Overview

Robot policy learning studies how robots can turn camera, depth, tactile, and proprioceptive inputs into actions for tasks such as manipulation, locomotion, and navigation. Common approaches include behavior cloning from demonstrations, reinforcement learning in simulation or on hardware, and diffusion, flow-matching, or vision-language-action policies that generate action sequences; world models and hierarchical planners can add foresight and long-horizon structure. Researchers evaluate these methods in simulation suites such as LIBERO, CALVIN, RoboTwin, and navigation benchmarks, as well as on physical robots, with growing attention to memory, contact, safety, and recovery from failure. A central tension is how to make policies generalize across tasks, robots, and changing conditions while remaining data-efficient, reactive, reliable, and fast enough to deploy.

Latest papers

405 papers42 papers in the last four weeks, down 58% on the four weeks before. 0.3% of all new papers.

Oct 28, 2026

Same Label, Different Interface: Beyond Action-Space Labels in Robot Learning

Robot-learning studies often compare position and velocity actions as though each label identified a single experimental treatment, yet the label alone does not determine what the robot executes. Before affecting robot motion, bounded policy output passes through filtering, physical scaling, reference construction, feedback, timing, and effort limits. We study how these omitted properties affect attribution under one shared learner and training budget. Across three contact-rich Factory tasks (PegInsert, GearMesh, and NutThread), we compare five joint-space interfaces, with ten independently trained policies per condition. We first remain within the same position-feedback law and vary the executed interface: substituting only the physical action scale as the directly modified component changes sample-median evaluation success by 0.645-1.000 across tasks, while removing an exponential moving average produces task-dependent changes. We then move to a cross-law comparison and choose a velocity scale that exactly matches the position interface's local raw-torque command gain. This calibration raises the sample median on GearMesh and NutThread, with no median change on PegInsert. Yet clear residual sample-median gaps remain on PegInsert and GearMesh, while the NutThread interval includes zero. Thus, even this explicit equality leaves feedback and held-action dynamics unmatched and does not establish position-velocity trained-outcome equivalence. Action-interface comparisons should therefore report the executed pathway and state the physical quantity they match.
Oct 27, 2026

Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling

Robot policy evaluation often relies on a binary success signal for task completion. In real-world deployment, however, desired execution behaviors are also defined by quality attributes such as execution speed and motion smoothness, which need to be dynamically controlled according to task requirements. To address this, we introduce Quality-Controllable Policy (QCP), a robot policy that enables inference-time control over both individual quality attributes and their combinations. To extend the controllable quality range beyond initial demonstrations, we further propose an iterative hindsight relabeling loop: QCP collects online rollouts under target quality labels, adds successful trajectories to the dataset, relabels the accumulated trajectories in hindsight according to their measured quality, and fine-tunes the policy. Experiments on Robomimic and RoboEval demonstrate that QCP consistently improves both task execution quality and success rates across iterations, producing successful rollouts that exceed the quality of the initial demonstrations. Finally, we validate QCP on real-world manipulation tasks, where controlling speed increases throughput in conveyor operations and controlling transport stability improves success when carrying wine glasses, demonstrating that quality-controllable policies yield practical gains in physical deployment.
Oct 27, 2026

A Trainable CPG Framework for Quadruped Locomotion

We present CPG-ENN, a trainable quadruped locomotion framework that combines explicit neural coordination with learned motion realization. A symmetry-based eight-neuron central pattern generator (CPG) supplies gait rhythms, while a pretrained, leg-shared execution neural network (ENN) maps rhythmic signals and trajectory parameters to joint-angle references without online inverse kinematics. A single feedback policy modulates six physically interpretable trajectory variables. The controller tracks planar velocity and yaw-rate commands across walk, trot, pace, bound, and pronk without gait-specific learned controllers or transitionspecific rewards. Simulation yields 99.39% transition success across all 20 directed gait pairs and all source-target speed combinations from {0.5, 1.0, 1.5, 2.0} m/s. Ablations show high cross-gait transition feasibility without transition exposure; exposure mainly refines gait acquisition and velocity transients. Comparisons with AllGaits and Walk These Ways demonstrate accurate gait-speed regulation, and Unitree Go2 experiments validate five gaits and their transitions.
Oct 26, 2026

