Quantitative strategy optimization remains largely manual, requiring domain experts to identify weak signals, tune risk-control rules, and repeatedly validate iterative revisions. Large language models can accelerate this process, but directly relying on them to rewrite trading strategies often introduces hallucinated edits, strategy drift, and back-test overfitting. We propose EVOQUANT, a self-evolving verifier-guided framework for strategy optimization in quantitative trading. Our method utilizes LLMs to deeply diagnose performance bottlenecks, generate semantically controlled candidate edits, select the best strategy through a multi-stage verification pipeline, and distill optimization experience into reusable knowledge for continual self-improvement. We evaluate our method using seven representative strategies: four from the A-share market and three from the crypto market. Experimental results show that our method significantly improves the Sharpe ratio across all tested strategies: the average test Sharpe increases from −0.298 to 0.538, and the best-performing strategy achieves a 199% relative improvement. Ablation studies and stress tests under stricter conditions further validate the effectiveness and robustness of the framework. Overall, this work transforms quantitative strategy optimization from costly manual trial-and-error into an automated and verifiable iterative paradigm, offering a new path for applying large language models to financial strategy research.

Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce trading value. Existing evaluations typically report performance metrics, but rarely examine agentic viability: whether dynamic LLM-mediated decisions convert their induced costs into measurable incremental profit. To apply this criterion, we introduce TradeLens, a trace-grounded diagnostic toolkit for evaluating agentic trading systems from their trading records, runtime traces, and deployment configurations. It reconstructs trading trajectories, attributes profit and cost to interpretable evidence, and diagnoses whether and why an agent pays for its own intelligence. We conduct extensive analysis across backbone models, capital scales, trading frequencies, and system architectures, together with deployment discussion. Our results show that viability hinges on intelligence-to-profit conversion: models exhibit different failure patterns, such as poor asset selection in DeepSeek-V3.2 and negative timing in GLM-4.7, while capital scale, trading frequency, and architecture matter primarily in these runs, especially through their effects on decision-attributed timing value. These findings reframe the evaluation of LLM-based trading agents from capability-centric performance ranking to trace-grounded diagnosis of intelligence-to-profit conversion. Our code is available at https://github.com/ParadooxAI/TradeLens.

In document AI, reliable analytics require converting long, noisy (often multi-document) corpora into heterogeneous structured data—e.g., tables for numerical fields, graphs for relations, and trees for hierarchies. Yet, one-pass LLM extraction often yields incomplete or inconsistent structures because it lacks explicit verification and opportunities to revise earlier choices. We present CycleIE, an iterative information extraction (IE) framework that closes the loop between reasoning and acting by coupling ReAct with Monte Carlo Tree Search (MCTS). CycleIE employs a multi-agent workflow to iteratively retrieve, structure, extract, and refine content under verification guidance. By treating extraction as a feedback-driven search process, CycleIE systematically corrects omissions and inconsistencies that defeat one-pass methods, while remaining orthogonal to retrieval-augmented generation (RAG). Experiments on challenging document-based QA benchmarks demonstrate that CycleIE delivers >10% relative improvements over strong baselines, particularly in lengthy or multi-document contexts.

Large language models (LLMs) are increasingly used to explain numerical time series, but fluent explanations can misstate when a change occurs, overstate a trend, or introduce unsupported patterns. Existing evaluations often score forecasts, answers, or whole explanations, leaving claim-level temporal grounding undermeasured. We introduce TimeClaimBench, a benchmark that parses explanations into atomic temporal claims and verifies them against a deterministic extracted event graph. Across five LLMs on controlled synthetic series, event-grounded prompting raises the strict graph-supported rate by 18.3 points and reduces graph-unsupported claims by 27.9 points under this fixed operational criterion. Calibration analyses show the boundary of that result. The extractor recovers the designed primary event in 394 of 400 series, but this does not estimate the precision of additional extracted events. A blinded two-annotator comparison on one model and 40 series reverses the automatic ordering: holistic ratings favor Direct and chain-of-thought outputs over event-grounded outputs. therefore distinguishes four axes that should not be conflated: designed-event recovery, the unresolved precision of additional events, claim-to-graph consistency, and whole-explanation human judgment. Code: https://github.com/lunaaa95/TimeClaimBench

