ClawGym II: Exploring Black-Box RL on Agent Harness

Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment. However, reinforcement learning through complex harnesses remains largely unexplored, as scaling such training to long-horizon agent tasks introduces fundamental challenges. In this work, we present a unified black-box RL framework for stable and scalable optimization of general agents through complex harnesses. Concretely, we first build a sandbox-based execution infrastructure that isolates task environments and harnesses within temporary sandboxes for large-scale concurrent rollouts. We then decouple policy optimization from opaque harness execution and place a serving proxy at the model boundary to capture model calls. To reconstruct multi-turn trajectories and improve training efficiency, we organize the captured calls into prefix trees and further adapt both critic-based PPO and critic-free GRPO to optimize over the recovered tree structure. Meanwhile, we maintain training-inference consistency throughout the optimization process. Finally, we introduce mix-harness training, allowing a single model to be jointly optimized by heterogeneous harnesses. With Qwen3-30A3B, black-box RL improves Pass@1 on ClawGym-Bench by 9.98 and 14.81 points through OpenClaw and Claude Code, respectively, while remaining stable over 200-400 optimization steps. Moreover, the framework yields consistent gains on more challenging tasks such as JobBench and OfficeQA. Overall, our framework enables effective, stable, and scalable optimization of general agents through black-box harnesses, supporting unified training across heterogeneous execution systems.

Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models

On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled from the student's own policy, yet its generalization behavior remains poorly understood, as most studies evaluate OPD on a single domain and on benchmarks close to the training data. We present a controlled study that varies one generalization factor at a time, from in-domain distribution shifts to cross-domain transfer and the multi-teacher setting. We find that OPD transfers a teacher's reasoning behavior rather than its answers to particular problems: training difficulty barely matters, and even problems the teacher never solves are useful. Transfer depends strongly on the origin relationship between teacher and student: same-origin pairs bring the student close to the teacher across languages, reasoning horizons, and even other domains, whereas cross-origin pairs mostly fit the trained distribution. This broad reach is a double-edged sword: since routing prompts to domain experts cannot confine each teacher's influence, combining them yields a mixture-dependent seesaw among their capabilities. These results clarify when OPD generalizes and offer a useful perspective for diagnosing multi-teacher OPD.

RoadWeaver: Large-Scale Lane-Level HD Map Generation from Scratch for Autonomous Driving Simulation

Autonomous driving simulation requires diverse and scalable lane-level HD maps to support long-horizon evaluation across complex road networks. Existing approaches either rely on handcrafted or reconstructed real-world maps, which limits scalability, or generate only local road structures rather than complete HD maps. We present RoadWeaver, a coarse-to-fine framework for from-scratch generation of diverse, large-scale HD maps. RoadWeaver first synthesizes a global road layout, expands it into a connected road network, and then constructs lane-level geometry with topologically consistent lane connectivity. Experimental results show that RoadWeaver achieves a 99.8\% reachability, a 10.7\% dead-end ratio, and an endpoint alignment error of 0.24 m. Compared with SOTA generation methods, it reduces endpoint alignment error by 94.4\% while generating complete HD maps in 1.39--3.50 s. The generated maps can be directly deployed in driving simulators, providing scalable simulation environments for future closed-loop evaluation of autonomous driving systems. The training code and an out-of-the-box implementation of RoadWeaver will be released upon acceptance.

Quantum Coordination Advantages in AI State-Tracking Tasks: Semantic Compilation and Latent Memory

We prove inference-time quantum coordination advantages for specified AI state-tracking tasks. A solver compresses semantic history into a future-accessible boundary state and later answers a query. We count communication $B$, persistent instance-dependent memory $M$, and local work $D$; classical recurrence, caches, tools, and recomputation are allowed and charged. The central result is a boundary-preserving semantic-compilation theorem. It maps a finite one-way, streaming, or adaptive causal task into a semantic AI interface while preserving event order and access to past input. Classical boundary-state lower bounds and quantum-memory upper bounds transfer up to explicit compiler overhead, independently of the finite-precision recurrent architecture. Two applications have classical semantics. Matched-entity synopsis QA inherits the hidden-matching separation between $O(\log N)$ qubits and $Ω(\sqrt{N})$ classical boundary bits. Continual requirements auditing inherits a Max-$k$SAT streaming separation: a recurrent solver uses $O(\log^5 n\log(1/δ))$ qubits and polylogarithmic classical workspace to obtain a $0.7172$-approximation, whereas every classical one-pass finite-information solver attaining that ratio requires $Ω(\sqrt{n})$ coordination width. As a quantum-native compiler test, a stabilizer latent-state dialogue uses $n$ qubits, while every exact finite-state classical causal online realization satisfies $B+M \ge \frac{1}{2}n^2+(\frac{3}{2}-\log_2 3)n+O(1)$. The source protocols, streaming algorithms, and stabilizer witness are imported; the new result is their architecture-independent semantic transfer. These are memory and coordination separations, not runtime or empirical advantages for present-day language models. The stabilizer result assumes exact simulation and ideal noiseless quantum memory.

