Papers

SimpleVLN: Towards Simple and Frontier Vision-Language Navigation

Vision-and-Language Navigation (VLN) requires embodied agents to ground language in visual observations and make long-horizon decisions. Existing methods often address these demands through task-specific architectures. As multimodal large language models (MLLMs) become increasingly capable, an important question remains: Have we truly unlocked the potential of native MLLMs for VLN before introducing task-specific architecture? We present SimpleVLN, an architecture-preserving framework developed through studies of navigation formulation, data construction, and optimization. At the formulation level, SimpleVLN combines single-turn decision inputs with fixed-budget global-local memory to efficiently use navigation history without unbounded context growth, while action chunks enable efficient output of multiple primitive actions per model invocation. For data construction, we combine expert demonstrations with policy-dependent DAgger experience and develop a scalable synthesis pipeline that generates large-scale tasks for reinforcement learning. At the optimization level, a progressive IL-DAgger-RL pipeline advances from action imitation to task-level outcome optimization. Comprehensive experiments validate the effectiveness of these three aspects. We instantiate SimpleVLN across multiple MLLM backbones and model sizes, demonstrating its generality. SimpleVLN achieves 76.7% and 80.1% success rates on the R2R-CE and RxR-CE splits, respectively, substantially outperforming existing methods. These results show that the navigation capabilities of native MLLMs can be effectively unlocked without task-specific architectural designs.

Vision-language navigationEmbodied AI

Lingyi Hong, Weiren Cai, Jiayu Chen · 34 views · Oct 16, 2026

Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

Agent learning is shifting from learning from human data toward learning through interaction with the world. However, scaling such learning directly in real-world computer systems is challenging and can introduce substantial security risks. We therefore propose Agent World Model in the Wild (WildAWM), a scalable pipeline for synthesizing controllable environments and tasks for training general computer-use agents (CUAs). Whereas existing approaches typically specialize in a single agent interaction interface, we construct executable environments that jointly support graphical user interfaces, model context protocol services, and command-line interfaces, allowing agents to flexibly combine visual interaction, tool use, and code execution. WildAWM is entirely powered by open-source models, demonstrating that high-quality computer-use environments can be generated without proprietary frontier models. Beyond environments, we address three recurring challenges in task synthesis: ensuring solvability, maintaining sufficient difficulty, and producing reliable verifiers, by introducing execution-based quality gates that combine heterogeneous agent rollouts, cross-judge consistency checks, and counterfactual probes of judgment robustness. The resulting pipeline synthesizes 341 long-horizon environment-task pairs that can require over 100 agent steps to solve and remain challenging even for frontier models, with GPT-6-Astra solving only 60% of them. We train two Qwen models of different sizes exclusively in these synthetic worlds. Both models achieve substantial gains across 8 out-of-distribution benchmarks spanning web, claw, and computer-use agents, demonstrating that learning in WildAWM's synthesized worlds generalizes broadly to unseen computer-use tasks. The code is publicly available at https://github.com/MSR-Orchard/WildAWM.

Computer-Use AgentWorld Models

Zhaoyang Wang, Qianhui Wu, Haorui Wang · 25 views · Oct 19, 2026

Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching

While recent advances in humanoid locomotion have achieved stable walking on varied terrains, capturing the agility and adaptivity of highly dynamic human motions remains an open challenge. In particular, agile parkour in complex environments demands not only low-level robustness, but also human-like motion expressiveness, long-horizon skill composition, and perception-driven decision-making. In this paper, we present Perceptive Humanoid Parkour (PHP), a modular framework that enables humanoid robots to autonomously perform long-horizon, vision-based parkour across challenging obstacle courses. Our approach first leverages motion matching, formulated as nearest-neighbor search in a feature space, to compose retargeted atomic human skills into long-horizon kinematic trajectories. This framework enables the flexible composition and smooth transition of complex skill chains while preserving the elegance and fluidity of dynamic human motions. Next, we train motion-tracking reinforcement learning (RL) expert policies for these composed motions, and distill them into a single depth-based, multi-skill student policy, using a combination of DAgger and RL. Crucially, the combination of perception and skill composition enables autonomous, context-aware decision-making: using only onboard depth sensing and a discrete 2D velocity command, the robot selects and executes whether to step over, climb onto, vault or roll off obstacles of varying geometries and heights. We validate our framework with extensive real-world experiments on a Unitree G1 humanoid robot, demonstrating highly dynamic parkour skills such as climbing tall obstacles up to 1.25m (96% robot height), as well as long-horizon multi-obstacle traversal with closed-loop adaptation to real-time obstacle perturbations.

