Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents

LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon interactive tasks. Existing skill libraries are typically treated as model-agnostic, reusing the same skill formulations across backbones with substantially different capacities and behaviors. However, our controlled experiments across multiple model scales show that skill effectiveness is strongly model-dependent: a skill that benefits one backbone can harm another. Motivated by this observation, we propose MASA Model-Aware Skill Alignment, a framework that adapts skills to each target backbone without modifying agent weights. MASA operates in two stages: (1) a hierarchical skill evolution pipeline that iteratively rewrites general and task-specific skills using hill climbing and UCB-driven tree search, guided by environment feedback and model capability profiles; and (2) a lightweight model-conditioned skill rewriter trained on evolution trajectories to reproduce the adaptation in a single forward pass. Experiments across three interactive environments and four backbones show that MASA consistently achieves the best overall performance, with gains of up to 25.8 points over the strongest baseline. The learned rewriter further generalizes to unseen tasks and environments without additional search, consistently outperforming a much larger teacher LLM at a fraction of the inference cost.

DELOS: Detecting Shallow Transits in Kepler Photometry Using a Contrastive-Learning Framework

We present DEtection in phase-folded Light curves with cOntrastive Scoring (DELOS), a contrastive-learning-based framework designed to search for shallow transits in Kepler photometry. DELOS combines GPU-accelerated phase folding, optimized phase binning, and a custom one-dimensional convolutional encoder to assign a transit-likeness score to each folded light curve, thereby producing a score periodogram over trial periods without relying on pre-detected threshold-crossing events. Focusing on intermediate-to-long-period signals with orbital periods of 100-150 days, DELOS was trained on 20 million synthetic light curves generated with realistic transit models and Kepler-like noise properties, achieving a validation accuracy of 99.3 percent on the synthetic validation set. In controlled injection-recovery experiments, DELOS improves the combined precision-recall performance by 15.5 percent relative to Box-fitting Least Squares (BLS) and 11.25 percent relative to Transit Least Squares (TLS) in the low Signal-to-Noise Ratios (low-SNR) regime. It also accelerates the search by factors of approximately 3-5 and 74-80 compared with BLS and TLS, respectively. Applied to a selected Kepler validation sample, DELOS recovered all known shallow intermediate-to-long-period transit signals in the tested period range. These results demonstrate that DELOS provides an efficient and sensitive framework for low-SNR transit searches and represents a practical step toward future searches for longer-period terrestrial planets in Kepler, K2, TESS, PLATO, and Earth 2.0 data. Accordingly, this work is intended as a methodological development and validation study, with the detailed astrophysical validation of newly identified candidates deferred to future work.

Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning

Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divided into general skills for broad cognitive transfer and task-specific skills for dynamic execution. However, existing skill-based reinforcement learning (RL) methods typically force a rigid choice between full externalization, which incurs prohibitive context overhead, and full internalization, which risks overfitting and knowledge conflicts. To address this dilemma, we propose Skill0.5, a novel agentic RL framework that explicitly differentiates skill treatments by combining general skill internalization with task-specific skill utilization. Driven by a dynamic, difficulty-aware router, Skill0.5 streams tasks into distinct mastery tiers to apply tailored optimization strategies: it internalizes general skills via privileged distillation to build a cognitive foundation for hard tasks, while using diagnostic probing on easy tasks to penalize shortcuts and enforce specific skill utilization. Experiments on ALFWorld and WebShop demonstrate that Skill0.5 outperforms both memory-based and skill-based RL baselines, yielding performance improvements across both in-distribution and out-of-distribution scenarios.

CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives

Autoregressive video generation aims at real-time, open-ended synthesis. Yet, cinematic storytelling is not merely the endless extension of a single scene; it requires progressing through evolving events, viewpoint shifts, and discrete shot boundaries. Existing autoregressive models often struggle in this setting. Trained primarily for short-horizon continuation, they treat long sequences as extended single shots, inevitably suffering from motion stagnation and semantic drift during long rollouts. To bridge this gap, we introduce CausalCine, an interactive autoregressive framework that transforms multi-shot video generation into an online directing process. CausalCine generates causally across shot changes, accepts dynamic prompts on the fly, and reuses context without regenerating previous shots. To achieve this, we first train a causal base model on native multi-shot sequences to learn complex shot transitions prior to acceleration. We then propose Content-Aware Memory Routing (CAMR), which dynamically retrieves historical KV entries according to attention-based relevance scores rather than temporal proximity, preserving cross-shot coherence under bounded active memory. Finally, we distill the causal base model into a few-step generator for real-time interactive generation. Extensive experiments demonstrate that CausalCine significantly outperforms autoregressive baselines and approaches the capability of bidirectional models while unlocking the streaming interactivity of causal generation. Demo available at https://yihao-meng.github.io/CausalCine/

Advancing Open-source World Models

We present LingBot-World, an open-sourced world simulator stemming from video generation. Positioned as a top-tier world model, LingBot-World offers the following features. (1) It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts, cartoon styles, and beyond. (2) It enables a minute-level horizon while preserving contextual consistency over time, which is also known as "long-term memory". (3) It supports real-time interactivity, achieving a latency of under 1 second when producing 16 frames per second. We provide public access to the code and model in an effort to narrow the divide between open-source and closed-source technologies. We believe our release will empower the community with practical applications across areas like content creation, gaming, and robot learning.

