Deep-search agents are commonly trained via repeated interaction with real-world search APIs and browser environments. While realistic, this paradigm is expensive, difficult to reproduce, and sensitive to external drift. Existing simulator-based alternatives reduce dependence on live retrieval, but they largely inherit task distributions from pre-existing QA datasets, limiting their alignment with the behaviors required for deep search. We introduce SynSearch, a framework for training deep-search agents entirely within a synthetic search–browse environment. Our core idea is to jointly design the environment and the training-task distribution, enabling the synthesis of environment-aligned tasks and reinforcement learning of compact language models in multi-turn search settings. By grounding task validity in executable environment trajectories rather than surface-level plausibility alone, SynSearch unifies task generation, trajectory verification, and policy optimization within a low-marginal-cost and reproducible framework. Experiments on multi-hop QA and deep-search benchmarks show that SynSearch consistently improves both answer accuracy and search behavior, with especially large gains on deep-search tasks. Moreover, SynSearch offers low marginal cost, reproducibility, controllability, and strong performance under real-search evaluation, highlighting synthetic environments as an effective substrate for training deep-search agents.

Production multimodal systems must serve complex vision-language tasks under strict latency, memory, and cost constraints. Frontier multimodal large language models (MLLMs) deliver strong reasoning but are prohibitively expensive for online serving; compact alternatives fit deployment budgets but lack structured reasoning ability. We present OmniThoughtVis, a scalable distillation pipeline that converts open-source multimodal corpora into deployment-ready chain-of-thought (CoT) supervision for compact MLLMs. Starting from a diverse seed pool, the pipeline generates structured reasoning traces from a high-capacity teacher, jointly annotates reasoning difficulty, answer quality, and semantic task tags, and applies difficulty-aware filtering with tag-based diversity sampling to produce a reusable 1.8M-sample candidate pool. Practitioners construct budget-specific training subsets from this pool without re-running distillation. A key practical finding is that reasoning difficulty is a far more effective data selection signal than answer quality, which becomes uninformative when teacher outputs are already strong. Distilled Qwen3-VL models (2B-8B) consistently improve over undistilled baselines across nine benchmarks, with the distilled 4B model matching or exceeding the undistilled 8B on multiple tasks. In production, replacing a large-model serving pipeline with the distilled compact model reduces end-to-end response latency by 79% while maintaining comparable downstream quality.

Small LLMs often struggle to match the agentic capabilities of large, costly models. While reinforcement learning can help, progress has been limited by two structural bottlenecks: existing open-source agentic training data are narrow in task variety and easily solved; real-world APIs lack diversity and are unstable for large-scale reinforcement learning rollout processes. We address these challenges with SYNTHAGENT, a framework that jointly synthesizes diverse tool-use training data and simulates complete environments. Specifically, a strong teacher model creates novel tasks and tool ecosystems, then rewrites them into intentionally underspecified instructions. This compels agents to actively query users for missing details. When handling synthetic tasks, an LLM-based user simulator provides user-private information, while a mock tool system delivers stable tool responses. For rewards, task-level rubrics are constructed based on required subgoals, user-agent interactions, and forbidden behaviors. Across 14 challenging datasets in math, search, and tool use, models trained on our synthetic data achieve substantial gains, with small models showing performance comparable to some larger baselines in certain domains.

Modern industrial applications increasingly demand language models that act as agents, capable of multi-step reasoning and tool use in real-world settings. These tasks are typically performed under strict cost and latency constraints, making small agentic models highly desirable. In this paper, we introduce the AgenticQwen family of models, trained via multi-round reinforcement learning (RL) on synthetic data and a limited amount of open-source data. Our training framework combines reasoning RL and agentic RL with dual data flywheels that automatically generate increasingly challenging tasks. The reasoning flywheel increases task difficulty by learning from errors, while the agentic flywheel expands linear workflows into multi-branch behavior trees that better reflect the decision complexity of real-world applications. We validate AgenticQwen on public benchmarks and in an industrial agent system. The models achieve strong performance on multiple agentic benchmarks, and in our industrial agent system, close the gap with much larger models on search and data analysis tasks.

In Retrieval-Augmented Generation (RAG) and agent-based frameworks, the “Chain of Models” approach is widely used, where multiple specialized models work sequentially on distinct sub-tasks. This approach is effective but increases resource demands as each model must be deployed separately. Recent advancements attempt to address this by applying prompt tuning, which allows a shared base model to adapt to multiple tasks with minimal parameter changes. However, a key challenge remains: intermediate outputs, passed between models as plain text, require recomputation of hidden states (i.e., Key and Value (KV) states in Transformers) during inference. In this paper, we introduce FTHSS, a novel prompt-tuning method that enables models to share KV hidden states, eliminating redundant forward passes and reducing KV cache storage. By modifying input and attention masks during training, FTHSS allows models to effectively utilize KV hidden states from prior models in both single- and multi-round scenarios. Empirical results on four tasks show that FTHSS matches the performance of traditional model chains while improving inference efficiency.

Detecting self-contradictions within documents is a challenging task for ensuring textual coherence and reliability. While large language models (LLMs) have advanced in many natural language understanding tasks, document-level self-contradiction detection (DSCD) remains insufficiently studied. Recent approaches leveraging Chain-of-Thought (CoT) prompting aim to enhance reasoning and interpretability; however, they only gain marginal improvement and often introduce inconsistencies across repeated responses. We observe that such inconsistency arises from incomplete reasoning chains that fail to include all relevant contradictory sentences consistently. To address this, we propose a two-stage method that combines supervised fine-tuning (SFT) and reinforcement learning (RL) to enhance DSCD performance. In the SFT phase, a teacher model helps the model learn reasoning patterns, while RL further refines its reasoning ability. Our method incorporates a task-specific reward function to expand the model’s reasoning scope, boosting both accuracy and consistency. On the ContraDoc benchmark, our approach significantly boosts Llama 3.1-8B-Instruct’s accuracy from 38.5% to 51.1%, and consistency from 59.6% to76.2%.

Despite the significant progress of large language models (LLMs) in various tasks, they often produce factual errors due to their limited internal knowledge. Retrieval-Augmented Generation (RAG), which enhances LLMs with external knowledge sources, offers a promising solution. However, these methods can be misled by irrelevant paragraphs in retrieved documents. Due to the inherent uncertainty in LLM generation, inputting the entire document may introduce off-topic information, causing the model to deviate from the central topic and affecting the relevance of the generated content. To address these issues, we propose the Retrieve-Plan-Generation (RPG) framework. RPG generates plan tokens to guide subsequent generation in the plan stage. In the answer stage, the model selects relevant fine-grained paragraphs based on the plan and uses them for further answer generation. This plan-answer process is repeated iteratively until completion, enhancing generation relevance by focusing on specific topics. To implement this framework efficiently, we utilize a simple but effective multi-task prompt-tuning method, enabling the existing LLMs to handle both planning and answering. We comprehensively compare RPG with baselines across 5 knowledge-intensive generation tasks, demonstrating the effectiveness of our approach.