Human experts tackle difficult math problems by identifying and executing a few pivotal steps rather than listing every intermediate thought. In contrast, standard Chain-of-Thought (CoT) distillation trains small models on lengthy reasoning traces, encouraging a uniform overthinking style across easy and hard items alike. The result is rigid, slow solutions that sacrifice adaptivity. This approach stands in sharp contrast to human intuition. Humans naturally adapt their problem-solving strategy, dedicating significant effort to difficult problems while finding quick, simple solutions for easier ones. We argue that the root cause lies in the training data: it contains excess information and reasoning steps organized in ways misaligned with human practice. We address this with Difficulty-Aware Distillation(DAD), a procedure for producing training data that mirrors concise human reasoning. A large teacher model first assesses a problem’s difficulty and then rewrites the solution to retain only the essential steps. Using this process, we constructed LiteCoT, a 100,000-example corpus of short, clear rationales, and used it to train our Liter models. With 100k LiteCoT, we outperform models trained on 800k long CoT and cut both training and inference costs. The advantage is consistent across standard math benchmarks, showing that concise, human-aligned data delivers equal or better accuracy with much less compute. For example, on the challenging AIME24 exam, our approach reaches 74.2% Pass@1 using only about 5K inference tokens, surpassing other methods that consume many more tokens.

Text-to-chart retrieval enables users to locate relevant charts through natural language queries and has emerged as a critical capability in modern business intelligence systems. However, current benchmarks fail to simulate realistic user queries or test deep semantic understanding, leaving a significant evaluation gap. To address this, we introduce CRBench, the first real-world BI-sourced benchmark comprising 21,862 charts and 326 queries, which adopts a Target-and-Distractor paradigm to evaluate discriminative retrieval among highly similar candidates. Benchmarking reveals that existing methods, which rely primarily on visual features, fail to capture the rich analytical semantics of charts. We therefore propose a semantic insights synthesis pipeline that automatically generates three hierarchical levels of insights for alignment training: visual patterns, statistical properties, and practical applications. Using this pipeline, we produce 207,498 insights for 69,166 charts as training data. Leveraging this data, we develop ChartFinder, which significantly outperforms state-of-the-art methods on CRBench, achieving 66.9% NDCG@10 for precise queries (an 11.58% improvement) and an average gain of 5% across fuzzy query metrics.

Despite well-known hallucination issues, LLMs have become an increasingly indispensable source of information, and the underlying technology has advanced rapidly to make their answers far more reliable. Early on, Retrieval-Augmented Generation (RAG) emerged as the dominant remedy, grounding LLM responses in external knowledge and evolving from simple retrieve-then-read pipelines into modular, graph-enhanced, and agentic systems. More recently, Agentic Deep Research has pushed the frontier further, equipping LLMs with autonomous planning, multi-hop investigation, and iterative synthesis to tackle open-ended questions that no single retrieval pass can answer. This tutorial offers an in-depth treatment of modern RAG and Deep Research, grounded in an AI-assisted systematic analysis of 2,000+ recent papers (2020–2026). Attendees will leave with a structured roadmap, evidence-backed practical recommendations, and a clear map of open research opportunities.

Retrieval-Augmented Generation (RAG) mitigates hallucination in Large Language Models (LLMs) by incorporating external data, with Knowledge Graphs (KGs) offering crucial information for question answering. Traditional Knowledge Graph Question Answering (KGQA) methods rely on semantic parsing, which typically retrieves knowledge strictly necessary for answer generation, thus often suffer from low coverage due to rigid schema requirements and semantic ambiguity. We present KERAG, a novel KG-based RAG pipeline that enhances QA coverage by retrieving a broader subgraph likely to contain relevant information. Our retrieval-filtering-summarization approach, combined with fine-tuned LLMs for Chain-of-Thought reasoning on knowledge sub-graphs, reduces noises and improves QA for both simple and complex questions. Experiments demonstrate that KERAG surpasses state-of-the-art solutions by about 7% in quality and exceeds GPT-4o (Tool) by 10-21%.