HumanoidParkour

Zhen Wu, Xiaoyu Huang, Lujie Yang · 40 views · Feb 17, 2026

Blind Precise Assembly: Proprioceptive Sim-to-Real Peg-in-Hole for Diverse Parts

Every robot already carries high-resolution contact sensors: its own joints. Legged robots and humanoids exploit them to walk, run, and track whole-body motions without vision, but there the contacts are large and forceful. Is joint sensing also enough for precise, contact-rich assembly, where the robot must find a millimeter-scale opening, mesh gear teeth, or catch a thread through light contact? We study this question by training blind assembly policies that observe only a short history of joint positions, velocities, and their own actions, without visual, force, torque, or tactile sensing. The poses of both the fixture and the part are unknown to the policy, and the grasp is randomized substantially. The policy must therefore assemble the parts through contact, sensed exclusively through its own proprioception. Trained with reinforcement learning entirely in simulation over randomized parts, grasps, and contacts, such policies learn peg insertion, gear meshing, and nut threading. The peg insertion policy transfers zero-shot to the real world and inserts pegs of different shapes and sizes in 73% of trials. Controlled comparisons with matched visual policies in simulation show that blind policies generalize far better to unseen part shapes and sizes, though they can be slower. Training such policies needs thousands of different assemblies, each simulated with its clearance intact, so we also release an open-source generator that builds them procedurally from exact convex pieces for MuJoCo; it is more accurate and faster than convex decomposition or MuJoCo's signed-distance collision. Videos and interactive simulations are at https://younghyopark.me/blind-proprioceptive-assembly/.

Peg-in-HoleSim-to-Real

Antonia Bronars, Younghyo Park, Kushal Kedia · 91 views · Oct 16, 2026

Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine

Converting verifier outcomes into useful policy updates and partial progress into complete task resolution is crucial for terminal agents. We present Terminal-RSI, which alternates Recursive Self-Rewrite (RSR) of verified trajectories with critic-inheriting Recursive Policy-Refine (RPR). We formulate Turn-Boundary Skip-Observation GAE (TB-GAE) to retain token-specific baselines while applying decay across interaction turns. Family Dense Reward (FDR) calibrates semantic progress across task families; Success-Prioritized Reward (SPR) separates strict success from bounded partial credit. A Warm-up Critic Model, recursive critic handoff, and stage-specific learning rates coordinate the two refinement phases. The five-stage sequence from Qwen3.8-27B base model through RSR-1, RPR-1, RSR-2, and RPR-2 yields Terminal-RSI-27B: 19.84% on Terminal-Bench 4.0, 86.52% on Terminal-Bench 2.1, 16.95% on Terminal-Bench 3.0, and 79.00% on Terminal-Bench Hard. On LHTB, process reward rises from 0.21 to 0.37 and strict completion from 0/46 to 5/46; SWR100 success doubles from 3.00% to 6.00%. By recursively coupling verified trajectory rewriting with critic-inheriting policy refinement, each retained stage consolidates discovered behaviors and progressively advances the agent from partial local repairs to strict terminal verification.