LongCat-Flash-Thinking-2601 Technical Report

We introduce LongCat-Flash-Thinking-2601, a 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability. LongCat-Flash-Thinking-2601 achieves state-of-the-art performance among open-source models on a wide range of agentic benchmarks, including agentic search, agentic tool use, and tool-integrated reasoning. Beyond benchmark performance, the model demonstrates strong generalization to complex tool interactions and robust behavior under noisy real-world environments. Its advanced capability stems from a unified training framework that combines domain-parallel expert training with subsequent fusion, together with an end-to-end co-design of data construction, environments, algorithms, and infrastructure spanning from pre-training to post-training. In particular, the model's strong generalization capability in complex tool-use are driven by our in-depth exploration of environment scaling and principled task construction. To optimize long-tailed, skewed generation and multi-turn agentic interactions, and to enable stable training across over 10,000 environments spanning more than 20 domains, we systematically extend our asynchronous reinforcement learning framework, DORA, for stable and efficient large-scale multi-environment training. Furthermore, recognizing that real-world tasks are inherently noisy, we conduct a systematic analysis and decomposition of real-world noise patterns, and design targeted training procedures to explicitly incorporate such imperfections into the training process, resulting in improved robustness for real-world applications. To further enhance performance on complex reasoning tasks, we introduce a Heavy Thinking mode that enables effective test-time scaling by jointly expanding reasoning depth and width through intensive parallel thinking.

HCFT: Hierarchical Convolutional Fusion Transformer for EEG Decoding

Electroencephalography (EEG) decoding requires models that can effectively extract and integrate complex temporal, spectral, and spatial features from multichannel signals. To address this challenge, we propose a lightweight and generalizable decoding framework named Hierarchical Convolutional Fusion Transformer (HCFT), which combines dual-branch convolutional encoders and hierarchical Transformer blocks for multi-scale EEG representation learning. Specifically, the model first captures local temporal and spatiotemporal dynamics through time-domain and time-space convolutional branches, and then aligns these features via a cross-attention mechanism that enables interaction between branches at each stage. Subsequently, a hierarchical Transformer fusion structure is employed to encode global dependencies across all feature stages, while a customized Dynamic Tanh normalization module is introduced to replace traditional Layer Normalization in order to enhance training stability and reduce redundancy. Extensive experiments are conducted on two representative benchmark datasets, BCI Competition IV-2b and CHB-MIT, covering both event-related cross-subject classification and continuous seizure prediction tasks. Results show that HCFT achieves 80.83% average accuracy and a Cohen's kappa of 0.6165 on BCI IV-2b, as well as 99.10% sensitivity, 0.0236 false positives per hour, and 98.82% specificity on CHB-MIT, consistently outperforming over ten state-of-the-art baseline methods. Ablation studies confirm that each core component of the proposed framework contributes significantly to the overall decoding performance, demonstrating HCFT's effectiveness in capturing EEG dynamics and its potential for real-world BCI applications.

GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence

Retrieval-Augmented Generation (RAG) integrates external knowledge to enhance Large Language Models (LLMs), yet systems remain susceptible to two critical flaws: providing correct answers without explicit grounded evidence and producing fabricated responses when the retrieved context is insufficient. While prior research has addressed these issues independently, a unified framework that integrates evidence-based grounding and reliable abstention is currently lacking. In this paper, we propose GRACE, a reinforcement-learning framework that simultaneously mitigates both types of flaws. GRACE employs a data construction method that utilizes heterogeneous retrievers to generate diverse training samples without manual annotation. A multi-stage gated reward function is then employed to train the model to assess evidence sufficiency, extract key supporting evidence, and provide answers or explicitly abstain. Experimental results on two benchmarks demonstrate that GRACE achieves state-of-the-art overall accuracy and strikes a favorable balance between accurate response and rejection, while requiring only 10% of the annotation costs of prior methods. Our code is available at https://github.com/YiboZhao624/Grace..

UCD: Unconditional Discriminator Promotes Nash Equilibrium in GANs

Adversarial training turns out to be the key to one-step generation, especially for Generative Adversarial Network (GAN) and diffusion model distillation. Yet in practice, GAN training hardly converges properly and struggles in mode collapse. In this work, we quantitatively analyze the extent of Nash equilibrium in GAN training, and conclude that redundant shortcuts by inputting condition in $D$ disables meaningful knowledge extraction. We thereby propose to employ an unconditional discriminator (UCD), in which $D$ is enforced to extract more comprehensive and robust features with no condition injection. In this way, $D$ is able to leverage better knowledge to supervise $G$, which promotes Nash equilibrium in GAN literature. Theoretical guarantee on compatibility with vanilla GAN theory indicates that UCD can be implemented in a plug-in manner. Extensive experiments confirm the significant performance improvements with high efficiency. For instance, we achieved \textbf{1.47 FID} on the ImageNet-64 dataset, surpassing StyleGAN-XL and several state-of-the-art one-step diffusion models. The code will be made publicly available.

E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness

Graph-based RAG methods like GraphRAG have shown promising global understanding of the knowledge base by constructing hierarchical entity graphs. However, they often suffer from inefficiency and rely on manually pre-defined query modes, limiting practical use. In this paper, we propose E^2GraphRAG, a streamlined graph-based RAG framework that improves both Efficiency and Effectiveness. During the indexing stage, E^2GraphRAG constructs a summary tree with large language models and an entity graph with SpaCy based on document chunks. We then construct bidirectional indexes between entities and chunks to capture their many-to-many relationships, enabling fast lookup during both local and global retrieval. For the retrieval stage, we design an adaptive retrieval strategy that leverages the graph structure to retrieve and select between local and global modes. Experiments show that E^2GraphRAG achieves up to 10 times faster indexing than GraphRAG and 100 times speedup over LightRAG in retrieval while maintaining competitive QA performance.