Long-term memory is a critical capability for multimodal large language model (MLLM) agents, particularly in conversational settings where information accumulates and evolves over time. However, existing benchmarks either evaluate multi-session memory in text-only conversations or assess multimodal understanding within localized contexts, failing to evaluate how multimodal memory is preserved, organized, and evolved across long-term conversational trajectories. Thus, we introduce Mem-Gallery, a new benchmark for evaluating multimodal long-term conversational memory in MLLM agents. Mem-Gallery features high-quality multi-session conversations grounded in both visual and textual information, with long interaction horizons and rich multimodal dependencies. Building on this dataset, we propose a systematic evaluation framework that assesses key memory capabilities along three functional dimensions: memory extraction and test-time adaptation, memory reasoning, and memory knowledge management. Extensive benchmarking across twelve memory systems reveals several key findings, highlighting the necessity of explicit multimodal information retention and memory organization, the persistent limitations in memory reasoning and knowledge management, as well as the efficiency bottleneck of current models. Our benchmark and dataset are available at https://github.com/YuanchenBei/Mem-Gallery.

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating them with an external knowledge base to improve the answer relevance and accuracy. In real-world scenarios, beyond pure text, a substantial amount of knowledge is stored in tables, and user questions often require retrieving answers that are distributed across multiple tables. Retrieving knowledge from a table corpora (i.e., various individual tables) for a question remains nascent, for (i) how to understand intra- and inter-table knowledge effectively, (ii) how to filter unnecessary tables and retrieve the most relevant tables efficiently, (iii) how to organize complex retrieved contexts for LLMs’ reasoning, and (iv) how to evaluate the corresponding performance in a realistic setting. Facing the above challenges, in this paper, we first propose a table-corpora-aware RAG framework, named T-RAG, which consists of the hierarchical memory index, multi-stage retrieval, and graph-aware context organization for effective and efficient table knowledge retrieval and inference. Then, we develop a multi-table question answering benchmark named MultiTableQA, which spans 3 different task types, 57,193 tables, and 23,758 questions in total, and the sources are all from real-world scenarios. Based on MultiTableQA, we perform a comprehensive comparison of table retrieval methods, RAG-based approaches, and table-to-graph representation learning methods. T-RAG consistently achieves state-of-the-art accuracy, recall, and runtime performance, with improvements of up to 9.4%. Moreover, T-RAG yields an average inference gain of 11.8% across different downstream backbone LLMs. Our code and data are available at https://github.com/jiaruzouu/T-RAG.

Recent advancements in Large Language Models (LLMs) have enabled autonomous agents to decompose complex tasks, select appropriate tools, and execute structured workflows. However, a key challenge in this field is the lack of a universal, large-scale, and cross-domain benchmark to systematically evaluate LLMs’ ability to reason over and utilize interconnected tools for automation. Existing benchmarks, such as TaskBench, focus on manually curated tool graphs for benchmark generation, which lack scalability and diversity across domains. To address this, we propose UniToolBench, a benchmark that incorporates automated tool graph construction by formulating link prediction as a probabilistic task, instead of relying on categorical LLM outputs. Furthermore, we introduce a confidence-based beam search sampling strategy to select high-confidence tool dependencies, ensuring more structured and semantically coherent subgraphs for evaluation. Through extensive experiments on multiple datasets, we demonstrate that while LLMs show promise in tool selection, significant challenges remain in parameter prediction and handling complex tool dependencies.

Large language models (LLMs) are increasingly integrated with specialized external tools, yet many tasks demand zero-shot tool usage with minimal or noisy documentation. Existing solutions rely on manual rewriting or labeled data for validation, making them inapplicable in true zero-shot settings. To address these challenges, we propose PLAY2PROMPT, an automated framework that systematically “plays” with each tool to explore its input-output behaviors. Through this iterative trial-and-error process, PLAY2PROMPT refines tool documentation and generates usage examples without any labeled data. These examples not only guide LLM inference but also serve as validation to further enhance tool utilization. Extensive experiments on real-world tasks demonstrate that PLAY2PROMPT significantly improves zero-shot tool performance across both open and closed models, offering a scalable and effective solution for domain-specific tool integration.

