The booming development of AI agents presents unprecedented opportunities for automating complex tasks across various domains. However, their multi-step, multi-tool collaboration capabilities in the financial sector remain underexplored. This paper introduces FinGAIA, an end-to-end benchmark designed to evaluate the practical abilities of AI agents in the financial domain. FinGAIA comprises 407 meticulously crafted tasks, spanning seven major financial sub-domains: securities, funds, banking, insurance, futures, trusts, and asset management. These tasks are organized into three hierarchical levels of scenario depth: basic business analysis, asset decision support, and strategic risk management. We evaluated 10 mainstream AI agents in a zero-shot setting. The best-performing agent, ChatGPT, achieved an overall accuracy of 48.9\%, which, while superior to non-professionals, still lags financial experts by over 35 percentage points. Error analysis has revealed five recurring failure patterns: Cross-modal Alignment Deficiency, Financial Terminological Bias, Operational Process Awareness Barrier, among others. These patterns point to crucial directions for future research. Our work provides the first agent benchmark closely related to the financial domain, aiming to objectively assess and promote the development of agents in this crucial field. Partial data is available at https://github.com/SUFE-AIFLM-Lab/FinGAIA.

Agentic search, as a more autonomous and adaptive paradigm of retrieval augmentation, is driving the evolution of intelligent search systems. However, existing evaluation frameworks fail to align well with the goals of agentic search. First, the complex queries commonly used in current benchmarks often deviate from realistic user search scenarios. Second, prior approaches tend to introduce noise when extracting ground truth for end-to-end evaluations, leading to distorted assessments at a fine-grained level. Third, most current frameworks focus solely on the quality of final answers, neglecting the evaluation of the iterative process inherent to agentic search. To address these limitations, we propose RAVine -- a Reality-Aligned eValuation framework for agentic LLMs with search. RAVine targets multi-point queries and long-form answers that better reflect user intents, and introduces an attributable ground truth construction strategy to enhance the accuracy of fine-grained evaluation. Moreover, RAVine examines model's interaction with search tools throughout the iterative process, and accounts for factors of efficiency. We benchmark a series of models using RAVine and derive several insights, which we hope will contribute to advancing the development of agentic search systems. The code and datasets are available at https://github.com/SwordFaith/RAVine.

Are AI systems truly representing human values, or merely averaging across them? Our study suggests a concerning reality: Large Language Models (LLMs) fail to represent diverse cultural moral frameworks despite their linguistic capabilities. We expose significant gaps between AI-generated and human moral intuitions by applying the Moral Foundations Questionnaire across 19 cultural contexts. Comparing multiple state-of-the-art LLMs' origins against human baseline data, we find these models systematically homogenize moral diversity. Surprisingly, increased model size doesn't consistently improve cultural representation fidelity. Our findings challenge the growing use of LLMs as synthetic populations in social science research and highlight a fundamental limitation in current AI alignment approaches. Without data-driven alignment beyond prompting, these systems cannot capture the nuanced, culturally-specific moral intuitions. Our results call for more grounded alignment objectives and evaluation metrics to ensure AI systems represent diverse human values rather than flattening the moral landscape.

Fine-tuning is an immensely resource-intensive process when retraining Large Language Models (LLMs) to incorporate a larger body of knowledge. Although many fine-tuning techniques have been developed to reduce the time and computational cost involved, the challenge persists as LLMs continue to grow in size and complexity. To address this, a new approach to knowledge expansion in LLMs is needed. Retrieval-Augmented Generation (RAG) offers one such alternative by storing external knowledge in a database and retrieving relevant chunks to support question answering. However, naive implementations of RAG face significant limitations in scalability and answer accuracy. This paper introduces KeyKnowledgeRAG (K2RAG), a novel framework designed to overcome these limitations. Inspired by the divide-and-conquer paradigm, K2RAG integrates dense and sparse vector search, knowledge graphs, and text summarization to improve retrieval quality and system efficiency. The framework also includes a preprocessing step that summarizes the training data, significantly reducing the training time. K2RAG was evaluated using the MultiHopRAG dataset, where the proposed pipeline was trained on the document corpus and tested on a separate evaluation set. Results demonstrated notable improvements over common naive RAG implementations. K2RAG achieved the highest mean answer similarity score of 0.57, and reached the highest third quartile (Q3) similarity of 0.82, indicating better alignment with ground-truth answers. In addition to improved accuracy, the framework proved highly efficient. The summarization step reduced the average training time of individual components by 93%, and execution speed was up to 40% faster than traditional knowledge graph-based RAG systems. K2RAG also demonstrated superior scalability, requiring three times less VRAM than several naive RAG implementations tested in this study.

The AI-Reporter represents a paradigmatic shift in scientific publication practice. This document demonstrates through a concrete case study how our system transforms academic presentations into publication-ready chapters -- in less than three minutes. Using Arno Simons' lecture on Large Language Models from the ``Large Language Models for the History, Philosophy, and Sociology of Science'' workshop (NEPI) as an example, we show how technological innovation bridges the gap between ephemeral presentation and permanent scientific documentation.

