Papers

nanoMuse: An Open-Source Personal Agent for Every Device You Own

nanoMuse places a full personal agent on each device, routes every tool call through a scoped Sentinel policy gate, and keeps synchronization optional. The open-source stack supports readable memory, provider choice, phone and desktop control, and self-hosted relay deployment.

Personal AgentOn-Device AI

Guangyi Liu, Yong Liu, Jiangning Zhang · 153 views · Oct 6, 2026

GLaM: Training a Latent World Model over Global Spatiotemporal Memory for Active Exploration and Navigation

GLaM is a goal-conditioned latent world model over an online spatiotemporal map that jointly predicts future map representations and robot-centric waypoint latents, with GLaM Nav adding observation-based verification, retrieval, and geometric control. On a controlled 50% HM3D-ObjectNav subset, it raises success rate from 78.50% to 86.89% and SPL from 47.70% to 48.35%; qualitative Astribot S1 demonstrations cover exploration and memory-based return in an unknown office.

Embodied AIObject Navigation

I-Tak Ieong, Ruizhi Feng, Zhaoyang Lu · 172 views · Sep 13, 2026

UniWAM Technical Report: Unified Mobile Manipulation via Mixed-Stream World-Action Modeling and Manipulation Anchor Pose Supervision

UniWAM models navigation and manipulation as independently sampled control streams over shared video and action diffusion transformers. It introduces automatically generated Manipulation Anchor Pose supervision at the scale of 1.5 million episodes, improving manipulation-ready docking accuracy and mobile-manipulation success on MAP-Bench and 24 real-robot tasks.

Mobile ManipulationWorld-action models

Wei Xue, Keliang Liu, Mingzhang Cui · 174 views · Sep 30, 2026

METATRON: A Promptable Whole-Body Execution Layer for Humanoids

Humanoid controllers often require task-specific training despite sharing the need for balance and whole-body coordination. We present Metatron, a promptable whole-body execution layer combining a generative base policy with a programmable skill layer. The base policy receives partial goals, collectively called a prompt, that can combine timed body-part targets, velocity commands, and style cues. It produces diverse whole-body motions consistent with these goals. Training combines motion capture, synthetic recovery trajectories, and retargeted scene-interaction motions. After training, the policy is frozen. Stateful programs called skills express task intent as prompts at each control step, drawing rough geometric sketches that the policy turns into coordinated movement. Skills are ordinary code, refined by coding agents that analyze motion data and fit compact rules without task-specific policy training. On the physical Unitree G1, one frozen checkpoint supports walking, recovery, teleoperated object pickup, and sitting on furniture. Comparative evaluations show higher reaching success and push robustness than the tested reference-tracking pipelines. The same recipe produces climbing and acrobatics on a simulated character. Metatron enables coding agents to turn learned motor capabilities into new skills through code, without further policy training.

HumanoidWhole-Body Control

Chen Tessler, Yifeng Jiang, Alec Otto · 452 views · Oct 27, 2026

L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory

L3G-World maintains a compact latent 3D Gaussian memory that adds primitives only in unseen regions and refines existing ones. Rendering the memory directly into diffusion latent space avoids VAE re-encoding and sustains long-horizon consistency at 9.02 FPS on one H100.

World Models3D Gaussian Splatting

Jinhyeok Choi, JoungBin Lee, Jongmin Lee · 300 views · Oct 29, 2026

BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion

BeyondMimic first masters diverse agile humanoid skills with a compact motion-tracking formulation, then composes and guides them through a unified latent diffusion model for unseen tasks and zero-shot deployment.

HumanoidMotion Tracking

Qiayuan Liao, Takara E. Truong, Xiaoyu Huang · 158 views · Aug 11, 2025

Memory Tax: Dissecting the Net Value of Agent Memory

Memory is increasingly used in long-horizon agents, yet the net value of building memory over direct retrieval from raw history remains largely unclear. Through a large-scale evaluation across multiple benchmarks and model backbones, we find many dedicated memory systems underperform naive RAG in many cases, indicating a negative net value. Taking RAG as a reference, we dissect the net value of memory into the gains and losses over direct retrieval, termed memory benefit and memory tax. These gains and losses arise because memory process changes how the raw information is organized and accessed. We view such changes as the double-edged deviations from the raw history. They are originally designed and introduced to benefit the task, for example by reorganizing facts or distilling preferences, but some may also remove or obscure evidence, giving rise to memory tax. Since memory benefit reflects the expected gains of its design, we then focus more on the overlooked memory tax, study how it arises from the system and evaluation side, and generalize the concept to more application scenarios of memory. We hope the notion of memory tax can provide a new lens and shift more attention from standalone performance to the net value of memory, informing more reliable memory designs and evaluations. We will open-source the code and results to the community. Project Page: https://hexuan21.github.io/MemoryTax/

Agent MemoryLong-Term Memory

Xuan He, Sining Zhoubian, Ruozhen Yang · 257 views · Oct 25, 2026

Harness-Zero: Harness Distillation via Agent-as-Harness

Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain tied to the harness at deployment. Because the best harness varies across domains, instances, and models, a general-purpose agent must either settle for a suboptimal shared harness or route among an ever-growing set of specialized ones. We therefore study agent harness distillation: using a domain- or instance-optimized harness as training-time guidance and transferring the behaviors it induces into model weights, so that its gains survive under a single fixed target harness. The challenge is that the two harnesses differ in action space and available information, so guidance from the optimized harness cannot serve directly as supervision for the target one. We introduce Harness-Zero, which enables harness distillation through agent-as-harness. Guided by the optimized harness, a harnessing agent corrects student responses before execution in the target harness's action space, turning harness guidance into training demonstrations. Fine-tuning on the resulting trajectories internalizes harness-induced behavior into the model, so the specialized harness can be removed at deployment. Our experiments spanning knowledge work, tool use, and science domains show that: (1) For frontier LLMs using the same evolved harness, agent-as-harness outperforms code-as-harness. (2) With the specialized harness removed at deployment, Harness-Zero improves the base model's macro-average task success from 23.3% to 44.3%, even exceeding the 41.7% it reaches with that harness still attached. (3) Harness-Zero recovers harness-induced behaviors absent from the base model, with 82.3% average recovery across 28 patterns in the three domains.

