Training Skills Like Parameters via Self-Supervised Semantic Diffusion

While Large Language Models (LLMs) demonstrate remarkable general instruction-following capabilities, they often fall short of human experts in highly specialized, open-ended domains such as creative screenwriting. Prior approaches typically adopt post-training, yet both supervised fine-tuning and reinforcement learning require weight access that closed-source frontier models do not offer, and demand heavy compute. Moreover, what is learned is tied to a single checkpoint and cannot be inspected by humans. Recent advancements in agentic continual learning instead attempt to bridge this gap by accumulating external textual skills. However, these methods heavily rely on costly human expert annotations or unreliable LLM-as-a-judge feedback for reflection. To overcome this bottleneck, we propose a novel, unsupervised self-evolving agent framework inspired by the corruption-and-reconstruction paradigm of diffusion models. Instead of relying on explicit external scoring, we leverage existing high-quality human artifacts to construct self-supervised signals. Training then follows the familiar loop of neural network training, forward, loss, and backward, with the loss coming from contrasting the agent's reconstruction against the human original. What is updated is not model weights but an external library of textual skills. We evaluate our framework on the challenging task of short drama screenwriting. Experimental results demonstrate that our method enables the agent to autonomously extract and internalize highly generalizable skills, significantly enhancing its domain-specific generation capabilities. Furthermore, this self-contrastive reflection paradigm offers a scalable pathway for agents to teach themselves the production of complex, high-quality human artifacts, without requiring external supervision.

LLM-Based Generative Retrieval for Snapchat Content Recommendation

Pretrained large language models (LLMs) are promising retrieval engines because they combine rich semantic priors, strong sequence modeling capabilities, and favorable scaling behavior. However, turning a pretrained LLM into a generative retriever in production deployment raises several challenges: the model must learn an internal item vocabulary that was absent from pretraining, and generate valid item identifiers under strict latency and cost constraints. We address these challenges through the design and launch of SnapLGR, an LLM-based generative retrieval system for short-video recommendation at Snapchat. The system is built around three main designs. First, we construct semantic identifiers (SIDs) from multimodal item embeddings and enhance them with Personalized PageRank (PPR)-based co-engagement contrastive learning, resulting in improved codebook utilization, reduced collisions, and infused collaborative signal. Second, we use continued pretraining (CPT) to ground the introduced SID tokens before supervised fine-tuning (SFT) on user interaction sequences. Third, we make SnapLGR serving practical through TensorRT-LLM CUDA-backed beam search and a decentralized worker-loop architecture. In a live A/B test, the launched system increased View Time by 0.37%, Time Spent by 0.09%, Deep Sessions by 0.18%, and Deep Sessions Unique User by 0.11% relative to the existing TIGER-style generative retrieval baseline. We then decompose this offline gap under a fixed tokenizer and quantify the gains due to model architecture, scaling, and pretraining. Overall, our deployment shows that successful production SnapLGR requires joint design across representation learning, vocabulary grounding, and efficient training and serving.

MemTX: Transactional Belief Commit for Stateful Agent Memory

LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with real side effects. Current agent memory systems treat every accepted write as immediately actionable truth, so a polluted tool result, a stale update, or a teammate's half-finished note can silently drive an irreversible action. We argue that a memory write is not a belief commit. We present MemTX, a transactional belief-commit protocol. Each record carries evidence, permissions, provenance, and validity. Writes are staged inside snapshot-isolated transactions and admitted by a validate-and-commit pipeline, irreversible tool calls are gated on in-flight belief state, and retracting a belief triggers typed cascading repair of its derived records and tool side effects. Two invariants, action-safety gating and cascade-repair completeness, are machine-checked by property-based testing and bounded exhaustive enumeration of 5.5 million protocol states, with zero violations. Across five backbones from three model families, MemTX leads all eight baselines with paired-McNemar significance on four backbones and statistically ties the best baseline on the fifth and strongest, while remaining the only method with zero downstream harm on every backbone. Backbone capability does not substitute for commit discipline.