Terminal AgentReinforcement Learning

Junyao Yang, Zongxia Li, Yucheng Shi · 151 views · Oct 15, 2026

BRACE: Adapting Whole-Body References for Force and Terrain Aware Humanoid Motion Tracking

Whole-body tracking has become the interface through which operators drive humanoid robots, yet the references it consumes are recorded on level ground and carrying nothing, so the tracker knows neither the forces the robot must exchange with objects nor the terrain it stands on. Existing controllers address one side of the gap: force-capable policies command an end-effector force but prescribe no whole-body pose, while terrain-adaptive trackers treat loads as disturbances to reject rather than wrenches to command. BRACE folds both into the reference the tracker follows: terrain conformance lifts footholds and root onto the local surface, and a wrench transformation resolves the hand displacement that produces a commanded force together with the center-of-mass and center-of-pressure shifts it induces, bounded by teacher-specific arm-effort limits. Separate exertion and compensation teachers are distilled by DAgger into one flow-matching student that runs on proprioception alone, without a height map or measured wrench, so a teleoperator can supply a flat-ground trajectory while the robot resolves slope and load onboard. On the Unitree G1, in simulation and on hardware, BRACE cuts global tracking error by 40% on average and improves success rate by 18.25 points.

HumanoidWhole-Body Control

Sudarshan Harithas, Chen Yu, Juan Borbon · 196 views · Oct 5, 2026

QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents

Large language model (LLM) agents increasingly undertake extreme-long (xLong) horizon tasks, where a single execution can span hours, hundreds of model-environment interactions, and nearly 1M tokens per rollout. Applying online reinforcement learning (RL) to such executions poses two fundamental challenges: (1) severe execution variance and prolonged rollout delays cause massive GPU idling; and (2) complex non-linear branching generates massive trajectory redundancy, crippling training efficiency. To address these, we present QwenGyre, an end-to-end framework for xLong-horizon online RL. QwenGyre elastically reallocates GPUs between rollout and training without interrupting live executions, while its trajectory processor reconstructs branching histories, scores partial progress, and deduplicates redundant paths to bound training costs. Scaled to our flagship model, Qwen 3.8 2.4T, with 700K tokens per rollout, QwenGyre yields a 6.0% absolute gain on NL2RepoBench (52.5% to 58.5%) in 48 steps. Across our evaluations on diverse domains of training datasets, QwenGyre delivers up to 1.85x and 1.78x speedups over Colocate and Async, respectively.

Reinforcement LearningLLM Agent

Weiqi Wang, Yuxin Zhou, Mouxiang Chen · 227 views · Sep 27, 2026

IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation

Most autoresearch systems couple idea generation with implementation, experiments, and writing, so it is unclear whether success comes from the idea or from downstream execution. IdeaScientist isolates research ideation as a standalone task: given a problem definition and a challenge that current solutions fail to meet, produce a grounded research proposal. An orchestrator coordinates three sub-agents - a gap finder that locates the shared methodological limitation in same-problem prior work, an innovator that retrieves mechanisms which solved an analogous challenge in other fields and adapts them, and a report writer that develops the surviving intuition into a complete proposal. Each role is trained separately with asynchronous GRPO and reference-grounded rubric rewards. The Svalbard Idea Vault decomposes 4.7M arXiv papers into 2.77M (problem, challenge, gap, intuition, proposal) tuples for retrieval, training, and temporally controlled evaluation with a January 1, 2026 cutoff and 277 held-out post-cutoff methodology papers. On Qwen3.6-27B, IdeaScientist reaches 74.6% overall, 14.0% above the strongest open-source autoresearch baseline, driven mainly by novelty, and beats Claude Code SDK with Claude-4.8-Opus by 5.9% and Codex SDK with GPT-5.4 by 5.1% on the same open backbone.

AI ScientistLLM Agent

Jiarui Liu, Renjie Tao, Yiwei Liao · 357 views · Oct 2, 2026

PhoneBot: A Low-Cost Open Humanoid Robot Platform Reusing Smartphones

PhoneBot is a roughly 400-dollar open-source 13-DoF bipedal platform that reuses a commodity smartphone as its IMU, camera and onboard computer. A torque-aware DYNAMIXEL XL430 actuator model in MJX, combined with sagittal-mirrored PPO, yields balanced walking, standup and camera-heading policies that run entirely on old or prepaid Android phones.