The advancement of large language models (LLMs) has led to a greater challenge of having a rigorous and systematic evaluation of complex tasks performed, especially in enterprise applications. Therefore, LLMs need to be benchmarked with enterprise datasets for a variety of NLP tasks. This work explores benchmarking strategies focused on LLM evaluation, with a specific emphasis on both English and Japanese. The proposed evaluation framework encompasses 25 publicly available domain-specific English benchmarks from diverse enterprise domains like financial services, legal, climate, cyber security, and 2 public Japanese finance benchmarks. The diverse performance of 8 models across different enterprise tasks highlights the importance of selecting the right model based on the specific requirements of each task. Code and prompts are available on GitHub.

Recent works have demonstrated the effectiveness of self-alignment in which a large language model is aligned to follow general instructions using instructional data generated from the model itself starting from a handful of human-written seeds. Instead of general alignment, in this work, we focus on self-alignment for expert domain specialization (e.g., biomedicine, finance). As a preliminary, we quantitively show the marginal effect that generic instruction-following training has on downstream expert domains’ performance. To remedy this, we propose self-specialization - allowing for effective model specialization while achieving cross-task generalization by leveraging only a few labeled seeds. Self-specialization offers a data- and parameter-efficient way of “carving out” an expert model out of a generalist pre-trained LLM. Exploring a variety of popular open large models as a base for specialization, our experimental results in both biomedical and financial domains show that our self-specialized models outperform their base models by a large margin, and even larger models that are generally instruction-tuned or that have been adapted to the target domain by other means.

This paper studies the relationship between the surface form of a mathematical problem and its solvability by large language models. We find that subtle alterations in the surface form can significantly impact the answer distribution and the solve rate, exposing the language model’s lack of robustness and sensitivity to the surface form in reasoning through complex problems. To improve mathematical reasoning performance, we propose Self-Consistency-over-Paraphrases (SCoP), which diversifies reasoning paths from specific surface forms of the problem. We evaluate our approach on four mathematics reasoning benchmarks over three large language models and show that SCoP improves mathematical reasoning performance over vanilla self-consistency, particularly for problems initially deemed unsolvable. Finally, we provide additional experiments and discussion regarding problem difficulty and surface forms, including cross-model difficulty agreement and paraphrasing transferability, and Variance of Variations (VOV) for language model evaluation.

Accurate prediction of the stock price volatility, the rate at which the price of a stock increases or decreases over a particular period, is an important problem in finance. Inaccurate prediction of stock price volatility might lead to investment risk and financial loss, while accurate prediction might generate significant returns for investors. Several studies investigated stock price volatility prediction in a regression task by using the transcripts of earning calls (quarterly conference calls held by public companies) with Natural Language Processing (NLP) techniques. Existing studies use the entire transcript and this degrades the performance due to noise caused by irrelevant information that might not have a significant impact on stock price volatility. In order to overcome these limitations, by considering stock price volatility prediction as a classification task, we explore several denoising approaches, ranging from general-purpose approaches to techniques specific to finance to remove the noise, and leverage AutoML systems that enable auto-exploration of a wide variety of models. Our preliminary findings indicate that domain-specific denoising approaches provide better results than general-purpose approaches, moreover AutoML systems provide promising results.

In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness. In this work, for the first time, we can improve the interpretability of explanations by allowing arbitrary text sequences as the explanation unit. On top of this, we implement a hessian-free method with a model faithfulness guarantee. Finally, to compare our method with the others, we propose a semantic-based evaluation metric that can better align with humans’ judgment of explanations than the widely adopted diagnostic or re-training measures. The empirical results on multiple real data sets demonstrate the proposed method’s superior performance to popular explanation techniques such as Influence Function or TracIn on semantic evaluation.