Detecting machine-generated text (MGT) has emerged as a critical challenge, driven by the rapid advancement of large language models (LLMs) capable of producing highly realistic, human-like content. However, the performance of current approaches often degrades significantly under domain shift. To address this challenge, we propose a novel framework designed to capture both domain-specific and domain-general MGT patterns through a two-stage Disentangled mixturE-of-ExpeRts (DEER) architecture. First, we introduce a disentangled mixture-of-experts module, in which domain-specific experts learn fine-grained, domain-local distinctions between human and machine-generated text, while shared experts extract transferable, cross-domain features. Second, to mitigate the practical limitation of unavailable domain labels during inference, we design a reinforcement learning-based routing mechanism that dynamically selects the appropriate experts for each input instance, effectively bridging the train-inference gap caused by domain uncertainty. Extensive experiments on five in-domain and five out-of-domain benchmark datasets demonstrate that DEER consistently outperforms state-of-the-art methods, achieving average F1-score improvements of 1.39% and 5.32% on in-domain and out-of-domain datasets respectively, along with accuracy gains of 1.35% and 3.61% respectively. Ablation studies confirm the critical contributions of both disentangled expert specialization and adaptive routing to model performance.

Test-time reinforcement learning (TTRL) offers a label-free paradigm for adapting models using only synthetic signals at inference, but its success hinges on constructing reliable learning signals. Standard approaches such as majority voting often collapse to spurious yet popular answers. We introduce Self-Harmony, a framework built on a simple intuition: the correct answer should remain stable across both an original question and its paraphrase. Self-Harmony operationalizes this by employing a single model in two complementary roles: a Solver to produce answers and a Reframer to rephrase the input. Based on this, we further propose a pseudo-label method: instead of majority voting, it aggregates answer frequencies across these original and reframed views using the harmonic mean. This is a process that naturally selects for solutions stable under reframing, thereby avoiding the common trap of favoring view-dependent, spurious answers. Crucially, this requires no human supervision or auxiliary models. Across diverse reasoning benchmarks, Self-Harmony achieves state-of-the-art results at the label-free test-time setting, ranking first in 28 of 30 settings across multiple methods. Beyond accuracy, it demonstrates unprecedented robustness, with zero training failures in all experiments, underscoring its stability and reliability.

The rapid spread of fake news threatens social stability and public trust, rendering its detection an imperative research priority. Although large language models (LLMs) excel at numerous natural language processing tasks with their remarkable contextual understanding and extensive prior knowledge, the time-bounded knowledge coverage and tendency for generating hallucination content reduce their reliability when handling fast-evolving news streams. Furthermore, models trained on existing static datasets also often lack the generalization needed for emerging news topics. To address these challenges, we propose ZoFia, a novel two-stage zero-shot fake news detection framework. First, we introduce Hierarchical Salience to quantify the importance of entities in the news content, and propose the SC-MMR algorithm to effectively select an informative and diverse set of keywords that serve as queries for retrieving up-to-date external evidence. Subsequently, a multi LLM interactive system, in which each agent assumes a distinct role, performs multi-view collaborative analysis and adversarial debate over the news text and its related information, and finally produces an interpretable and robust judgment. Comprehensive experiments on two public datasets demonstrate that ZoFia obviously outperforms existing zero-shot baselines and most of few-shot methods. Our codes will be open-sourced to facilitate related communities.

Large language models (LLMs) are widely deployed for open-ended communication, yet most bias evaluations still rely on English, classification-style tasks. We introduce DebateBias-8K, a new multilingual, debate-style benchmark designed to reveal how narrative bias appears in realistic generative settings. Our dataset includes 8,400 structured debate prompts spanning four sensitive domains: women's rights, socioeconomic development, terrorism, and religion, across seven languages ranging from high-resource (English, Chinese) to low-resource (Swahili, Nigerian Pidgin). Using four flagship models (GPT-4o, Claude 3, DeepSeek, and LLaMA 3), we generate and automatically classify over 100,000 responses. Results show that all models reproduce entrenched stereotypes despite safety alignment: Arabs are overwhelmingly linked to terrorism and religion (>=95%), Africans to socioeconomic "backwardness" (up to <=77%), and Western groups are consistently framed as modern or progressive. Biases grow sharply in lower-resource languages, revealing that alignment trained primarily in English does not generalize globally. Our findings highlight a persistent divide in multilingual fairness: current alignment methods reduce explicit toxicity but fail to prevent biased outputs in open-ended contexts. We release our DebateBias-8K benchmark and analysis framework to support the next generation of multilingual bias evaluation and safer, culturally inclusive model alignment.

Salespeople frequently face the dynamic screening decision of whether to persist in a conversation or abandon it to pursue the next lead. Yet, little is known about how these decisions are made, whether they are efficient, or how to improve them. We study these decisions in the context of high-volume outbound sales where leads are ample, but time is scarce and failure is common. We formalize the dynamic screening decision as an optimal stopping problem and develop a generative language model-based sequential decision agent - a stopping agent - that learns whether and when to quit conversations by imitating a retrospectively-inferred optimal stopping policy. Our approach handles high-dimensional textual states, scales to large language models, and works with both open-source and proprietary language models. When applied to calls from a large European telecommunications firm, our stopping agent reduces the time spent on failed calls by 54% while preserving nearly all sales; reallocating the time saved increases expected sales by up to 37%. Upon examining the linguistic cues that drive salespeople's quitting decisions, we find that they tend to overweight a few salient expressions of consumer disinterest and mispredict call failure risk, suggesting cognitive bounds on their ability to make real-time conversational decisions. Our findings highlight the potential of artificial intelligence algorithms to correct cognitively-bounded human decisions and improve salesforce efficiency.