Rollback: Experience Backtracking in World Models for Policy Improvement

Action-conditioned world models offer a scalable alternative to costly real-world interaction for improving robot policies. However, existing world-model-based methods largely treat world models as forward-only surrogates of the physical environment, leaving untapped a capability no physical environment affords: rewinding to past decision points to explore counterfactual futures. We introduce Rollback, a policy improvement paradigm that turns world models from passive simulators into counterfactual engines: it rolls back to critical decision points, branches into alternative actions, and contrasts their outcomes to attribute success to individual decisions. This concentrates imagination where it matters most and distills counterfactual outcomes into fine-grained, action-level supervision without a separately learned value model. We build a scalable training system that unifies distributed world-model search with asynchronous real-robot execution, forming a self-reinforcing cycle: real-world experience continually sharpens the world model, and a sharper world model in turn drives further policy improvement. We term the world-model side of this cycle test-time physics grounding, a capability that hand-built physics simulators lack: while the world model serves as the training environment, real transitions from the policy it trains correct its dynamics through a lightweight LoRA pipeline. Experiments on three challenging real-world tasks show that Rollback improves success rates over the strongest baseline by an absolute 10.67%, 11.11%, and 11.85% on block extraction, ball tossing, and tabletop curling, respectively, while achieving more stable improvement throughout training. Although initialized from teleoperated demonstrations far below human level, Rollback surpasses the average success rate of human players on both ball tossing and tabletop curling within 8 hours of training.
Oct 26, 2026

DiffContact: Differentiable Contact Dynamics for Policy Learning and Contact-Implicit Trajectory Optimization

This paper proposes DiffContact, a smooth analytic gradient for frictional contact, and applies it to policy learning and contact-implicit trajectory optimization for legged locomotion. The exact contact sensitivity is available in closed form but describes changes within the current contact mode, providing no first-order information toward neighboring contact modes. The proposed gradient replaces this sensitivity only in the backward pass, leaving the hard-contact forward solve unchanged and the realized rollout feasible. A central-path relaxation of the de Saxcé-corrected second-order-cone complementarity problem for Coulomb friction smooths the conditions defining the separating, clamping, and sliding modes. The relaxed sensitivity is evaluated at a point on the central path obtained by a Newton iteration initialized from the hard-contact solution. The sensitivity remains continuous through contact-mode transitions and converges to the exact sensitivity as the relaxation vanishes. Using 100,000 samples and less than 2 min of training on a desktop PC, policy learning with the proposed gradient produces a policy that transfers to hardware without fine-tuning. On hardware, the robot under a trotting policy withstands pushes and traverses debris and slippery ground. In trajectory optimization, the proposed gradient reaches contact-rich solutions missed by exact and Signorini-relaxed gradients. Project page: https://diffcontact.github.io
Oct 26, 2026

Learning Direct Control from Optimization for Dynamic Target Tracking

Dynamic target tracking requires a mobile robot to maintain target visibility while navigating obstacles with smooth, feasible controls. Online trajectory optimization explicitly encodes these objectives but requires repeated numerical solving, whereas waypoint-based neural policies separate geometric prediction from control execution. We introduce LECO, a framework that transfers tracking optimization into offline learning of a direct-control policy. LECO predicts control sequences and maps them to trajectories through a differentiable kinematic model, allowing trajectory-level objectives to directly guide control learning. A decaying expert-guidance curriculum initializes effective tracking behavior and progressively shifts learning toward these task objectives. At deployment, a predictive safety lock checks short-horizon obstacle clearance and invokes a classical planning and control fallback when the predicted motion is unsafe or the target prediction is invalid. Across three simulated obstacle densities, LECO reduces root-mean-square linear jerk by 14.1--31.2% relative to the best competing method for this metric and achieves the highest tracking success rate, with per-cycle computation times of 4.25--5.63,ms. Experiments on two robot platforms further demonstrate tracking through indoor narrow passages and outdoor forest environments. These results demonstrate that learning direct control from optimization enables smooth and robust dynamic target tracking.
Oct 26, 2026

Behavioural Quality Is Not Learning Utility: Objective Mismatch in Human Behaviour Models for Robot Learning

Human behaviour models are increasingly used to provide simulated human interactions for training robots via reinforcement learning (RL). Existing approaches primarily evaluate these models according to how closely their generated behaviours resemble real human data, while their usefulness as training partners is less commonly assessed. This creates a potential objective mismatch: a model that performs well according to behavioural evaluation metrics may not necessarily provide useful training experiences for downstream robot policy learning. Across two human-robot interaction (HRI) domains, highway driving and object handover, we evaluate different types of human behaviour models using common generative-model evaluation metrics. We consider multiple human trajectory representations and compare the resulting evaluations with the downstream performance of RL policies trained using the corresponding models. We find that existing behavioural evaluation metrics do not consistently predict downstream policy performance across domains and trajectory representations, while their evaluations are sensitive to the choice of trajectory representation. We also show that even when the true testing behaviour distribution is known, training against a different distribution may yield better downstream performance than training directly against the true distribution.
Oct 25, 2026