Cross-Document Multi-entity question answering (MEQA) demands the integration of scattered information across documents to resolve complex queries involving entities, relationships, and contextual dependencies. Although Large Language Models (LLMs) and Retrieval-augmented Generation (RAG) systems show promise, their performance on cross-document MEQA remains underexplored due to the absence of tailored benchmarks. To address this gap, we introduce MEBench, a scalable multi-document, multi-entity benchmark designed to systematically evaluate LLMs’ capacity to retrieve, consolidate, and reason over scattered and dense information. Our benchmark comprises 4,780 questions which are systematically categorized into three primary categories: Comparative Reasoning, Statistical Reasoning and Relational Reasoning, further divided into eight distinct types, ensuring broad coverage of real-world multi-entity reasoning scenarios. Our experiments on state-of-the-art LLMs reveal critical limitations: even advanced models achieve only 59% accuracy on MEBench. Our benchmark emphasizes the importance of completeness and factual precision of information extraction in MEQA tasks, using Entity-Attributed F1 (EA-F1) metric for granular evaluation of entity-level correctness and attribution validity. MEBench not only highlights systemic weaknesses in current LLM frameworks but also provides a foundation for advancing robust, entity-aware QA architectures.

Chart question answering (ChartQA) tasks play a critical role in interpreting and extracting insights from visualization charts. While recent advancements in multimodal large language models (MLLMs) like GPT-4o have shown promise in high-level ChartQA tasks, such as chart captioning, their effectiveness in low-level ChartQA tasks (e.g., identifying correlations) remains underexplored.In this paper, we address this gap by evaluating MLLMs on low-level ChartQA using a newly curated dataset, ChartInsights, which consists of 22,347 (chart, task, query, answer) covering 10 data analysis tasks across 7 chart types. We systematically evaluate 19 advanced MLLMs, including 12 open-source and 7 closed-source models. The average accuracy rate across these models is 39.8%, with GPT-4o achieving the highest accuracy at 69.17%.To further explore the limitations of MLLMs in low-level ChartQA, we conduct experiments that alter visual elements of charts (e.g., changing color schemes, adding image noise) to assess their impact on the task effectiveness. Furthermore, we propose a new textual prompt strategy, Chain-of-Charts, tailored for low-level ChartQA tasks, which boosts performance by 14.41%, achieving an accuracy of 83.58%. Finally, incorporating a visual prompt strategy that directs attention to relevant visual elements further improves accuracy to 84.32%.

A multimodal large language model MLLMs may struggle with answering visual-based (personal) entity questions (VEQA), such as ”who is A?” or ”who is A that B is talking to?” for various reasons, e.g., the absence of the name of A in the caption or the inability of MLLMs to recognize A, particularly for less common entities. Furthermore, even if the MLLMs can identify A, it may refrain from answering due to privacy concerns. In this paper, we introduce a novel method called Matching-Augmented Reasoning (MAR) to enhance VEQA. Given a collection of visual objects with captions, MAR preprocesses each object individually, identifying faces, names, and their alignments within the object. It encodes this information and stores their vector representations in vector databases. When handling VEQA, MAR retrieves matching faces and names and organizes these entities into a matching graph. MAR then derives the answer to the query by reasoning over this matching graph. Extensive experiments show that MAR significantly improves VEQA compared with the state-of-the-art methods using MLLMs.

Fact verification has attracted a lot of attention recently, e.g., in journalism, marketing, and policymaking, as misinformation and dis- information can sway one’s opinion and affect one’s actions. While fact-checking is a hard task in general, in many cases, false statements can be easily debunked based on analytics over tables with reliable information. Hence, table- based fact verification has recently emerged as an important and growing research area. Yet, progress has been limited due to the lack of datasets that can be used to pre-train language models (LMs) to be aware of common table operations, such as aggregating a column or comparing tuples. To bridge this gap, this paper introduces PASTA for table-based fact verification via pre-training with synthesized sentence–table cloze questions. In particular, we design six types of common sentence–table cloze tasks, including Filter, Aggregation, Superlative, Comparative, Ordinal, and Unique, based on which we synthesize a large corpus consisting of 1.2 million sentence–table pairs from WikiTables. PASTA uses a recent pre-trained LM, DeBERTaV3, and further pre- trains it on our corpus. Our experimental results show that PASTA achieves new state-of-the-art (SOTA) performance on two table-based fact verification datasets TabFact and SEM-TAB- FACTS. In particular, on the complex set of TabFact, which contains multiple operations, PASTA largely outperforms previous SOTA by 4.7% (85.6% vs. 80.9%), and the gap between PASTA and human performance on the small test set is narrowed to just 1.5% (90.6% vs. 92.1%).