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly fragmented and tightly coupled, hindering reproducibility and causing redundant engineering. To address this, we introduce AgentCompass, an open-source, lightweight, and extensible infrastructure for evaluating LLM-based agents. AgentCompass organizes the evaluation process around three independent components, namely Benchmark, Harness, and Environment, thereby enabling flexible configurations without requiring the reimplementation of complex execution logic. Furthermore, it features a fault-tolerant asynchronous runtime and comprehensive trajectory analysis tools to transparently diagnose nuanced failure modes like reward-hacking. Natively supporting over 20 benchmarks across five capability dimensions, AgentCompass provides the community with a scalable and reproducible infrastructure for advancing agent research.

GatedLinear: Adaptive Routing of Complementary Linear Bases for Time Series Forecasting

Time series forecasting requires models to capture diverse, often mutually exclusive, temporal dynamics, from smooth trend continuation to nonstationary drift and strict phase-aligned recurrence. While recent deep learning models have improved accuracy, they typically force these diverse patterns through a single computational backbone governed by fixed algorithmic inductive biases (e.g., self-attention or spectral filtering). This single-mechanism approach often struggles with the profound heterogeneity of real-world series, where different variables and forecast horizons necessitate fundamentally different predictive treatments. To address this, we propose GatedLinear: a lightweight framework that frames forecasting as the adaptive routing of complementary linear bases. GatedLinear leverages a pool of three specialized mechanisms: a global trend-seasonal basis for smooth projection, a difference-based incremental basis for nonstationary drift, and a phase-aligned recurrence basis for explicit cyclic reuse. To dynamically orchestrate these distinct behaviors, we introduce a Tri-Factorized Fusion Gate that disentangles routing decisions into channel-specific preferences, horizon-aware offsets, and phase-indexed biases derived from known future time marks. This design allows the model to perform highly granular, point-wise soft routing across different predictive regimes without stacking computationally heavy neural modules. Experiments on standard benchmarks show that our method achieves state-of-the-art or highly competitive accuracy against recent complex foundational models, while offering explicitly interpretable routing patterns and operating with a substantially smaller parameter footprint.

OpenCompass: A Universal Evaluation Platform for Large Language Models

In recent years, the field of artificial intelligence has undergone a paradigm shift from task-specific small-scale models to general-purpose large language models (LLMs). With the rapid iteration of LLMs, objective, quantitative, and comprehensive evaluation of their capabilities has become a critical link in advancing technological development. Currently, the mainstream static benchmark dataset-based evaluation methods face challenges such as the diversity of task types, inconsistent evaluation criteria, and fragmentation of data and processing workflows, making it difficult to efficiently conduct cross-domain and large-scale model evaluation. To address the aforementioned issues, this paper proposes and open-sources OpenCompass, a one-stop, scalable, and high-concurrency-supported general-purpose LLM evaluation platform. Adhering to the design philosophy of modularization and component decoupling, the platform boasts three core advantages: high compatibility, flexibility, and high concurrency. The core architecture of OpenCompass comprises five key components: the Configuration System, Task Partitioning Module, Execution and Scheduling Module, Task Execution Unit, and Result Visualization Module. Its workflow provides rule-based, LLM-as-a-Judge, and cascaded evaluators to adapt to the requirements of different task scenarios. Supporting mainstream benchmark datasets across multiple domains, including knowledge, reasoning, computation, science, language, code, etc., the platform offers a unified and efficient LLM evaluation tool for both academia and industry, facilitating the accurate identification of strengths and weaknesses of LLMs as well as their subsequent optimization.