AdaPolicy: Action-Driven Anticipatory Robot Policies via Next-Chunk Prediction

Endowing robot policies with anticipatory capabilities has proven effective in improving control performance. However, existing methods predominantly rely on explicit supervision derived from future observations, in either pixel or latent space, at the cost of additional architectural and computational complexity. Departing from explicit future supervision, we ask whether such foresight can be elicited directly from the action signal. To this end, we propose AdaPolicy, an Action-driven anticipatory policy framework that shapes future-aware representations via cascaded next-chunk prediction. Specifically, an Online Action Head jointly produces the current action chunk and an evolved latent state. Building on this state, a cascaded Unrolled Action Head forecasts the next chunk, and the resulting loss flows back through the evolved state to instill implicit foresight into the online policy. Importantly, this training-only unroll requires no future-observation encoding, keeping AdaPolicy lightweight to train with zero inference-time overhead. Experiments on MetaWorld, RoboTwin 2.0, LIBERO, and real-world deployments demonstrate consistent gains across diverse settings, including up to 1414 percentage points on millimeter-precision tasks such as earphone assembly and shoelace threading. More details and visualizations are available at https://teee111.github.io/AdaPolicy/.
Oct 25, 2026

ElevateHead: Decide Once, Then Commit: When the Action Head Matters for Multimodal Imitation

Robots that learn from people often see several valid ways to do the same task: pass an obstacle on the left or on the right, open the microwave or move the kettle first. A policy that re-decides at every step can waver between these ways mid-task. We ask when the action head (the part of a policy that turns the state into actions) matters, and how it should make this choice. On a controlled task, heads that sample one way succeed far more often than a head that averages the ways when the demonstrations contain several ways and the state gives no hint which to take (+0.72 success with two ways); this trend was not reproduced on the other tasks we ran. We then present ElevateHead, a head that decides once at a learned decision point, commits to that choice for the episode, and exposes the choice as an input a user can set. We designed it by diagnosis: each version was frozen and tested on tasks it had not seen, and the next version changed only what a measured failure pointed to; predictions were registered before each run. The first four versions each fell below BeT on at least one held-out task. The fifth completed all four subtasks of the held-out Franka Kitchen task in 45.2% of episodes against 29.3% for BeT, the strongest baseline across our tasks (+0.160, 95% CI [+0.129, +0.188]); when a mode was forced, the first completed subtask matched it in 95% of successful episodes. Diagnosis also located where commitment breaks: varied start positions (repaired on the controlled task: commitment 0.22 to 0.81, success 0.74 to 0.91) and varied object placement (partly repaired: in an exploratory variant, commitment 0.03 to 0.59 on aligning with no detectable change in success). On held-out block stacking, version 4 was comparable to BeT and did not exceed it. A real-robot test with predictions fixed in advance is planned for a follow-up version of this paper.
Oct 23, 2026

Tiny Recursive Policy: Recursive Latent Refinement for Visuomotor Control

Behaviour cloning has become a powerful approach for robotic manipulation, but many modern policies reconstruct their internal representation from a fixed observation window at each prediction and do not maintain persistent latent context throughout execution. We introduce Tiny Recursive Policy (TRP), a parameter-efficient behaviour-cloning policy that combines persistent temporal state with recursive latent refinement. At each control step, TRP repeatedly updates high- and low-level latent states using a shared computation module before decoding an action sequence, and propagates the resulting state to subsequent predictions. We evaluate TRP across LIBERO-100, MetaWorld ML45, and the LIBERO-Mem benchmarks. TRP performs competitively across multi-task and few-shot settings and shows substantial gains on long-horizon and context-dependent tasks, while using significantly fewer parameters than large generative baselines. Execution-time perturbations show that reliance on the persistent carry increases with temporal-context demand, while training with carry perturbations substantially improves robustness to both carry and visual corruptions. Ablations reveal a strong interaction between persistent state and recursive refinement: the benefit of carry depends strongly on the amount of within-step computation, and the resulting performance cannot be explained by parameter count alone.
Oct 23, 2026

Retiming Robot Demonstrations with a Learned Speed Prior

The pace of a robot demonstration is often determined by the teleoperator rather than by the task itself. As a result, the same motion can appear at widely different speeds across demonstrations, and policies trained on such data may inherit operator-specific timing along with task behavior. We propose to learn a speed prior directly from large-scale demonstration data. Given a task instruction, a motion path and the images along it, it predicts a distribution over execution speed along the path, from which a chosen quantile defines a consistent clock for retiming each demonstration. Existing methods derive the acceleration signal from the very data they accelerate, so each new task costs another fit, annotation, or pair of predefined rates. A single trained speed prior instead covers every task in a corpus. We fit a speed prior on both robot teleoperation data and handheld demonstrations in which a human arm, rather than a robot arm, moves the gripper, and use it to retime robot demonstrations to the handheld pace before fine-tuning a vision-language-action policy. For execution, we pair the policy with a real-time optimal-control layer that tracks predicted action chunks under robot constraints using the predicted pace. On 120 RoboLab tasks, policies fine-tuned on our learned clocks succeed more often and move with up to half the jerk compared with policies fine-tuned on the original demonstration timing and uniformly accelerated to the same speed. On a real robot, our policy stacks cups in 3.50s, 1.72×\times faster than the default policy's 6.02s while succeeding as often, in 29 of 30 trials. Videos and further material are available at https://mllab.snu.ac.kr/projects/learned_speed_prior.
Oct 21, 2026