Agent HarnessHarness Distillation

Ye, Haoran, Lu, Yuxing, Dong, Haonan · 255 views · Sep 21, 2026

Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning

We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a model's ability to solve complex, verifiable tasks can be enhanced even when generating synthetic data is infeasible and only binary feedback is available. Our framework operates in two stages: first, upon failing a given task, the model generates a self-reflective commentary analyzing its previous attempt; second, the model is given another attempt at the task with the self-reflection in context. If the subsequent attempt succeeds, the tokens generated during the self-reflection phase are rewarded. Our experimental results show substantial performance gains across a variety of model architectures, as high as 34.7% improvement at math equation writing and 18.1% improvement at function calling. Notably, smaller fine-tuned models (1.5 billion to 7 billion parameters) outperform models in the same family that are 10 times larger. Our novel paradigm is thus an exciting pathway to more useful and reliable language models that can self-improve on challenging tasks with limited external feedback.

Large Language ModelsReinforcement Learning

Shelly Bensal, Umar Jamil, Christopher Bryant · 208 views · May 30, 2025

RLSR: Reinforcement Learning from Self Reward

Large language models can generate solutions to complex problems, but training them with reinforcement learning typically requires verifiable rewards that are expensive to create and not possible for all domains. We demonstrate that LLMs can effectively self-improve through self-judging without reference solutions, leveraging the inherent asymmetry between generating and verifying solutions. Our experiments show that models can provide reliable reward signals without ground truth answers, enabling reinforcement learning in domains where verifiable rewards are impractical. By implementing self-judging across Countdown puzzles and integration problems, we achieve performance comparable to formal verification without ground truth solutions. Most notably, Qwen 2.5 7B DeepSeek Distilled trained with self-rewards qualifies for the prestigious MIT Integration Bee competition, performance through self-supervised improvement. When combined with synthetic question generation, we establish a complete self-improvement loop where models generate practice problems, solve them, and evaluate their own performance without any external validation. Our findings demonstrate that LLM judges can provide effective reward signals for training, unlocking reinforcement learning in countless domains previously limited by reward engineering challenges. This work represents a significant step toward autonomous AI systems that continuously improve through self-directed learning rather than human-guided training, potentially accelerating progress across domains where training data is scarce or evaluation is complex.

Reinforcement LearningLarge Language Models

Toby Simonds, Kevin Lopez, Akira Yoshiyama · 195 views · May 12, 2025

Post-Training Large Language Models via Reinforcement Learning from Self-Feedback

Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. Recent research suggests that Chain-of-Thought (CoT) reasoning paths are inherent in pre-trained LLMs and can be elicited by simply altering the decoding process, where the presence of a CoT path correlates with higher answer confidence. Building on these insights, we present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that utilises the model's intrinsic confidence as a self-generated reward. By generating multiple CoT decoding beams from a frozen LLM, we compute the confidence of each final answer span and rank the resulting traces accordingly to create synthetic preferences. These preferences are subsequently utilised to fine-tune the policy through standard preference optimisation, requiring no human labels, gold answers, or externally curated rewards. RLSF simultaneously (i) refines the model's probability estimates–restoring well-behaved calibration–and (ii) strengthens step-by-step reasoning, yielding improved performance on arithmetic reasoning and multiple-choice question answering. By converting a model's own uncertainty into structured self-feedback, RLSF affirms reinforcement learning on intrinsic model behaviour as a principled and data-efficient component of the LLM post-training pipeline. Our results demonstrate that leveraging these inherent reasoning capabilities provides a robust path for enhancing model reliability without manual prompt engineering or external supervision.

Large Language ModelsReinforcement Learning

Carel van Niekerk, Renato Vukovic, Benjamin Ruppik · 366 views · Jul 29, 2025

SGM-SLAM: Scene Graph Matching for Data-Efficient Distributed SLAM

We introduce a data-efficient distributed Simultaneous Localization and Mapping (SLAM) framework for multi-robot operation in GPS-denied and communication-constrained environments. The framework is designed for teams of robots equipped with LiDAR, cameras, and inertial sensors, where robots may operate from independently initialized local coordinate frames and share only limited spatial overlap. Our approach constructs a scene graph by using fused RGB-LiDAR point clouds to generate both a semantically segmented point cloud layer, and a layer of discrete bounded objects, to accompany estimated robot trajectories. Scene graph matching is performed collaboratively through exchanging and matching object data with neighboring robots. To maximize communication efficiency, we utilize a multi-step data exchange and optimization process. We demonstrate the effectiveness and communication efficiency of the proposed approach using real-world datasets containing limited trajectory overlap, viewpoint variation, repeated structures, and degraded visual conditions.

Distributed SLAMScene Graph Matching

Yewei Huang, Tixiao Shan, Abhinav Rajvanshi · 140 views · Jun 15, 2026

As an Amazon Associate, we earn from qualifying purchases.