consistent improvements over PPO, DPO, GRPO, and DAPO, achieving a 90.8% length-controlled win rate on AlpacaEval 2.0 and a score of 9.14 on MT-Bench, with 41% less training instability. MeRLa retains its benefits when combined with process-based and rubric-based enhanced rewards.
Designing effective reward functions for model-free reinforcement learning under non-holonomic constraints remains a persistent challenge, often resulting in severe local minima such as policy paralysis or over-conservative hazard avoidance. In this work, we present a parameterized reward shaping framework featuring coverage-gated alignment feedback, drive-direction switch regularization, and an aligned episode termination mechanism evaluated on an autonomous parallel parking task. Crucially, we show that environmental reward parameters and algorithmic hyperparameters are deeply co-dependent, requiring joint meta-optimization to achieve stable convergence. By employing surrogate-based Bayesian optimization, our co-optimized Deep Q-Network (DQN) agent resolves characteristic control failure modes, significantly outperforming uncalibrated baselines across both success rate and trajectory smoothness.
Dense per-step supervision is an appealing remedy for sparse-reward, long-horizon LLM agents: reward the agent for predicting its next observation, and memory should follow. We show that under group-normalized RL (GRPO), this recipe does not merely fail -- it destroys the policy. Across Qwen3-1.7B/4B/8B on ALFWorld, a potential-based prediction reward drives every run into a degenerate absorbing state (prediction accuracy -> 1.0, task success -> 0,episode length pinned at the horizon): the "dark room" pathology, built automatically by the optimizer. A single-factor ablation localizes the cause -- removing only GRPO's std normalization turns the same reward from catastrophic (0%) into baseline parity -- and a two-line proposition explains why: in all-fail groups the z-scored advantage is invariant to the shaping coefficient, so bounded rewards become unbounded pressure and annealing cannot help. Our central insight generalizes this: what z-scoring amplifies is a dense signal's within-group variance while all-fail groups dominate, so signals whose variance decays by mastery are structurally amplifier-safe.This variance-profile criterion retrodicts our collapses, carries preregistered predictions for arms that had not yet run, and is consistent with published reward-channel successes (a compatibility check, not an independent test). Finally, a controlled signal-delivery matrix (identical signal, varying only the consumption mechanism) shows the reward channel is at best neutral while the auxiliary-loss channel gains ~20 points -- and a shuffled-gold placebo matches the true-gold arm, so the gap survives without correct labels. Endpoints are single-seed; seed replication and group-size controls are preregistered and in progress.
Knowledge graphs (KGs) are widely used to inject prior knowledge into reinforcement learning (RL), yet the literature is dominated by single-domain, positive-result method papers, so we lack a systematic account of when KG structure helps an agent, when it is neutral, and when it hurts. We conduct a controlled study that independently varies the RL task, the injection mechanism (state features, action masking, or potential-based reward shaping), and KG quality. Using a synthetic, fully controllable KG over MiniGrid environments, we report three findings. First, on compositional sparse-reward tasks structured KG guidance improves sample efficiency and solve reliability (70% to 97% of seeds), and a shuffle control that permutes the KG's edges while preserving their count collapses the benefit toward baseline (masking p=0.0001; shaping p=0.006), so the gain is structural rather than generic regularization. Second, KG value scales with the amount of task-relevant knowledge the graph contains. Third, and most consequential, safety depends on the mechanism: soft, optimality-preserving injection benefits from correct knowledge and harmlessly ignores incorrect knowledge, whereas hard masking is brittle, forbidding essential actions when the KG is incomplete or corrupted and making a wrong KG worse than none. A UMLS-derived clinical case study on sepsis management under offline RL is a careful null, underscoring that benefits require task structure the chosen mechanism can exploit. Our results give practitioners concrete guidance on how, and how much, to trust a KG when using it to guide RL.
Large language models that generate step-by-step reasoning traces have achieved strong performance on complex tasks, and extending them to long-context settings has emerged as an important frontier. However, we identify a critical failure mode in this regime: \emph{repetitive copying}, where models extensively copy text from the input into their reasoning traces rather than productively solving the problem. We show that this behavior is pervasive across frontier long-context LLMs and intensifies with context length. By separating each prompt into task-relevant key evidence and irrelevant distractor context, we further show that the root cause is insufficient grounding: models copy from the prompt indiscriminately, and those that fail to focus on key evidence are far more likely to answer incorrectly. Motivated by this diagnosis, we propose GEAR (Grounding Evidence-Aware Reward), a reward shaping method that augments the accuracy signal with a grounding reward for overlap with key evidence and a distractor penalty for overlap with irrelevant context. To enable GEAR on natural-language data, we develop an automated pipeline that constructs evidence-annotated training data from arbitrary documents. We validate GEAR across multiple model scales and benchmarks, showing consistent improvements of up to +4.6 average points over standard RL with accuracy-based rewards, with larger gains at longer contexts, while also reducing repetitive copying and thinking length. Our findings suggest that, even as long-context evaluation shifts from simple retrieval toward complex reasoning, accurate grounding in relevant evidence remains an indispensable capability with substantial room for improvement.
In-hand manipulation without external sensing is challenging due to uncertainties from finger-object contacts and disturbances by gravity. While reinforcement learning has shown promise in learning complex finger gaiting, existing approaches do not prioritize maintaining well-conditioned grasps for sustained manipulation. We introduce two complementary physics priors for robust in-hand rolling: a global grasp-quality prior derived from classical grasp analysis and a local contact-geometry prior based on fingertip curvature. The grasp-quality prior is used as a dense reward-shaping term that encourages well-distributed contacts with improved worst-case wrench resistance. The contact-geometry prior is expressed in the fingertip geometry that mechanically shapes the contact interface toward task-aligned rolling while reducing off-axis drift. We evaluate the effect of these priors on learning in-hand rolling manipulation for a multifingered robotic hand manipulating three different objects at four palm orientations. Results show significant improvement in rotation efficiency, grasp stability, and disturbance rejection, suggesting that physics priors embedded in both learning and fingertip morphology improve task robustness and sim-to-real transfer. An overview video can be found at https://youtu.be/pdd1wHxQnJM?si=dM-U5kiiPTYsk3Pk.
Reinforcement learning for deep-search agents has largely focused on trajectory-level scoring -- outcome correctness, citation-aware rewards, and evidence coverage. Yet the actions that expose supporting documents receive no targeted credit, a gap we call the reward-credit mismatch. We propose STAMP, in which a reference-based verifier judges whether each cited document supports an entity or relation in a training-time evidence graph, and first-exposure attribution traces each supported citation back to the action that first surfaced it. This step credit is injected through sign-preserving advantage modulation, which redistributes advantage across steps without changing the trajectory-level reward or the relative ranking of trajectories within each group. On BrowseComp, BrowseComp-ZH, and xbench-DS, STAMP improves the GRPO baseline by +2.0/+5.5/+3.0 points under matched SFT initialization, training data, and search tools, and composes with both outcome-only and citation-rubric base rewards. Component ablations confirm that the provenance-based credit signal and the sign-preserving advantage modulation each contribute to the gains.
As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making. We introduce AgenticAI-Supervisor, an API and UI-driven RL Gym environment that decouples environment creation from scalable execution. By moving to verifiable execution outcomes, the platform generates high-fidelity traces and applies multi-dimensional reward shaping. Critically, our framework mitigates reward hacking through rigorous internal state validation and testing. This work provides a first look at our platform's core capabilities through a Customer Support Agent case study demonstrating a consistent closed-loop feedback for model optimization. Future work will focus on advanced features such as Computer Use, Tool Use, automated "stumping", and edge-case generation.