Asymmetric On-Policy Distillation Learns In-Context Exploration

Sequential decision-making under partial observability is difficult because agents must explore to infer hidden, task-relevant information before acting effectively. Learning such information-gathering behaviors tabula rasa via online reinforcement learning is sample-inefficient, whereas offline imitation averages expert actions across hidden states and fails to learn exploration. In this work, we propose ASTEROID, a simple and effective student--teacher supervised learning framework that can learn test-time exploration. Although a privileged expert never needs to explore, we demonstrate that a history-conditioned student can learn to do so when trained with on-policy contexts: the student first collects on-policy context under partial observability, and then imitates the privileged expert conditioned on that context. By distilling expert actions directly conditioned on the student's on-policy history, the student learns to systematically resolve partial observability, i.e., search while uncertain and exploit once the hidden state is revealed. This enables efficient test-time exploration (similar to Bayesian posterior sampling) without incurring the impractical training-data costs of reinforcement learning. Across a diverse range of eleven different environments, including discrete exploration benchmarks, robotic manipulation, navigation, and Procgen environments, ASTEROID achieves ~2x higher returns under fixed exploration budgets, uses ~100x fewer interactions than RL baselines, and outperforms frontier models at exploration. Finally, our method transfers policies trained in simulation to vision-denied real-world robot manipulation, exhibiting efficient exploration and increasing success by +40% over standard distillation. Overall, it provides a simple yet surprisingly effective framework to learn efficient test-time exploration.
Oct 21, 2026

AirPlayground: Benchmarking Aerial Navigation across Diverse Reconstructed Environments

Large-scale aerial resources provide a foundation for learning navigation across diverse environments. However, existing resources remain limited in providing (1) densely sampled flight demonstrations for learning different policy formulations and (2) broad environment coverage for standardized closed-loop evaluation. To address these limitations, we introduce AirPlayground, a unified benchmark for training and evaluating aerial navigation policies across diverse environments. We first construct 94 photorealistic 3D Gaussian Splatting (3DGS) environments spanning indoor, urban outdoor, and vegetation settings, with aligned collision geometry. Building on these environments, we develop a scene-adaptive pipeline for automated expert flight collection, yielding 94K demonstrations and 46.5M synchronized observation-state-action samples at 50 Hz. We further provide an extensible API that supports training different policy formulations on this shared corpus and evaluating them under unified protocols in the corresponding environments. We benchmark seven baselines spanning four policy paradigms across three navigation settings in seen and unseen environments, and further examine scaling behavior with ACT. Scaling ACT's training corpus from 5 to 70 scenes raises median success rates on seen and unseen environments from 30.6% and 16.8% to 41.2% and 29.4%, respectively. Through this shared training and evaluation framework, AirPlayground supports analysis of how offline prediction errors relate to closed-loop outcomes. Our analyses highlight the roles of prediction errors, execution protocols, and scene interactions in closed-loop performance.
Oct 20, 2026

GPT-6-Astra Understands Touch and Outperform Vision--Tactile--Language--Action Models

General-purpose multimodal models have shown promise as direct robot action policies, yet whether they grasp the physics underlying real-world interactions and can apply that understanding to guide action remains underexplored. We investigate this question using contact-rich manipulation as a representative testbed, examining tactile understanding as a concrete instance of this broader capability. Contact-rich manipulation requires interpreting tactile feedback and adjusting actions after obstruction. Existing learned tactile policies acquire these capabilities through specialized pretraining and per-task optimization, with substantial data and training costs. We present GPT-as-Tactile-Policy, which summarizes expert demonstrations into task guidance and tactile references for contact assessment and corrective action. GPT-6-Astra combines this context with multimodal observations and interaction history to generate control commands and adjust actions through contact feedback. Without additional robotics-specific pretraining or per-task policy fine-tuning, our method achieves 93.8% mean success across five UniVTAC tasks. Overall performance is comparable to state-of-the-art policies, with higher success on selected tasks. On Insert Hole, tactile feedback improves success from 31% to 99%. Execution analysis further demonstrates contact-guided probing and correction, supporting manipulation progress through explicit expert experience and online feedback.
Oct 20, 2026

AWLS: Advantage-Weighted Latent Steering for One-Step Generative Robotic Manipulation Policies