Self-Evolving Neuro-Symbolic Skills for Tool-Augmented Spatial Reasoning

Large vision-language models have achieved strong performance in multimodal reasoning, but they remain unreliable on fine-grained spatial tasks that demand both precise spatial perception and fine-grained geometric computation beyond end-to-end generation. Tool augmentation offers a natural solution, while existing methods either plan tool calls from scratch without explicit dependency constraints or rely on fixed pipelines that are redundant and generalize poorly across spatial tasks. An effective spatial reasoning agent should instead accumulate reusable experience and adaptively compose it for new problems. To this end, we propose NeSy-Spatial, a neuro-symbolic framework for self-evolving spatial skills. NeSy-Spatial abstracts tool interactions and geometric operations into typed executable atomic instructions and composes them into two complementary skill types: Tool-Use Skills for organizing tool execution and Geometry Skills for structured geometric reasoning. During inference, NeSy-Spatial retrieves and executes relevant skills in a closed-loop process. During evolution, it analyzes buffered successful and failed trajectories to refine skill structures and prune unreliable or inactive entries. Experiments on three spatial reasoning benchmarks show that NeSy-Spatial consistently improves reasoning accuracy with more precise tool utilization.

VLN-AVP: Zero-Shot Vision-Language Navigation with Hybrid Long-Short-Term Memory for Autonomous Valet Parking

Existing methods in Autonomous Valet Parking (AVP) typically rely on pre-built maps, which severely restricts their scalability to unseen environments and open-vocabulary targets. Inspired by the application of Vision-Language Models (VLMs) in Vision-Language Navigation (VLN) tasks, we propose VLN-AVP, a zero-shot navigation framework for AVP tasks. By combining the precise spatial perception of a Bird's-Eye-View (BEV) model with the general intelligence of VLMs, our framework 1) eliminates the dependency on pre-built maps, 2) interprets semantic environmental contexts in parking scenarios, and 3) enables intuitive navigation following natural language instructions. Specifically, we introduce a hybrid memory system: a short-term perception memory tracks semantic visual cues to address the limitations of VLM's single-frame reasoning in existing methods, while a long-term topological memory facilitates stable policy learning from past experiences. To bridge the gap in existing benchmarks, we also present the VLN-AVP dataset and benchmark. Featuring 10 high-fidelity parking scenes and over 1,000 navigation episodes, it has the largest number of garage scenes to date and is the first VLN benchmark for underground parking. Extensive experiments demonstrate that in simulation, our method achieves an over 25% improvement in success rate compared to VLN methods and an over 15% improvement compared to other autonomous driving methods. Furthermore, it attains a leading success rate in real-world vehicle experiments, proving its practical feasibility.

Towards Precision Therapy in Hepatocellular Carcinoma: A Clinical-Reasoning LLM for Risk Stratification and Treatment Guidance

Hepatocellular carcinoma (HCC) is a common malignancy and a leading cause of cancer-related mortality. Current guidelines and staging systems provide coarse categories, but often miss within-stage heterogeneity and the clinical context in electronic medical records (EMRs). We present HCC-STAR (Hepatocellular Carcinoma Staging, Treatment And pRognosis), a clinically aligned large language model that reads routine EMR narratives and jointly outputs risk score-based staging, ranked guideline-consistent treatments with evidence-based rationales, and individualized survival estimates. We curated about 30,000 HCC cases from SEER and expanded them into EMR-style narrative training data using a clinician-validated, prompt-based augmentation workflow. On this corpus, we developed a knowledge-aligned reasoning framework optimized with a step-verifiable composite reward, moving beyond text-level memorization of clinical guidelines. In a multi-center cohort of 6,668 patients from 12 hospitals in China, HCC-STAR achieved state-of-the-art performance in treatment recommendation and risk stratification compared with clinical guidelines and competitive models, including GPT-5 and Gemini-2.5 Pro. Hypothetical overall-survival analysis showed a median survival of 51 months under adherence to HCC-STAR recommendations, compared with 29 and 32 months under BCLC and CNLC. In clinician-centric evaluations, blinded hepatobiliary specialists rated HCC-STAR's reasoning and evidence-based justifications as trustworthy. The model surpassed resident and attending physicians in treatment accuracy and helped physicians make more accurate decisions faster when used as an assistant. These findings support HCC-STAR as a reliable and verifiable decision-support system for risk stratification and precision therapy in HCC.

