Self-Evolving Embodied Agents via Skill-Harness Evolution

Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces, and execution harness surrounding the model. While supervised fine-tuning and reinforcement learning can adapt agents to new environments, they require additional data, rewards, and training runs; meanwhile, many train-free code-centric approaches rely on programmable robot APIs that may be unavailable in fixed-interface settings. We propose SHAPER, a self-evolving framework for train-free embodied adaptation that keeps model parameters frozen and improves the non-parametric agent system by evolving reusable skills and a context-code harness through target-environment rollouts. In SHAPER, the same frozen model can serve as both planner and optimizer, refining its external skills and context-code harness without parameter updates. We evaluate SHAPER on VLABench and ESI-Bench, covering embodied agents with different low-level action interfaces, and compare against pure execution, supervised fine-tuning, and test-time-scaling baselines such as verifier-free selection and voting. Our results suggest that skill-and-harness optimization is a practical route to self-evolving embodied agents when model training is expensive, unavailable, or undesirable.

From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization

The optimization of long-horizon agents increasingly relies on reflection-based mechanisms, where a large language model (LLM) acts as an optimizer to diagnose agent failures and improve agent policies. However, real execution traces are difficult to use directly for optimization: large trace collections are often redundant and heterogeneous, making optimization inefficient and prone to overfitting to low-value failures; meanwhile, each individual trajectory also contains many irrelevant steps, while naive context reduction methods such as truncation or sliding windows can discard causally important evidence and produce misleading optimization signals. To resolve this dilemma, we introduce STRACE (Structural TRajectory Analysis and Causal Extraction), a framework that constructs high signal-noise optimization contexts for more precise and effective optimization. At the batch level, STRACE mines failure patterns to filter redundant traces and retain representative failures; within each selected trace, it performs causal localization over a textual dependency graph to remove non-causal steps and identify the true root-cause module for optimization. Empirical results demonstrate that STRACE significantly outperforms standard context-filtering baselines. Notably, on a challenging formal verification task (VeruSAGE-Bench), it successfully optimizes human-expert designed agents, delivering $1.4\times$ success-rate improvement (42.5% to 58.5%). The code is available at https://github.com/moomight/STRACE .

TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought

Background: Retrieval augmented generation (RAG) technology can empower large language models (LLMs) to generate more accurate, professional, and timely responses without fine tuning. However, due to the complex reasoning processes and substantial individual differences involved in traditional Chinese medicine (TCM) clinical diagnosis and treatment, traditional RAG methods often exhibit poor performance in this domain. Objective: To address the limitations of conventional RAG approaches in TCM applications, this study aims to develop an improved RAG framework tailored to the characteristics of TCM reasoning. Methods: We developed TCM-DiffRAG, an innovative RAG framework that integrates knowledge graphs (KG) with chains of thought (CoT). TCM-DiffRAG was evaluated on three distinctive TCM test datasets. Results: The experimental results demonstrated that TCM-DiffRAG achieved significant performance improvements over native LLMs. For example, the qwen-plus model achieved scores of 0.927, 0.361, and 0.038, which were significantly enhanced to 0.952, 0.788, and 0.356 with TCM-DiffRAG. The improvements were even more pronounced for non-Chinese LLMs. Additionally, TCM-DiffRAG outperformed directly supervised fine-tuned (SFT) LLMs and other benchmark RAG methods. Conclusions: TCM-DiffRAG shows that integrating structured TCM knowledge graphs with Chain of Thought based reasoning substantially improves performance in individualized diagnostic tasks. The joint use of universal and personalized knowledge graphs enables effective alignment between general knowledge and clinical reasoning. These results highlight the potential of reasoning-aware RAG frameworks for advancing LLM applications in traditional Chinese medicine.