Human-collected real-world robotic manipulation demonstrations often contain mixed-quality trajectories, including hesitant, indirect, or inefficient action segments. While diffusion- and flow-based policies can model such multimodal data, standard behavior cloning (BC) assigns equal likelihood to all demonstrated actions and may therefore reproduce suboptimal modes. Offline RL value estimates offer a natural signal for biasing policies toward higher-value behavioral modes, but directly fine-tuning the generative policy or using critic gradients for policy steering can amplify critic errors and induce prior drift. We propose Advantage-Weighted Latent Steering (AWLS), an offline post-training method for improving frozen one-step generative manipulation policies without updating their decoders. AWLS learns a residual noise shaper, an observation-conditioned residual correction to the policy's latent noise, and trains it with an advantage-weighted action reconstruction objective. The advantages are detached, scale-normalized, and used only as supervised weights on demonstrated actions, avoiding critic-gradient policy updates while preserving fast single-step inference. We further introduce a rollout-free decoder-sensitivity criterion for selecting pretrained checkpoints that remain responsive to latent-noise perturbations. Experiments on simulated and real-world robotic manipulation tasks with clean and mixed-quality demonstrations show that AWLS improves over the frozen base policy while limiting drift from the pretrained behavior prior. Project page: https://awls-corl2026.github.io/
Oct 19, 2026

Learning from Fleet Experience: Collective Experience Learning Across 96 Robots

Robot deployment generates experience that can support policy improvement, but continued reliance on expert corrective actions makes learning difficult to scale across growing fleets. We propose learning from fleet experience: using deployed robots' own executions as a source of supervision for further policy improvement. We call this paradigm Collective Experience Learning (CEL), in which robots pool execution experience to update a shared policy that returns to the fleet. Following expert-supervised initialization, we realize CEL through failure-guided experience retrieval fine-tuning (FERT). FERT uses failure contexts to retrieve relevant segments from successful trajectories and prioritizes their recorded actions for supervised updates, without collecting additional expert demonstrations or corrective actions. Operators provide binary episode-outcome labels and environment resets. A fault-tolerant asynchronous training system (FATS) coordinates robot execution, cloud inference and policy optimization despite local interruptions. Across five real-world manipulation tasks, the resulting policies achieve success rates of 93.3-99.2%, evaluated over 120 trials per task on robots excluded from training data collection. With collection time per robot held fixed, larger fleets provide more experience and generally improve performance across the evaluated sizes. On multi-stage phone packaging, learning with 96 robots raises success from 79.2% to 98.3%. These results support CEL as a scalable approach to improving robot policy reliability through experience generated during deployment.
Oct 17, 2026

Escape Without a Recipe: Maneuver-Agnostic Mars Rover Recovery from Granular Entrapment

Wheeled planetary rovers immobilised in loose regolith have no principled recovery controller: scripted maneuvers are terrain-specific, and naive driving deepens entrapment. We introduce a recurrent policy that learns to escape without a predefined maneuver. The framework rests on a verified trap: in a continuum material point method (MPM) simulator we identify a configuration at sinkage-to-radius ratio z/r = 2.0 where the strongest of ten scripted controllers succeeds in only 7/32 trials, yet the regolith retains traction and continues to shear, confirming granular entrapment rather than a numerical artifact. A frozen entrapment detector, trained on 81,771 windows spanning three materials and six sinkage levels, supplies a three-state belief to the policy observation. A separate simulator mobility latch gates training rewards. Across five training seeds, mean action evaluation achieves 62.5% escape (range 28.1-81.3%; 32 trials per seed) versus 7/32 for the strongest scripted controller and 0/32 for action noise. A numerical audit identifies a coupling-buffer fault that silently discarded 9.7% of contact nodes at 16 parallel environments. Results establish recovery in the tested simulation regime; physical transfer remains unverified.
Oct 16, 2026

Learning Robot Metareasoning: Adaptive Computation Budgets for Real-Time Control

Planning while moving faces an historical trade-off between deliberation and reactivity. A planner running concurrently with execution needs time to compute, so the robot must commit to an open-loop action chunk for that duration: a longer commitment buys a better plan at the cost of feedback frequency. Existing controllers fix this action commitment, and consequently the computation budget, before deployment. However, the optimal computation time is highly state-dependent (due to factors such as unmodeled dynamics, safety constraints, and marginal optimisation gains), i.e. dynamic, therefore offline static tuning risks leaving systems blind during critical maneuvers or unable to find global effective solutions. We cast the identification of the optimal computation budget as a semi-Markov decision process (SMDP) in which a single decision defines both the robot action commitments and the time allocated to the solver. To solve this, we train a reinforcement-learning policy conditioned on the current state, the executing plan, and inexpensive planner statistics. Across ground-robot navigation, agile quadrotor flight, and contact-rich manipulation, the learned policy changes its budget with the demands of the scenario, discovering efficient reasoning patterns that outperform fixed-budget baselines. https://lorenzomagnino.github.io/learning-robot-metareasoning-review/
Oct 16, 2026

