We develop a physics-informed neural network (PINN) framework for parameter estimation in fractional-order SEIRD epidemic models. By embedding the Caputo fractional derivative into the network residuals via the L1 discretization scheme, our method simultaneously reconstructs epidemic trajectories and infers both epidemiological parameters and the fractional memory order $α$. The fractional formulation extends classical integer-order models by capturing long-range memory effects in disease progression, incubation, and recovery. Our framework learns the fractional memory order $α$ as a trainable parameter while simultaneously estimating the epidemiological rates $(β, σ, γ, μ)$. A composite loss combining data misfit, physics residuals, and initial conditions, with constraints on positivity and population conservation, ensures both accuracy and biological consistency. Tests on synthetic Mpox data confirm reliable recovery of $α$ and parameters under noise, while applications to COVID-19 show that optimal $α\in (0, 1]$ captures memory effects and improves predictive performance over the classical SEIRD model. This work establishes PINNs as a robust tool for learning memory effects in epidemic dynamics, with implications for forecasting, control strategies, and the analysis of non-Markovian epidemic processes.

Recent reinforcement learning (RL) methods have substantially enhanced the planning capabilities of Large Language Models (LLMs), yet the theoretical basis for their effectiveness remains elusive. In this work, we investigate RL's benefits and limitations through a tractable graph-based abstraction, focusing on policy gradient (PG) and Q-learning methods. Our theoretical analyses reveal that supervised fine-tuning (SFT) may introduce co-occurrence-based spurious solutions, whereas RL achieves correct planning primarily through exploration, underscoring exploration's role in enabling better generalization. However, we also show that PG suffers from diversity collapse, where output diversity decreases during training and persists even after perfect accuracy is attained. By contrast, Q-learning provides two key advantages: off-policy learning and diversity preservation at convergence. We further demonstrate that careful reward design is necessary to prevent reward hacking in Q-learning. Finally, applying our framework to the real-world planning benchmark Blocksworld, we confirm that these behaviors manifest in practice. Planning is a fundamental cognitive construct that underpins human intelligence, shaping our ability to organize tasks, coordinate activities, and formulate complex solutions such as mathematical proofs. It enables humans to decompose complex goals into manageable steps, anticipate potential challenges, and maintain coherence during problem solving. Similarly, planning plays a pivotal role in state-of-the-art Large Language Models (LLMs), enhancing their ability to address structured and long-horizon tasks with greater accuracy and reliability. Early generations of LLMs primarily relied on next-token prediction and passive statistical learning, which limited their planning capabilities to short-horizon, reactive responses.

Deep neural networks (DNNs) have been widely applied to solve real-world regression problems. However, selecting optimal network structures remains a significant challenge. This study addresses this issue by linking neuron selection in DNNs to knot placement in basis expansion techniques. We introduce a difference penalty that automates knot selection, thereby simplifying the complexities of neuron selection. We name this method Deep P-Spline (DPS). This approach extends the class of models considered in conventional DNN modeling and forms the basis for a latent variable modeling framework using the Expectation-Conditional Maximization (ECM) algorithm for efficient network structure tuning with theoretical guarantees. From a nonparametric regression perspective, DPS is proven to overcome the curse of dimensionality, enabling the effective handling of datasets with a large number of input variable, a scenario where conventional nonparametric regression methods typically underperform. This capability motivates the application of the proposed methodology to computer experiments and image data analyses, where the associated regression problems involving numerous inputs are common. Numerical results validate the effectiveness of the model, underscoring its potential for advanced nonlinear regression tasks.

Transformer-based architectures traditionally employ softmax to compute attention weights, which produces dense distributions over all tokens in a sequence. While effective in many settings, this density has been shown to be detrimental for tasks that demand precise focus on fixed-size patterns: as sequence length increases, non-informative tokens accumulate attention probability mass, leading to dispersion and representational collapse. We show in this paper that dynamically sparse attention mechanisms using $α$-entmax can avoid these issues, due to their ability to assign exact zeros to irrelevant tokens. Furthermore, we introduce Adaptive-Scalable Entmax (ASEntmax), which endows $α$-entmax with a learnable temperature parameter, allowing the attention distribution to interpolate between sparse (pattern-focused) and dense (softmax-like) regimes. Our empirical evaluation on synthetic tasks and language modeling demonstrates that ASEntmax substantially outperforms softmax, scalable softmax, and fixed-temperature $α$-entmax baselines, achieving up to 1000$\times$ length extrapolation on synthetic benchmarks and superior long-context generalization on language modeling while preserving short-context performance, including better perplexity trends and higher retrieval accuracies at 8$\times$ training length.