Beyond Random Sampling: Distribution-Aware Alignment for Semi-Supervised Medical Image Segmentation

Precise medical image segmentation is crucial for clinical diagnosis and treatment planning, yet relies heavily on expensive expert annotations. Semi-supervised medical image segmentation (SSMIS) offers a cost-effective solution but typically operates under the assumption of independent and identically distributed (i.i.d.) data, defaulting to random sampling. While statistically valid at scale, this strategy suffers from severe representation bias in low-data regimes, failing to capture the heterogeneous medical data manifold. To address this, we propose a highly data-efficient framework driven by distribution alignment. First, we introduce an offline Distribution-Aware Sample Selection strategy. By leveraging Vision Foundation Models (VFMs) and our designed Density-K-Center algorithm, we explicitly identify representative structural anchors, establishing a more representative labeled domain. Second, to bridge the remaining distribution gap, we propose the Memory-guided Copy-Paste (MCP) module. Tailored for the inherent class imbalance in medical scans, MCP leverages a semantic memory mechanism to retrieve historically consistent priors for cross-domain alignment, encouraging semantic consistency. Coupled with an easy-to-hard progressive schedule, this framework effectively mitigates early-stage pseudo-label noise. Extensive experiments on six diverse 2D and 3D datasets demonstrate strong segmentation performance, particularly in extremely low-labeled scenarios (\eg, 1/16 ratio).

DSIP: A Dynamic Coordination Planner for Signal-Free Intersections using Diffusion-Model-Based Multi-Agent Motion Planning

Traffic signal control at urban intersections inherently introduces stop-and-go behavior, resulting in increased delays and reduced traffic efficiency, especially under high traffic demand. With the emergence of connected and automated vehicles (CAVs), trajectory-level coordination has emerged as a high-potential strategy to augment or transcend conventional phase-based management. This paper proposes DSIP (Diffusion-model-based Signal-free Intersection Planner), a multi-agent motion planning framework driven by a generative diffusion process. DSIP shifts the intersection management paradigm from discrete temporal phasing to continuous multi-vehicle trajectory optimization. This work evaluates the theoretical upper-bound performance of this coordination strategy under idealized communication and execution conditions to isolate the core benefits of the diffusion-driven approach. Using the SUMO platform, we evaluate DSIP across diverse four-leg intersection configurations. Experimental results demonstrate that DSIP significantly reduces average delay and maintains higher average speed compared to both fixed-time signal control and state-of-the-art reinforcement-learning-based controllers, particularly in medium- to high-density traffic. These findings suggest that diffusion-based trajectory planning provides a scalable and robust foundation for future autonomous intersection management. By unlocking latent intersection capacity through software-defined coordination, this approach offers a cost-effective pathway to improve urban traffic flow efficiency without requiring physical infrastructure expansion.

Not All Relations Rotate Alike: Transformation-Aware Decoupling for Viewpoint-Robust 3D Scene Graph Generation

3D Scene Graph Generation (3DSGG) represents 3D scenes as structured object-relation-object graphs, providing a compact relational abstraction for spatial understanding. In embodied intelligence settings, the same 3D scene may be observed by agents from viewpoints that differ by yaw rotations. However, current 3DSGG models often fail to produce relation predictions that follow the expected transformation behavior under such viewpoint shifts. This behavior reveals an empirical mismatch related to predicate-level transformation heterogeneity: directional predicates such as left, front, right, and behind should transform with the observation frame, whereas most contact, support, and semantic predicates such as standing on and attached to should remain stable. To reduce this mismatch, we propose Transformation-Aware Decoupling (TAD), a viewpoint-robust 3DSGG framework that decouples relation reasoning according to predicate transformation behavior and is supported by viewpoint-stable object representations. TAD decomposes relation reasoning into two parts: one learns cues that should stay stable across viewpoints, while the other learns directional cues that should change with the observation frame. The two parts are merged for standard multi-label predicate prediction. Transformation-specific descriptors and group-aware auxiliary supervision encourage the two branches to capture complementary relation cues. Extensive experiments on 3DSSG show that TAD achieves state-of-the-art robustness under yaw viewpoint changes without training-time rotation augmentation, while maintaining competitive performance under the standard benchmark. The project page is available at https://tad-predicate.github.io/.