TransNav: Transformer-Based End-to-End Navigation Method for Static and Dynamic Quadrotor Obstacle Avoidance

Obstacle avoidance for autonomous quadrotors in cluttered environments remains challenging, especially when both dense static obstacles and moving obstacles are present. Existing methods are often tailored to either static or dynamic settings, which always limit their adaptability across diverse environments. This paper presents TransNav, a transformer-based end-to-end navigation method for quadrotor obstacle avoidance in both static and dynamic environments. TransNav employs a patch-based point-cloud encoding scheme that combines local feature extraction with global contextual modeling, enabling compact yet informative environment representation. The method integrates perception and navigation in a single architecture and directly predicts a finite-horizon action sequence, from which the first action is executed. Moreover, we develop an unsupervised learning strategy by incorporating a lightweight point-mass dynamics model, which directly optimizes trajectory-level costs over the predicted sequence through numerical gradient propagation. Thus, the policy can be efficiently trained without expert demonstrations. Simulation and real-world experiments show that the proposed method achieves strong performance in dense static environments and competitive obstacle-avoidance capability in dynamic scenarios, while maintaining low inference cost for onboard deployment.
Oct 16, 2026

Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors

Generalist robot policies offer strong behavioral priors, but achieving deployment-level reliability and throughput remains difficult. Reinforcement learning (RL) can improve these policies, yet its effectiveness is constrained by the cost of online interaction. Existing methods adapt frozen flow-matching policies by treating noise space as a continuous action space. We show that this behaviorally unstructured space makes exploration inefficient, often preventing these methods from extracting meaningful learning signals on challenging tasks. We introduce AnchorQ, which enables coarse-to-fine policy improvement through a structured, refinable latent action representation. At each decision step, AnchorQ uses flow reversal to map reference behaviors to state-conditioned latent anchors, samples local particles around those anchors, and applies value-guided sampling to explore promising refinements. Our analysis shows that anchors reduce identification complexity at the cost of support bias; particle refinement trades this bias against action-class complexity; and critic accuracy determines the reliability of KL-regularized, value-guided selection. Across simulated and real-world manipulation tasks, AnchorQ outperforms state-of-the-art post-training baselines in sample efficiency, delivering a 37% improvement in real-world success rate and 97% higher simulated task throughput under the same interaction budget. Additional visualizations are available on our website https://anchorq-rl.com/.
Oct 15, 2026

CoDA: Co-Evolution of Data Engines and Action Policies

Generative simulation can automate robot environment construction, but physically valid environments are not necessarily useful for training. The challenge is to identify environments that address a policy's failures and supervision that helps it overcome them. We introduce CoDA, a framework in which a simulation data engine and an action policy co-evolve through a shared heterogeneous memory of environment construction, policy failures, and learning progress. The memory compiles validated diagnoses from a vision-language critic into generation programs that recreate difficulties and training programs that help the policy overcome them. We further propose Text2potential to convert these diagnoses into staged potentials for action-chunk value learning, providing dense supervision for policy updates while preserving the task's optimal policy under standard shaping assumptions. Measured learning progress guides further generation and program refinement. Across four manipulation task families, CoDA improves out-of-distribution success from 5.3% after supervised fine-tuning to 27.6%, exceeding the strongest closed-loop baseline by 9.5 percentage points with the same generation budget. On LIBERO-Pro, 15 rounds of generation and training raise success from 25% to 84% under position perturbations and from 1% to 76% under instruction perturbations.
Oct 15, 2026

MOSS: Mode-Oriented Source Shaping for Robot Flow Matching Policies

In robotic manipulation, the same observation often admits multiple feasible actions. Generative policies such as diffusion and flow matching naturally capture such multimodal behaviors, yet which mode is executed is left to random sampling and cannot be actively controlled. We propose Mode-Oriented Source Shaping (MOSS), which turns mode selection into an explicit choice of where generation starts. We first reveal, both empirically and theoretically, that deterministic flow transport induces mode-dependent structure in the source space. Under ideal deterministic ODE transport, distinct behavioral modes have distinct source-space preimages, while practical approximation errors can blur their boundaries due to imbalanced data, limited model capacity, and few inference steps. Motivated by this source-space structure, MOSS constructs semantically aligned mode-specific Gaussian sources that encode mode identity in the initial noise. A modality-strength estimator predicts the local degree of multimodality, which adaptively controls the geometry of the mode-specific sources. It contracts them toward a shared Gaussian where behaviors are similar and separates them near behavioral branching points. During deployment, the desired behavior is selected at inference simply by sampling from the corresponding component. Across 6 simulated and 3 real-world manipulation tasks, MOSS steers to the target mode up to 100% of the time with high task success, recovers minority modes at over 90% guidance rate under a 10:90 imbalance dataset, and surpasses mode-conditioned flow policy by 43.3 points of guidance rate on real robots.
Oct 14, 2026