Learning to Commit: Generating Organic Pull Requests via Online Repository Memory

Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject. The root cause is not functional incorrectness but a lack of organicity: generated code ignores project-specific conventions, duplicates functionality already provided by internal APIs, and violates implicit architectural constraints accumulated over years of development. Simply exposing an agent to the latest repository snapshot is not enough: the snapshot reveals the final state of the codebase, but not the repository-specific change patterns by which that state was reached. We introduce Learning to Commit, a framework that closes this gap through Online Repository Memory. Given a repository with a strict chronological split, the agent performs supervised contrastive reflection on earlier commits: it blindly attempts to resolve each historical issue, compares its prediction against the oracle diff, and distils the gap into a continuously growing set of skills-reusable patterns capturing coding style, internal API usage, and architectural invariants. When a new PR description arrives, the agent conditions its generation on these accumulated skills, producing changes grounded in the project's own evolution rather than generic pretraining priors. Evaluation is conducted on genuinely future, merged pull requests that could not have been seen during the skill-building phase, and spans multiple dimensions including functional correctness, code-style consistency, internal API reuse rate, and modified-region plausibility. Experiments on an expert-maintained repository with rich commit history show that Online Repository Memory effectively improves organicity scores on held-out future tasks.

Kimi K2.5: Visual Agentic Intelligence

We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that two modalities enhance each other. This includes a series of techniques such as joint text-vision pre-training, zero-vision SFT, and joint text-vision reinforcement learning. Building on this multimodal foundation, K2.5 introduces Agent Swarm, a self-directed parallel agent orchestration framework that dynamically decomposes complex tasks into heterogeneous sub-problems and executes them concurrently. Extensive evaluations show that Kimi K2.5 achieves state-of-the-art results across various domains including coding, vision, reasoning, and agentic tasks. Agent Swarm also reduces latency by up to $4.5\times$ over single-agent baselines. We release the post-trained Kimi K2.5 model checkpoint to facilitate future research and real-world applications of agentic intelligence.

AutoTour: Automatic Photo Tour Guide with Smartphones and LLMs

We present AutoTour, a system that enhances user exploration by automatically generating fine-grained landmark annotations and descriptive narratives for photos captured by users. The key idea of AutoTour is to fuse visual features extracted from photos with nearby geospatial features queried from open matching databases. Unlike existing tour applications that rely on pre-defined content or proprietary datasets, AutoTour leverages open and extensible data sources to provide scalable and context-aware photo-based guidance. To achieve this, we design a training-free pipeline that first extracts and filters relevant geospatial features around the user's GPS location. It then detects major landmarks in user photos through VLM-based feature detection and projects them into the horizontal spatial plane. A geometric matching algorithm aligns photo features with corresponding geospatial entities based on their estimated distance and direction. The matched features are subsequently grounded and annotated directly on the original photo, accompanied by large language model-generated textual and audio descriptions to provide an informative, tour-like experience. We demonstrate that AutoTour can deliver rich, interpretable annotations for both iconic and lesser-known landmarks, enabling a new form of interactive, context-aware exploration that bridges visual perception and geospatial understanding.

Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management

Large Language Models (LLMs) suffer from significant performance degradation when processing long contexts due to proactive interference, where irrelevant information in earlier parts of the context disrupts reasoning and memory recall. While most research focuses on external memory systems to augment LLMs' capabilities, we propose a complementary approach: empowering LLMs with Active Context Management (ACM) tools to actively sculpt their internal working memory. We introduce Sculptor, a framework that equips LLMs with three categories of tools: (1) context fragmentation, (2) summary, hide, and restore, and (3) intelligent search. Our approach enables LLMs to proactively manage their attention and working memory, analogous to how humans selectively focus on relevant information while filtering out distractions. Experimental evaluation on information-sparse benchmarks-PI-LLM (proactive interference) and NeedleBench Multi-Needle Reasoning-demonstrates that Sculptor significantly improves performance even without specific training, leveraging LLMs' inherent tool calling generalization capabilities. By enabling Active Context Management, Sculptor not only mitigates proactive interference but also provides a cognitive foundation for more reliable reasoning across diverse long-context tasks-highlighting that explicit context-control strategies, rather than merely larger token windows, are key to robustness at scale.