The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major threat is indirect prompt injection, where attackers embed malicious instructions in external environment output, causing agents to interpret and execute them as if they were legitimate prompts. While previous research has focused primarily on plain-text injection attacks, we find a significant yet underexplored vulnerability: LLMs' dependence on structured chat templates and their susceptibility to contextual manipulation through persuasive multi-turn dialogues. To this end, we introduce ChatInject, an attack that formats malicious payloads to mimic native chat templates, thereby exploiting the model's inherent instruction-following tendencies. Building on this foundation, we develop a persuasion-driven Multi-turn variant that primes the agent across conversational turns to accept and execute otherwise suspicious actions. Through comprehensive experiments across frontier LLMs, we demonstrate three critical findings: (1) ChatInject achieves significantly higher average attack success rates than traditional prompt injection methods, improving from 5.18% to 32.05% on AgentDojo and from 15.13% to 45.90% on InjecAgent, with multi-turn dialogues showing particularly strong performance at average 52.33% success rate on InjecAgent, (2) chat-template-based payloads demonstrate strong transferability across models and remain effective even against closed-source LLMs, despite their unknown template structures, and (3) existing prompt-based defenses are largely ineffective against this attack approach, especially against Multi-turn variants. These findings highlight vulnerabilities in current agent systems.

This paper introduces Agentics, a functional agentic AI framework for building LLM-based structured data workflow pipelines. Designed for both research and practical applications, Agentics offers a new data-centric paradigm in which agents are embedded within data types, enabling logical transduction between structured states. This design shifts the focus toward principled data modeling, providing a declarative language where data types are directly exposed to large language models and composed through transductions triggered by type connections. We present a range of structured data workflow tasks and empirical evidence demonstrating the effectiveness of this approach, including data wrangling, text-to-SQL semantic parsing, and domain-specific multiple-choice question answering. The open source Agentics is available at https://github.com/IBM/Agentics.

The rapid advancement of Diffusion Large Language Models (dLLMs) introduces unprecedented vulnerabilities that are fundamentally distinct from Autoregressive LLMs, stemming from their iterative and parallel generation mechanisms. In this paper, we conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics. Experimental results reveal a harmful bias inherent in the standard greedy remasking strategy and identify a critical phenomenon we term Denoising-path Dependence, where the safety of early-stage tokens decisively influences the final output. These findings also indicate that while current decoding strategies constitute a significant vulnerability, dLLMs possess a substantial intrinsic safety potential. To unlock this potential, we propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach: Stochastic Annealing Remasking dynamically introduces controlled randomness to mitigate greedy selection bias, while Block-level Audit and Repair exploits internal model representations for autonomous risk detection and guided correction. Comprehensive experiments on four dLLMs demonstrate DiffuGuard's exceptional effectiveness, reducing Attack Success Rate against six diverse jailbreak methods from 47.9% to 14.7% while preserving model utility and efficiency. Our code is available at: https://github.com/niez233/DiffuGuard.