Physical Time as a Missing Dimension of Robot Policy Memory Dynamics

Existing robot policy memories typically evolve with observation sequences, implicitly treating each update as the same amount of physical time. Yet identical observation histories can span different durations and require different actions, exposing physical time as a missing dimension of policy memory. We introduce Temporal Flow Policy (TFP), which learns memory dynamics to retain past events and evolve the memory state over measured time intervals. Observations and prior memory determine the content and time scales of each transition; elapsed time determines how far the state advances. TFP conditions diffusion and flow-matching policies through this memory state and is trained with their native imitation objectives. We evaluate TFP with Diffusion Policy and π0.5π_{0.5} through controlled comparisons of memory designs. These experiments show that successful timing depends on both measured intervals and retained history. TFP achieves higher average success than the recurrent and state-space memories we equip with the same intervals and than a variant that feeds the interval to a learned gate. Memory readouts recover the time since an event and motion information after occlusion. Changing the supplied intervals systematically delays or advances actions, linking time inputs to behavior. Real-robot tasks requiring timing or memory, together with LIBERO evaluations, demonstrate benefits in physical and general manipulation. These results suggest viewing robot memory not as stored observation history, but as a state that retains past events and evolves with physical time.
Oct 14, 2026

When Do Discrete Actions Make Good Continuous Controllers?

Though modern AI models like LLMs predict discrete tokens, today's robotic foundation models represent actions as continuous vectors. In this paper, we challenge this common consensus by asking if continuous action parametrizations are superior to their discrete counterparts. We conduct an extensive comparison of single-step regression and multi-step flow variants of both continuous and discrete policies in both from-scratch single-task and multi-task VLA training, in both simulation and on real hardware. In all regimes, we find that discrete action prediction, even the most naive, uniform-bin quantization, can match or even outperform continuous-action policies in task success rate. Moreover, we find that the challenge to discrete action policies is not action precision, but rather factorization error introduced by product-distribution predictions across time and action dimensions. We show that, when paired with the correct interventions (iterative computation through discrete flows, or distribution sharpening through classifier-free guidance), discrete flow policies can turn this weakness into a strength, enabling more responsive action changes during a predicted action chunk. Lastly, we show that attempts to explicitly inject geometric information into discrete policies, e.g. through corruption processes that emulate continuous flow matching, do not yield consistent improvements. Taken together, our findings question existing assumptions that robotic action prediction requires distinct design decisions compared to other AI domains, and motivate the possibility of discrete action prediction as a compelling alternative to today's continuous action parametrizations. Project page: https://iscoyizj.github.io/discrete-action-website/
Oct 14, 2026

Refine Actions If Needed: Adaptive Action Chunk Refinement for Robot Manipulation

Computationally lightweight manipulation policies predict executable actions with low inference latency, but prediction errors can limit task success. Iterative generative policies can achieve higher task success rates, but repeated network evaluations increase inference latency. Refining action proposals from computationally lightweight policies can combine these strengths, but the amount of refinement needed varies across states. We introduce RAIN (Refine Actions If Needed), a framework that predicts action errors at different refinement levels to decide whether and how much to refine each executable proposal, before performing any refinement. We train an ensemble to predict these errors by comparing action proposals and their refined versions with expert actions from offline demonstrations, without requiring explicit labels of refinement needs. Calibration balances uncertainty, computation, and temporal consistency. We evaluate RAIN on eight ManiSkill tasks and four real-robot tasks. In simulation, our policy achieves 66.6% success, approaching the best evaluated diffusion-policy success rate with 5.71 times lower policy latency. On the real robot, success increases from 55.0% with Action Chunking with Transformers (ACT) to 72.5%, with comparable average successful completion time. Matched controls show that dynamic routing maintains the strongest observed fixed-refinement success level with 26.6% fewer refiner evaluations. Project page: https://rain-policy.github.io/.
Oct 14, 2026

ACRO: Actor-Critic Rollout Orchestration

Executing a vision-language-action (VLA) policy involves deciding when to continue an attempt and when to intervene to improve its chances of success. We introduce ACRO, an Actor--Critic rollout orchestration layer that makes these decisions for a fixed VLA. ACRO seeks interventions that offer a more promising continuation, are physically feasible, and leave sufficient time to complete the task. A Critic learned from policy rollouts estimates success prospects to decide when to intervene and select a re-entry target along the executed trajectory. Trajectory Retraction shortcuts the visited path to return the robot to that target, where the same VLA resumes execution from a fresh observation. We evaluate ACRO with GR00T N1.7 and π0.5π_{0.5} across SimplerEnv, RoboCasa, and real-robot manipulation. Under the same physical execution budget, including all return motion, ACRO improves success by 10.4, 7.3, and 21.7 percentage points, respectively. It also completes additional tasks as the execution budget grows. These results show that controlling when and where a policy resumes can turn its existing capabilities into more successful task executions. Project page: https://junhoo.me/acro
Oct 14, 2026

