Function calling agents powered by Large Language Models (LLMs) select external tools to automate complex tasks. On-device agents typically use a retrieval module to select relevant tools, improving performance and reducing context length. However, existing retrieval methods rely on static and limited inputs, failing to capture multi-step tool dependencies and evolving task context. This limitation often introduces irrelevant tools that mislead the agent, degrading efficiency and accuracy. We propose Dynamic Tool Dependency Retrieval (DTDR), a lightweight retrieval method that conditions on both the initial query and the evolving tool calling plan. DTDR models tool dependencies from function calling demonstrations, enabling adaptive retrieval as plans unfold. We benchmark DTDR against state-of-the-art retrieval methods across multiple datasets and LLM backbones, evaluating retrieval precision, downstream task accuracy, and computational efficiency. Additionally, we explore strategies to integrate retrieved tools into prompts. Our results show that DTDR improves function calling success rates between 23% and 104% compared to state-of-the-art static retrievers.
论文检索
输入标题、作者或关键词，从 12,319 篇学术成果中精准定位
Current molecular generation benchmarks emphasize task complexity, molecule novelty, and property alignment; they largely overlook a critical concern: the potential safety risks of AI-generated molecules. In practice, many generative models may produce molecules with toxic, reactive, or otherwise hazardous characteristics—posing hidden dangers that remain insufficiently addressed. To address this gap, we introduce MolSafeEval, a benchmark dedicated to evaluating and analyzing the safety risks of molecular generation. Unlike prior approaches that rely on narrow toxicity predictors, MolSafeEval integrates heterogeneous safety knowledge—ranging from toxicological databases to hazard rules—into a structured molecular safety knowledge graph. This graph serves as a foundation for large language model–based reasoning, enabling systematic detection and explanation of unsafe features in generated compounds. We further categorize molecular generative models into four representative task types—unconditional generation, property optimization, target protein–based design, and text-based generation—and provide standardized datasets and safety evaluation protocols for each.
Recent advances in Text-to-SQL have greatly benefited from large language models, yet small and medium-sized models still suffer from frequent execution errors and limited self-correction ability. We present ReSQL (Retrieval-augmented error reasoning for Text-to-SQL), a self-improving framework that generates and learns from its own error-reasoning dataset, enabling models to autonomously refine their SQL generation and correction capabilities. ReSQL combines feedback-driven fine-tuning with retrieval-based inference: it gathers model-generated errors, analyzes them through structured feedback prompts, and retrieves relevant correction examples during inference. This unified approach allows models to internalize robust error-reasoning patterns and dynamically apply them to unseen queries. Experimental results on the SPIDER and BIRD benchmarks show that ReSQL substantially improves execution accuracy and self-correction ability over strong baselines, achieving competitive performance with much larger proprietary models such as GPT-4. Our findings highlight ReSQL as a promising step toward self-improving, reasoning-aware Text-to-SQL systems that can continually enhance their reliability and interpretability without external supervision. All code and generated reasoning datasets are available to facilitate application to open-source LLMs and reproducible baseline training.
Large language model (LLM)-based agents have demonstrated remarkable capabilities in tool use, but their ability to follow user preferences when calling tools remains underexplored. To address this gap, we introduce APOLLO, a benchmark designed to evaluate agents’ ability to identify personalized user preferences from interaction histories and to adhere to these preferences when calling tools to solve user queries. In APOLLO, user preferences expressed in the interaction history take two forms: explicit preferences stated directly, and implicit preferences conveyed through behaviors such as option selection and comparison. In addition, the benchmark includes two types of queries, reactive and proactive, which pose challenges for LLMs to ground user queries in the corresponding preferences. Using APOLLO, we evaluate and analyze both language models and reasoning models, and investigate the impact of different agent frameworks, such as Reflexion, on model performance. Experimental results show that current models still struggle to follow user preferences when calling tools. For instance, GPT-4o achieves only 51.16% accuracy on the benchmark. Furthermore, we develop a reinforcement learning-based approach to improve LLMs, achieving substantial performance gains on APOLLO. Our dataset and code are publicly available at https://github.com/zhiyuanc2001/APOLLO.
Measurement scales play a crucial role in quantifying the nuanced dimensions of human cognition and behavior, however, their development typically demands extensive manual labor, and current methodologies lack systematic automation and standardized evaluation. In this paper, we introduce AutoScale, a pioneering multi-agent framework that automates scale development by leveraging collaborative AI agents. Our contributions are threefold: (1) a novel multi-agent LLM-based framework for end-to-end scale generation that replicates expert collaboration and iterative data-driven refinement, (2) the first comprehensive dataset, SCALE-1.2K, comprising 1.2K validated scales across 16 psychological domains, establishing a benchmark for automated scale development, and (3) a multi-dimensional evaluation system, featuring Muti-LLM-as-judge for conceptual and linguistic assessment and simulated large-scale testing for rigorous psychometric verification. Experimental results demonstrate that AutoScale streamlines the scale development process while maintaining rigorous quality standards, significantly reducing manual effort and paving the way for more efficient and objective measurement design in diverse research fields.
