MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety

Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their \textbf{reliance on static, pre-collected data distributions}. In this paper, we introduce \textbf{MAGIC}, a novel multi-turn multi-agent reinforcement learning framework that formulates LLM safety alignment as an adversarial asymmetric game. Specifically, an attacker agent learns to iteratively rewrite original queries into deceptive prompts, while a defender agent simultaneously optimizes its policy to recognize and refuse such inputs. This dynamic process triggers a \textbf{co-evolution}, where the attacker's ever-changing strategies continuously uncover long-tail vulnerabilities, driving the defender to generalize to unseen attack patterns. Remarkably, we observe that the attacker, endowed with initial reasoning ability, evolves \textbf{novel, previously unseen combinatorial strategies} through iterative RL training, underscoring our method's substantial potential. Theoretically, we provide insights into a more robust game equilibrium and derive safety guarantees. Extensive experiments validate our framework's effectiveness, demonstrating superior defense success rates without compromising the helpfulness of the model. Our code is available at https://github.com/BattleWen/MAGIC.

KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning

Despite the impressive performance of large language models (LLMs) pretrained on vast knowledge corpora, advancing their knowledge manipulation-the ability to effectively recall, reason, and transfer relevant knowledge-remains challenging. Existing methods mainly leverage Supervised Fine-Tuning (SFT) on labeled datasets to enhance LLMs' knowledge manipulation ability. However, we observe that SFT models still exhibit the known&incorrect phenomenon, where they explicitly possess relevant knowledge for a given question but fail to leverage it for correct answers. To address this challenge, we propose KALE (Knowledge-Aware LEarning)-a post-training framework that leverages knowledge graphs (KGs) to generate high-quality rationales and enhance LLMs' knowledge manipulation ability. Specifically, KALE first introduces a Knowledge-Induced (KI) data synthesis method that efficiently extracts multi-hop reasoning paths from KGs to generate high-quality rationales for question-answer pairs. Then, KALE employs a Knowledge-Aware (KA) fine-tuning paradigm that enhances knowledge manipulation by internalizing rationale-guided reasoning through minimizing the KL divergence between predictions with and without rationales. Extensive experiments on eight popular benchmarks across six different LLMs demonstrate the effectiveness of KALE, achieving accuracy improvements of up to 11.72% and an average of 4.18%.

The Two-Stage Decision-Sampling Hypothesis: Understanding the Emergence of Self-Reflection in RL-Trained LLMs

Self-reflection capabilities emerge in Large Language Models after RL post-training, with multi-turn RL achieving substantial gains over SFT counterparts. Yet the mechanism of how a unified optimization objective gives rise to functionally distinct capabilities of generating solutions and evaluating when to revise them remains opaque. To address this question, we introduce the Gradient Attribution Property to characterize how reward gradients distribute across policy components, formalized through the Two-Stage Decision-Sampling (DS) Hypothesis, which decomposes the policy into sampling ($π_{sample}$) for generation and decision ($π_{d}$) for verification. We prove that surrogate rewards exhibit Balanced Gradient Attribution, while SFT and KL penalties exhibit Unbalanced Gradient Attribution, with length-weighting creating asymmetric regularization that constrains $π_{sample}$ while leaving $π_{d}$ under-optimized, providing an theoretical explanation of why RL succeeds where SFT fails. We also empirically validate our theoretical predictions on arithmetic reasoning demonstrates that RL's superior generalization stems primarily from improved decision-making ($π_{d}$) rather than sampling capabilities, providing a first-principles mechanistic explanation for self-correction in thinking models.