Accelerating VLA Inference with Perturbation Informed Execution

Action-chunking vision-language-action (VLA) models predict sequences of future robot actions. Under fixed-horizon execution, the robot executes a fixedlength prefix of each predicted chunk before invoking the policy again, leaving the remaining predictions unused. For a given number of executed actions, short execution horizons require more policy calls. Extending the execution horizon amortizes policy inference cost over more actions. However, uniformly applying long horizons across episodes can limit opportunities for precise corrections. To address this limitation, we propose PICES (Perturbation-Informed Chunk and Execution Horizon Selection), a training-free method that jointly selects an action chunk and the number of actions executed before the next policy call. Within a single policy call, the action expert generates a batch of action chunks from multiple initial noise samples and their locally perturbed counterparts, using the same conditioning features across all samples. PICES exploits differences between corresponding actions in each nominal chunk and its counterpart to determine candidate-specific execution horizons and select a nominal chunk for execution. Experiments on simulation benchmarks and real-world manipulation tasks demonstrate that PICES achieves speedup by up to 2.3x in wall-clock policy inference time on Jetson Orin and Thor relative to fixed horizon baselines while improving the success rate.
Oct 14, 2026

PolyMorph: Learning Locomotion Policy for Cross-Embodiment Adaptation

Reinforcement learning has enabled robust locomotion for legged robots, but learned policies are typically tied to a specific robot morphology and require additional engineering when the number of legs, actuators, or mechanical properties change. We present PolyMorph, a morphology-conditioned framework that learns a single locomotion policy for heterogeneous legged robots. PolyMorph converts each robot's URDF into joint-link modules and combines a recurrent encoder, graph-based Transformer, and per-joint decoder to generate actions across variable leg counts and joint configurations. To improve training stability, PolyMorph uses morphology-normalized rewards, adaptive robot sampling, and URDF-derived PD-gain initialization. We evaluate PolyMorph in simulation across bipedal, tripedal, and quadrupedal robots, including unseen morphology variants and platforms, and deploy the policy on real quadruped platforms operated in multiple configurations. The results show that a single PolyMorph policy generalizes across diverse robot morphologies without per-robot policy retraining.
Oct 13, 2026

PACER: Process-Aware VLA Policy Learning from Human Corrections for Robotic Disassembly

Robotic disassembly of end-of-life (EoL) products requires robots to accommodate product variation, follow prerequisite sequences, and approach components precisely for contact-rich manipulation. Supervised fine-tuning (SFT) provides a practical path for adaptation, but limited and costly disassembly data cannot capture the distribution shifts arising from changing environments and product uncertainties. The policy's own rollouts record its approach attempts, and human corrections demonstrate recovery from its errors, but turning these experiences into better policy performance remains challenging. We introduce PACER, a Process-Aware Correction and Evidence Reweighting framework that learns from these experiences through SFT, using progress toward the target and each trace's source and outcome to weight valid action chunks in the native supervised action loss. PACER trains one policy per weighting setting and selects one of the resulting policies through held-out validation. We evaluate PACER on UR5e motherboard disassembly across five component classes, where it achieves 87/100 successful approach-and-handoff trials on the held-out benchmark, compared with 54/100 for vanilla post-SFT.
Oct 13, 2026

LoopWAM: Closed-Loop Generalist Policy Improvement from Deployment Rollouts

Scaling expert demonstrations alone does not enable generalist robot policies to improve from deployment. Real-world rollouts contain successes, suboptimal behavior, and failures: imitating every recorded action can reinforce poor behavior, while filtering out failures discards evidence of physical interactions and their consequences. We introduce LoopWAM, a closed-loop world-action model that learns directly from this full quality spectrum, using rollouts from both itself and other deployed policies. Source-dependent noise sampling unifies behavior learning and action-conditioned world modeling, while quality steering and quality-weighted supervision retain full video supervision across qualities and regulate action imitation. Video and action tokens interact throughout parallel denoising, allowing learned consequences to inform action generation directly. On RoboChallenge Table30-V2, three deployment-and-training rounds raise success from 23.67% to 43.33%, a 19.7-percentage-point gain, with a final score of 56.80. LoopWAM also achieves 94.5% average success on RoboTwin 2.0 and 49.5% overall success on RoboCasa365 without additional embodied pretraining, obtaining the best overall results among the compared methods across all three benchmarks. On challenging shirt folding task, two rounds of deployment-driven improvement after single-task post-training raise success from 13.20% to 55.56%. These results demonstrate closed-loop improvement from mixed-quality experience under both multi-task learning and single-task post-training. Project page: https://loop-wam.github.io/