Building Large Language Model agents that expand their capabilities by interacting with external tools represents a new frontier in AI research and applications. In this paper, we introduce InfoAgent, a deep research agent powered by an innovative data synthesis pipeline and orchestrated web search tools. To construct challenging, hard-to-find queries, we build entity trees and apply sub-tree sampling with entity fuzzification to systematically increase question difficulty. Unlike prior work that relies heavily on commercial search tools, we develop a dedicated self-hosted search infrastructure, enhancing transparency of agent environments and facilitating further advancement of agent capacity. We evaluate the effectiveness of our data pipeline by measuring the average number of tool calls required to correctly answer a question, and also show that our agent yields better performance when equipped with our tools. Our InfoAgent is post-trained from Qwen3-14B using a two-stage recipe: cold-start supervised finetun-ing to instill long-horizon search behaviors, followed by reinforcement learning which significantly improves reasoning-driven tool use. With our methods, InfoAgent achieves 15.3% accuracy on BrowseComp, 29.2% on BrowseComp-ZH, and 40.4% on Xbench-DS, outperforming prior open-source deep research agents such as WebSailor-72B and DeepDive-32B. The Internet has revolutionized the way people acquire knowledge, yet the tools that mediate access to online information have evolved unevenly (Zhang et al., 2025). Recently, researchers have enhanced Large Language Models (LLMs) with agentic capabilities via Reinforcement Learning (RL), which allows them to autonomously plan, search, and learn in an ongoing loop (OpenAI, 2025b). Deep Research Agents (DRAs) are distinguished by their ability to plan, reason, execute multi-step information-seeking actions, such as retrieving documents from the Internet via given tools, and complete complex research tasks. Recognizing their potential, major AI providers have raced to deliver commercial implementations (OpenAI, 2025a; Perplexity, 2025; xAI, 2025a; Google, 2025). This phenomenon shows that deep research is becoming a defining feature of next-generation information platforms. The implementation of DRA faces two challenges: effective strategy for data synthesis and the establishment of an efficient interactive environment. Existing open-source DRAs often perform shallow searches, mainly because they are trained on relatively simple data (Jin et al., 2025; Li et al., 2025c). Training dataset must encompass a broad range of data, which is of various uncertain types, so that the agent is forced to link disparate pieces of information and infer new knowledge when retrieving documents. Meanwhile, some agents are trained in simulated environments, which are underpowered when confronted with challenging real-world problems (Jin et al., 2025).

We introduce DC-VideoGen, a post-training acceleration framework for efficient video generation. DC-VideoGen can be applied to any pre-trained video diffusion model, improving efficiency by adapting it to a deep compression latent space with lightweight fine-tuning. The framework builds on two key innovations: (i) a Deep Compression Video Autoencoder with a novel chunk-causal temporal design that achieves 32x/64x spatial and 4x temporal compression while preserving reconstruction quality and generalization to longer videos; and (ii) AE-Adapt-V, a robust adaptation strategy that enables rapid and stable transfer of pre-trained models into the new latent space. Adapting the pre-trained Wan-2.1-14B model with DC-VideoGen requires only 10 GPU days on the NVIDIA H100 GPU. The accelerated models achieve up to 14.8x lower inference latency than their base counterparts without compromising quality, and further enable 2160x3840 video generation on a single GPU. Code: https://github.com/dc-ai-projects/DC-VideoGen.

We introduce SIRI, Scaling Iterative Reinforcement Learning with Interleaved Compression, a simple yet effective RL approach for Large Reasoning Models (LRMs) that enables more efficient and accurate reasoning. Existing studies have observed repetitive thinking patterns in LRMs, and attempts to reduce them often come at the cost of performance. In this paper, we show that this trade-off can be overcome through a training regime that iteratively alternates between compressing and expanding the reasoning budget, by dynamically adjusting the maximum rollout length during training. The compression phase cuts the rollout length, forcing the model to make precise and valuable decisions within a limited context, which effectively reduces redundant tokens and increases reasoning density. The expansion phase then relaxes the length limit, providing space for the model to explore and plan in long-horizon settings. Remarkably, we find that after each compression-expansion cycle, the model's performance improves even as its output length decreases, steadily pushing it closer to the Pareto frontier in the performance-efficiency trade-off. Training on DeepSeek-R1-Distill-Qwen-1.5B, SIRI-low improves performance on AIME24 by 43.2% while reducing token usage by 46.9% after three iterations, and SIRI-high achieves the highest accuracy compared to all other methods (Figure 1). Our findings shed light on the potential of periodically oscillating the LRM's output truncation length during training to dynamically balance exploration and efficiency in reasoning, converging towards an optimal "sweet spot" between the two. Our models are publicly available.