The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models

Reinforcement learning (RL) plays a crucial role in shaping the behavior of large language and reasoning models (LLMs/LRMs). However, it often produces brittle and unstable policies, leading to critical failures such as spurious reasoning, deceptive alignment, and instruction disobedience that undermine the trustworthiness and safety of LLMs/LRMs. Currently, these issues lack a unified theoretical explanation and are typically addressed using ad-hoc heuristics. This paper presents a rigorous mathematical framework for analyzing the stability of the mapping from a reward function to the optimal policy. We show that policy brittleness often stems from non-unique optimal actions, a common occurrence when multiple valid traces exist in a reasoning task. This theoretical lens provides a unified explanation for a range of seemingly disparate failures, reframing them as rational outcomes of optimizing rewards that may be incomplete or noisy, especially in the presence of action degeneracy. We extend this analysis from the fundamental single-reward setting to the more realistic multi-reward RL across diverse domains, showing how stability is governed by an "effective reward" aggregation mechanism. We also prove that entropy regularization restores policy stability at the cost of increased stochasticity. Our framework provides a unified explanation for recent empirical findings on deceptive reasoning, instruction-following trade-offs, and RLHF-induced sophistry, and is further validated through perturbation experiments in multi-reward RL. This work advances policy-stability analysis from empirical heuristics towards a principled theory, offering essential insights for designing safer and more trustworthy AI systems.

SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law

We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framework, which incorporates large-scale, progressive, safety-oriented reinforcement learning post-training, supported by a suite of multi-principled verifiers. Unlike previous alignment methods such as RLHF that simply learn human preferences, SafeLadder enables SafeWork-R1 to develop intrinsic safety reasoning and self-reflection abilities, giving rise to safety `aha' moments. Notably, SafeWork-R1 achieves an average improvement of $46.54\%$ over its base model Qwen2.5-VL-72B on safety-related benchmarks without compromising general capabilities, and delivers state-of-the-art safety performance compared to leading proprietary models such as GPT-4.1 and Claude Opus 4. To further bolster its reliability, we implement two distinct inference-time intervention methods and a deliberative search mechanism, enforcing step-level verification. Finally, we further develop SafeWork-R1-InternVL3-78B, SafeWork-R1-DeepSeek-70B, and SafeWork-R1-Qwen2.5VL-7B. All resulting models demonstrate that safety and capability can co-evolve synergistically, highlighting the generalizability of our framework in building robust, reliable, and trustworthy general-purpose AI.

DeepInnovation AI: A Global Dataset Mapping the AI innovation from Academic Research to Industrial Patents

In the rapidly evolving field of artificial intelligence (AI), mapping innovation patterns and understanding effective technology transfer from research to applications are essential for economic growth. However, existing data infrastructures suffer from fragmentation, incomplete coverage, and insufficient evaluative capacity. Here, we present DeepInnovationAI, a comprehensive global dataset containing three structured files. DeepPatentAI.csv: Contains 2,356,204 patent records with 8 field-specific attributes. DeepDiveAI.csv: Encompasses 3,511,929 academic publications with 13 metadata fields. These two datasets leverage large language models, multilingual text analysis and dual-layer BERT classifiers to accurately identify AI-related content, while utilizing hypergraph analysis to create robust innovation metrics. Additionally, DeepCosineAI.csv: By applying semantic vector proximity analysis, this file presents approximately one hundred million calculated paper-patent similarity pairs to enhance understanding of how theoretical advancements translate into commercial technologies. DeepInnovationAI enables researchers, policymakers, and industry leaders to anticipate trends and identify collaboration opportunities. With extensive temporal and geographical scope, it supports detailed analysis of technological development patterns and international competition dynamics, establishing a foundation for modeling AI innovation and technology transfer processes.