Large Language Models (LLMs) integrated with agent-based reasoning frameworks have recently shown strong potential for autonomous decision-making and system-level operations. One promising yet underexplored direction is microservice remediation, where the goal is to automatically recover faulty microservice systems. Existing approaches, however, still rely on human-crafted prompts from Site Reliability Engineers (SREs), with LLMs merely converting textual instructions into executable code. To advance research in this area, we introduce MicroRemed, the first benchmark for evaluating LLMs in end-to-end microservice remediation, where models must directly generate executable Ansible playbooks from diagnosis reports to restore system functionality. We further propose ThinkRemed, a multi-agent framework that emulates the reflective and perceptive reasoning of SREs. Experimental results show that MicroRemed presents substantial challenges to current LLMs, while ThinkRemed improves end-to-end remediation performance through iterative reasoning and system reflection. The benchmark is available at https://github.com/LLM4AIOps/MicroRemed.

Large Language Models (LLMs) have demonstrated strong capabilities in natural language reasoning, yet their application to Cyber Threat Intelligence (CTI) remains limited. CTI analysis involves distilling large volumes of unstructured reports into actionable knowledge, a process where LLMs could substantially reduce analyst workload. CTIBench introduced a comprehensive benchmark for evaluating LLMs across multiple CTI tasks. In this work, we extend CTIBench by developing AthenaBench, an enhanced benchmark that includes an improved dataset creation pipeline, duplicate removal, refined evaluation metrics, and a new task focused on risk mitigation strategies. We evaluate twelve LLMs, including state-of-the-art proprietary models such as GPT-5 and Gemini-2.5 Pro, alongside seven open-source models from the LLaMA and Qwen families. While proprietary LLMs achieve stronger results overall, their performance remains subpar on reasoning-intensive tasks, such as threat actor attribution and risk mitigation, with open-source models trailing even further behind. These findings highlight fundamental limitations in the reasoning capabilities of current LLMs and underscore the need for models explicitly tailored to CTI workflows and automation.

We investigate the application of large language models (LLMs) to construct credit networks from firms' textual financial statements and to analyze the resulting network structures. We start with using LLMs to translate each firm's financial statement into a credit network that pertains solely to that firm. These networks are then aggregated to form a comprehensive credit network representing the whole financial system. During this process, the inconsistencies in financial statements are automatically detected and human intervention is involved. We demonstrate that this translation process is effective across financial statements corresponding to credit networks with diverse topological structures. We further investigate the reasoning capabilities of LLMs in analyzing credit networks and determining optimal strategies for executing financial operations to maximize network performance measured by the total assets of firms, which is an inherently combinatorial optimization challenge. To demonstrate this capability, we focus on two financial operations: portfolio compression and debt removal, applying them to both synthetic and real-world datasets. Our findings show that LLMs can generate coherent reasoning and recommend effective executions of these operations to enhance overall network performance.

Existing LLM-based automatic test generation methods mainly produce input and expected output pairs to categorize the intended behavior of correct programs. Although straightforward, these methods have limited diversity in generated tests and cannot provide enough debugging information. We propose HarnessLLM, a two-stage training pipeline that enables LLMs to write harness code for testing. Particularly, LLMs generate code that synthesizes inputs and validates the observed outputs, allowing complex test cases and flexible output validation such as invariant checking. To achieve this, we train LLMs with SFT followed by RLVR with a customized reward design. Experiments show that HarnessLLM outperforms input-output-based testing in bug finding and testing strategy diversity. HarnessLLM further benefits the code generation performance through test-time scaling with our generated test cases as inference-phase validation. Our code is available at https://github.com/UCSB-NLP-Chang/HarnessLLM.git.

Reasoning over temporal and numerical data, such as time series, is a crucial aspect of fact-checking. While many systems have recently been developed to handle this form of evidence, their evaluation remains limited by existing datasets, which often lack structured evidence, provide insufficient justifications for verdicts, or rely on synthetic claims. In this paper, we introduce TSVer, a new benchmark dataset for fact verification focusing on temporal and numerical reasoning with time-series evidence. TSVer contains 287 real-world claims sourced from 38 fact-checking organizations and a curated database of 400 time series covering diverse domains. Each claim is annotated with time frames across all pertinent time series, along with a verdict and justifications reflecting how the evidence is used to reach the verdict. Using an LLM-assisted multi-step annotation process, we improve the quality of our annotations and achieve an inter-annotator agreement of kappa=0.745 on verdicts. We also develop a baseline for verifying claims against time-series evidence and show that even the state-of-the-art reasoning models like Gemini-2.5-Pro are challenged by time series, achieving a 63.37 accuracy score on verdicts and an Ev2R score of 48.63 on verdict justifications.