HumanoidOpen-source hardware

Ruochen Hou, Quanyou Wang, Daniel Koh · 263 views · Oct 6, 2026

Agile and Generalized Legged Locomotion via Attention-Based Neural Map Encoding

Achieving agile and generalized legged locomotion across terrains requires tight integration of perception and control, especially under occlusions and sparse footholds. Existing methods have demonstrated agility on parkour courses but often rely on end-to-end sensorimotor models with limited generalization and interpretability. By contrast, methods targeting generalized locomotion typically exhibit limited agility and struggle with visual occlusions. We introduce a unified reinforcement learning (RL) framework for agile and generalized locomotion that incorporates a novel attention-based map encoder in the control policy. This encoder extracts local and global mapping features and uses attention mechanisms to focus on salient regions, producing an interpretable and generalized embedding for RL-based control. We further propose a learning-based mapping pipeline that provides fast, uncertainty-aware terrain representations robust to noise and occlusions, serving as policy inputs. It uses neural networks to convert depth observations into local elevations with uncertainties, and fuses them with odometry. The pipeline also integrates with parallel simulation so that we can train controllers with online mapping, aiding sim-to-real transfer. We validate our framework with the proposed mapping pipeline on a quadruped and a biped robot, and the resulting controllers demonstrate strong agility and generalization to unseen terrains in simulation and in real-world experiments.

Legged LocomotionReinforcement Learning

Chong Zhang, Victor Klemm, Fan Yang · 376 views · Jan 13, 2026

HuMBLE: Human Motion-Driven Behavior Learning for Embodied Locomotion

Despite recent advances in humanoid locomotion, controllers optimized for command tracking and robustness tend to produce mechanical gaits, whereas controllers tied to human motion data often fail to generalize to commands outside the data distribution. This work introduces a learning framework that balances these competing objectives to synthesize real-time steerable, robust, and biomimetic locomotion policies from human data. Using an in-house curated locomotion dataset covering diverse speeds and directions, we first learn a natural locomotion prior policy through a teacher-student distillation process. Specifically, we train a full-body reference-conditioned policy with Reinforcement Learning (RL), then distill it into a lightweight prior policy conditioned solely on proprioception and a planar torso-velocity steering command. Next, we fine-tune the prior policy with multi-task RL to expand command coverage and robustness beyond the data distribution, pairing a goal-conditioned task that tracks arbitrary commands with a reference-guided task that tracks the human data as an explicit style regularizer. We validate our framework on three humanoid robots: the Boston Dynamics Atlas R1, Atlas D1, and Unitree G1. Experimental results demonstrate robust performance across real-world scenarios, including direct user-controlled locomotion in indoor and outdoor environments, and integration as the locomotion layer within hierarchical control stacks. Benchmarks against Tabula Rasa RL policies trained without human data and ablation studies confirm that our framework yields a lightweight, deployable policy that reconstructs coordinated whole-body behavior from a steering command, retaining the human gait characteristics while remaining robust and fully steerable.

Humanoid LocomotionMotion Imitation

Mike Zhang, Dongho Kang, Kevin Bergamin · 615 views · Oct 7, 2026

CHOREO: Every Humanoid Skill as a Trajectory

CHOREO, from Ocean University of China and CASIA, is a training-free framework for composing heterogeneous humanoid skills: motion libraries, RL policies, and generative models are converted into SkillMotion trajectory assets with semantics and boundary descriptors, and boundary mismatch scoring decides between a quintic seam (matching position, velocity, and acceleration) and a pre-validated standing bridge before a frozen GMT tracker executes on Unitree G1. It reaches 95.4% sequence success across 130 multi-action tasks (93.8% on eight-action sequences), 96.7% switch success over 552 boundaries, cuts the fall rate from 41.5% to 4.6%, and admits all 3,069 heterogeneous instances.

Humanoidskill-composition

Ziyi Sun, Jingwen Chen, Yuxi Wang · 455 views · Sep 11, 2026

As an Amazon Associate, we earn from qualifying purchases.