Large language models (LLMs) have shown strong performance across natural language reasoning tasks, yet their reasoning processes remain brittle and difficult to interpret. Prompting techniques like Chain-of-Thought (CoT) enhance reliability by eliciting intermediate reasoning steps or aggregating multiple outputs. However, they lack mechanisms for enforcing logical structure and assessing internal coherence. We introduce Theorem-of-Thought (ToTh), a novel framework that models reasoning as collaboration among three parallel agents, each simulating a distinct mode of inference: abductive, deductive, and inductive. Each agent produces a reasoning trace, which is structured into a formal reasoning graph. To evaluate consistency, we apply Bayesian belief propagation guided by natural language inference (NLI), assigning confidence scores to each step. The most coherent graph is selected to derive the final answer. Experiments on symbolic (WebOfLies) and numerical (MultiArith) reasoning benchmarks show that ToTh consistently outperforms CoT, Self-Consistency, and CoT-Decoding across multiple LLMs, while producing interpretable and logically grounded reasoning chains. Our findings suggest a promising direction for building more robust and cognitively inspired LLM reasoning. The implementation is available at https://github.com/KurbanIntelligenceLab/theorem-of-thought.

Large Language Models (LLMs) increasingly shape public discourse, yet most evaluations of political and economic bias have focused on high-resource, Western languages and contexts. This leaves critical blind spots in low-resource, multilingual regions such as Pakistan, where linguistic identity is closely tied to political, religious, and regional ideologies. We present a systematic evaluation of political bias in 13 state-of-the-art LLMs across five Pakistani languages: Urdu, Punjabi, Sindhi, Pashto, and Balochi. Our framework integrates a culturally adapted Political Compass Test (PCT) with multi-level framing analysis, capturing both ideological stance (economic/social axes) and stylistic framing (content, tone, emphasis). Prompts are aligned with 11 socio-political themes specific to the Pakistani context. Results show that while LLMs predominantly reflect liberal-left orientations consistent with Western training data, they exhibit more authoritarian framing in regional languages, highlighting language-conditioned ideological modulation. We also identify consistent model-specific bias patterns across languages. These findings show the need for culturally grounded, multilingual bias auditing frameworks in global NLP.

Constructing specialized content corpora from vast, unstructured web sources for domain-specific applications poses substantial data curation challenges. In this paper, we introduce a streamlined approach for generating high-quality, domain-specific corpora by efficiently acquiring, filtering, structuring, and cleaning web-based data. We showcase how Large Language Models (LLMs) can be leveraged to address complex data curation at scale, and propose a strategical framework incorporating LLM-enhanced techniques for structured content extraction and semantic deduplication. We validate our approach in the behavior education domain through its integration into 30 Day Me, a habit formation application. Our data pipeline, named 30DayGen, enabled the extraction and synthesis of 3,531 unique 30-day challenges from over 15K webpages. A user survey reports a satisfaction score of 4.3 out of 5, with 91% of respondents indicating willingness to use the curated content for their habit-formation goals.

Speech and voice conditions can alter the acoustic properties of speech, which could impact the performance of paralinguistic models for affect for people with atypical speech. We evaluate publicly available models for recognizing categorical and dimensional affect from speech on a dataset of atypical speech, comparing results to datasets of typical speech. We investigate three dimensions of speech atypicality: intelligibility, which is related to pronounciation; monopitch, which is related to prosody, and harshness, which is related to voice quality. We look at (1) distributional trends of categorical affect predictions within the dataset, (2) distributional comparisons of categorical affect predictions to similar datasets of typical speech, and (3) correlation strengths between text and speech predictions for spontaneous speech for valence and arousal. We find that the output of affect models is significantly impacted by the presence and degree of speech atypicalities. For instance, the percentage of speech predicted as sad is significantly higher for all types and grades of atypical speech when compared to similar typical speech datasets. In a preliminary investigation on improving robustness for atypical speech, we find that fine-tuning models on pseudo-labeled atypical speech data improves performance on atypical speech without impacting performance on typical speech. Our results emphasize the need for broader training and evaluation datasets for speech emotion models, and for modeling approaches that are robust to voice and speech differences.

Referring Expression Generation (REG) is a core task for evaluating the pragmatic competence of vision-language systems, requiring not only accurate semantic grounding but also adherence to principles of cooperative communication (Grice, 1975). However, current evaluations of vision-language models (VLMs) often overlook the pragmatic dimension, reducing REG to a region-based captioning task and neglecting Gricean maxims. In this work, we revisit REG from a pragmatic perspective, introducing a new dataset (RefOI) of 1.5k images annotated with both written and spoken referring expressions. Through a systematic evaluation of state-of-the-art VLMs, we identify three key failures of pragmatic competence: (1) failure to uniquely identify the referent, (2) inclusion of excessive or irrelevant information, and (3) misalignment with human pragmatic preference, such as the underuse of minimal spatial cues. We also show that standard automatic evaluations fail to capture these pragmatic violations, reinforcing superficial cues rather than genuine referential success. Our findings call for a renewed focus on pragmatically informed models and evaluation frameworks that align with real human communication.