Optimal Trade and Industrial Policies in the Global Economy: A Deep Learning Framework

We propose a deep learning framework, DL-opt, designed to efficiently solve for optimal policies in quantifiable general equilibrium trade models. DL-opt integrates (i) a nested fixed point (NFXP) formulation of the optimization problem, (ii) automatic implicit differentiation to enhance gradient descent for solving unilateral optimal policies, and (iii) a best-response dynamics approach for finding Nash equilibria. Utilizing DL-opt, we solve for non-cooperative tariffs and industrial subsidies across 7 economies and 44 sectors, incorporating sectoral external economies of scale. Our quantitative analysis reveals significant sectoral heterogeneity in Nash policies: Nash industrial subsidies increase with scale elasticities, whereas Nash tariffs decrease with trade elasticities. Moreover, we show that global dual competition, involving both tariffs and industrial subsidies, results in lower tariffs and higher welfare outcomes compared to a global tariff war. These findings highlight the importance of considering sectoral heterogeneity and policy combinations in understanding global economic competition.

Relating the Seemingly Unrelated: Principled Understanding of Generalization for Generative Models in Arithmetic Reasoning Tasks

Large language models (LLMs) have demonstrated impressive versatility across numerous tasks, yet their generalization capabilities remain poorly understood. To investigate these behaviors, arithmetic tasks serve as important venues. In previous studies, seemingly unrelated mysteries still exist -- (1) models with appropriate positional embeddings can correctly perform longer unseen arithmetic operations such as addition, but their effectiveness varies in more complex tasks like multiplication; (2) models perform well for longer unseen cases in modular addition under specific moduli (e.g., modulo 100) but struggle under very close moduli (e.g., modulo 101), regardless of the positional encoding used. We believe previous studies have been treating the symptoms rather than addressing the root cause -- they have paid excessive attention to improving model components, while overlooking the differences in task properties that may be the real drivers. This is confirmed by our unified theoretical framework for different arithmetic scenarios. For example, unlike multiplication, the digital addition task has the property of translation invariance which naturally aligns with the relative positional encoding, and this combination leads to successful generalization of addition to unseen longer domains. The discrepancy in operations modulo 100 and 101 arises from the base. Modulo 100, unlike 101, is compatible with the decimal system (base 10), such that unseen information in digits beyond the units digit and the tens digit is actually not needed for the task. Extensive experiments with GPT-like models validate our theoretical predictions. These findings deepen our understanding of the generalization mechanisms, and facilitate more data-efficient model training and objective-oriented AI alignment.

Machine Learning for Economic Forecasting: An Application to China's GDP Growth

This paper aims to explore the application of machine learning in forecasting Chinese macroeconomic variables. Specifically, it employs various machine learning models to predict the quarterly real GDP growth of China, and analyzes the factors contributing to the performance differences among these models. Our findings indicate that the average forecast errors of machine learning models are generally lower than those of traditional econometric models or expert forecasts, particularly in periods of economic stability. However, during certain inflection points, although machine learning models still outperform traditional econometric models, expert forecasts may exhibit greater accuracy in some instances due to experts' more comprehensive understanding of the macroeconomic environment and real-time economic variables. In addition to macroeconomic forecasting, this paper employs interpretable machine learning methods to identify the key attributive variables from different machine learning models, aiming to enhance the understanding and evaluation of their contributions to macroeconomic fluctuations.

Large Language Models at Work in China's Labor Market

This paper explores the potential impacts of large language models (LLMs) on the Chinese labor market. We analyze occupational exposure to LLM capabilities by incorporating human expertise and LLM classifications, following Eloundou et al. (2023)'s methodology. We then aggregate occupation exposure to the industry level to obtain industry exposure scores. The results indicate a positive correlation between occupation exposure and wage levels/experience premiums, suggesting higher-paying and experience-intensive jobs may face greater displacement risks from LLM-powered software. The industry exposure scores align with expert assessments and economic intuitions. We also develop an economic growth model incorporating industry exposure to quantify the productivity-employment trade-off from AI adoption. Overall, this study provides an analytical basis for understanding the labor market impacts of increasingly capable AI systems in China. Key innovations include the occupation-level exposure analysis, industry aggregation approach, and economic modeling incorporating AI adoption and labor market effects. The findings will inform policymakers and businesses on strategies for maximizing the benefits of AI while mitigating adverse disruption risks.