Multi-view Normal and Distance Guidance Gaussian Splatting for Surface Reconstruction

3D Gaussian Splatting (3DGS) achieves remarkable results in the field of surface reconstruction. However, when Gaussian normal vectors are aligned within the single-view projection plane, while the geometry appears reasonable in the current view, biases may emerge upon switching to nearby views. To address the distance and global matching challenges in multi-view scenes, we design multi-view normal and distance-guided Gaussian splatting. This method achieves geometric depth unification and high-accuracy reconstruction by constraining nearby depth maps and aligning 3D normals. Specifically, for the reconstruction of small indoor and outdoor scenes, we propose a multi-view distance reprojection regularization module that achieves multi-view Gaussian alignment by computing the distance loss between two nearby views and the same Gaussian surface. Additionally, we develop a multi-view normal enhancement module, which ensures consistency across views by matching the normals of pixel points in nearby views and calculating the loss. Extensive experimental results demonstrate that our method outperforms the baseline in both quantitative and qualitative evaluations, significantly enhancing the surface reconstruction capability of 3DGS. Our code will be made publicly available at (https://github.com/Bistu3DV/MND-GS/).

DP2FL: Dual Prompt Personalized Federated Learning in Foundation Models

Personalized federated learning (PFL) has garnered significant attention for its ability to address heterogeneous client data distributions while preserving data privacy. However, when local client data is limited, deep learning models often suffer from insufficient training, leading to suboptimal performance. Foundation models, such as CLIP (Contrastive Language-Image Pretraining), exhibit strong feature extraction capabilities and can alleviate this issue by fine-tuning on limited local data. Despite their potential, foundation models are rarely utilized in federated learning scenarios, and challenges related to integrating new clients remain largely unresolved. To address these challenges, we propose the Dual Prompt Personalized Federated Learning (DP2FL) framework, which introduces dual prompts and an adaptive aggregation strategy. DP2FL combines global task awareness with local data-driven insights, enabling local models to achieve effective generalization while remaining adaptable to specific data distributions. Moreover, DP2FL introduces a global model that enables prediction on new data sources and seamlessly integrates newly added clients without requiring retraining. Experimental results in highly heterogeneous environments validate the effectiveness of DP2FL's prompt design and aggregation strategy, underscoring the advantages of prediction on novel data sources and demonstrating the seamless integration of new clients into the federated learning framework.

Improving TCM Question Answering through Tree-Organized Self-Reflective Retrieval with LLMs

Objectives: Large language models (LLMs) can harness medical knowledge for intelligent question answering (Q&A), promising support for auxiliary diagnosis and medical talent cultivation. However, there is a deficiency of highly efficient retrieval-augmented generation (RAG) frameworks within the domain of Traditional Chinese Medicine (TCM). Our purpose is to observe the effect of the Tree-Organized Self-Reflective Retrieval (TOSRR) framework on LLMs in TCM Q&A tasks. Materials and Methods: We introduce the novel approach of knowledge organization, constructing a tree structure knowledge base with hierarchy. At inference time, our self-reflection framework retrieves from this knowledge base, integrating information across chapters. Questions from the TCM Medical Licensing Examination (MLE) and the college Classics Course Exam (CCE) were randomly selected as benchmark datasets. Results: By coupling with GPT-4, the framework can improve the best performance on the TCM MLE benchmark by 19.85% in absolute accuracy, and improve recall accuracy from 27% to 38% on CCE datasets. In manual evaluation, the framework improves a total of 18.52 points across dimensions of safety, consistency, explainability, compliance, and coherence. Conclusion: The TOSRR framework can effectively improve LLM's capability in Q&A tasks of TCM.

Hybrid bundle-adjusting 3D Gaussians for view consistent rendering with pose optimization

Novel view synthesis has made significant progress in the field of 3D computer vision. However, the rendering of view-consistent novel views from imperfect camera poses remains challenging. In this paper, we introduce a hybrid bundle-adjusting 3D Gaussians model that enables view-consistent rendering with pose optimization. This model jointly extract image-based and neural 3D representations to simultaneously generate view-consistent images and camera poses within forward-facing scenes. The effective of our model is demonstrated through extensive experiments conducted on both real and synthetic datasets. These experiments clearly illustrate that our model can effectively optimize neural scene representations while simultaneously resolving significant camera pose misalignments. The source code is available at https://github.com/Bistu3DV/hybridBA.