High-quality mathematical and logical datasets with verifiable answers are essential for strengthening the reasoning capabilities of large language models (LLMs). While recent data augmentation techniques have facilitated the creation of large-scale benchmarks, existing LLM-generated datasets often suffer from limited reliability, diversity, and scalability. To address these challenges, we introduce PuzzleClone, a formal framework for synthesizing verifiable data at scale using a novel DSL-driven approach. Our approach features three key innovations: (1) encoding seed puzzles into structured logical specifications, (2) generating scalable variants through systematic variable and constraint randomization, and (3) ensuring validity via a reproduction mechanism. Applying PuzzleClone, we construct PC-83K, a benchmark comprising over 83K diverse and programmatically validated puzzles. The generated puzzles span a wide spectrum of difficulty and formats, posing significant challenges to current state-of-the-art models. Experimental results show that post training (SFT and RL) on PC-83K yields substantial improvements not only on the testset but also on various logic and mathematical benchmarks. Post training raises average performance on PC-83K from 14.5 to 66.0 and delivers consistent improvements across 7 logic and mathematical benchmarks up to 18.4 absolute percentage points (SATBench from 51.6 to 70.0). Our code and data are available at https://github.com/HiThink-Research/PuzzleClone.
Large Language Models (LLMs) have shown strong capabilities in code generation, but their adherence to fine-grained user intent with multiple constraints remains a significant challenge. Our empirical analysis reveals two key observations: 1) Model performance deteriorates quickly as the number of constraints in the user intent increases, and 2) While user intent does influence the model’s logits, such an influence may not be strong enough to effectively steer the decoding process. To this end, we propose Intent-Amplified Code Generation (IntentCoding), a novel decoding strategy that enhances an LLM’s ability to follow user intent. IntentCoding captures the influence of user intent by masking out the intent, and applies a multi-strength ensemble mechanism to amplify the effect of user intent during generation. IntentCoding is model-agnostic, requires no additional training, and integrates seamlessly with existing decoding procedures. To enable systematic evaluation, we also construct CodeConstraints, a benchmark dataset specifically designed to test user intent compliance under varying numbers of constraints. Experiments on our constructed Constraints, as well as popular IFEvalCode, HumanEval and LiveCodeBench datasets, show that our IntentCoding model significantly improves both constraint satisfaction and functional correctness compared to standard decoding approaches. IntentCoding achieves up to 71.0% relative improvement on CodeConstraints, achieves up to 67.3% relative improvement on IFEvalCode and achieves up to 29.3% relative improvement in pass@1 on HumanEval and LiveCodeBench compared with greedy decoding.
Detecting missing foreign keys (FKs) requires accurately modeling semantic dependencies across database schemas, which conventional heuristic-based methods are fundamentally limited in capturing. We propose LLM-FK, the first fully automated multi-agent framework for FK detection, designed to address three core challenges that hinder naive LLM-based solutions in large-scale complex databases: combinatorial search space explosion, ambiguous inference under limited context, and global inconsistency arising from isolated local predictions. LLM-FK coordinates four specialized agents: a Profiler that decomposes the FK detection problem into the task of validating FK candidate column pairs and prunes the search space via a unique-key-driven schema decomposition strategy; an Interpreter that injects self-augmented domain knowledge; a Refiner that constructs compact structural representations and performs multi-perspective chain-of-thought reasoning; and a Verifier that enforces schema-wide consistency through a holistic conflict resolution strategy. Experiments on five benchmark datasets demonstrate that LLM-FK consistently achieves F1-scores above 93%, surpassing existing baselines by 15% on the large-scale MusicBrainz database, while reducing the candidate search space by two to three orders of magnitude without losing true FKs and maintaining robustness under challenging conditions like missing data. These results demonstrate the effectiveness and scalability of LLM-FK in real-world databases.
SudokuFill: A Multi-Agent Progressive Filling Framework for Document-Level Scientific Information Extraction
PDF ↗Scientific information extraction (SciIE) is a key bottleneck for turning unstructured papers into computable knowledge bases, yet most existing systems still follow a “local extraction then global assembly” paradigm. This workflow is inherently lossy: by extracting fields in isolation, it breaks global correlations and discards high-confidence signals that could otherwise be reused as internal supervision, forcing systems to repeatedly restart from scratch, especially in long, multimodal scientific documents. In this paper, We propose a different view: SciIE should be solved as a progressive filling problem, similar to solving a Sudoku,once a field is filled with high confidence, it should act as a constraint that guides the remaining uncertain fields. Based on this idea, we introduce SudokuFill, a multi-agent framework that maintains a Global Filling State and performs priority scheduling to establish reliable anchors first, then reuses them as internal supervision for iterative deliberation over harder fields. Evaluated on a specialized document-level adjuvant dataset, our framework achieves a SOTA score of 51.83% on our benchmark. Crucially, SudokuFill enables a 7B model to outperform the vanilla GPT-4o, proving that structured architectural reasoning can effectively compensate for parameter scale.
Training effective AI agents for real-world tool-use interactions requires data that faithfully captures the dynamics of human–agent collaboration. However, such data is scarce, and existing methods often resort to synthetic data generation. The inherently dynamic and complex nature of user–agent interactions makes ensuring data quality particularly challenging. Current verification approaches are typically entangled with the synthesis process itself, resulting in complicated implementations that undermine both reproducibility and scalability. To address this, we introduce Tool-Verifier-7B, a plug-and-play framework for data quality control in tool-use scenarios. Building on this verifier and our data synthesis strategy, we construct the Tool-Verify dataset, which contains 3,295 curated samples. To directly assess verifier performance, we further release Tool-V-Bench, a benchmark of 165 human-validated trajectories spanning diverse interaction complexities. Comprehensive experiments show that Tool-Verifier-7B surpasses Qwen2.5-72B-Instruct on Tool-V-Bench. Moreover, the Tool-Verify dataset achieves superior performance compared to the previous APIGen-MT dataset.
Financial decision-making in multilingual settings demands accurate numerical reasoning grounded in diverse modalities, yet existing benchmarks largely overlook this high-stakes, real-world challenge, especially for Indic languages. We introduce FinVQA, a benchmark for evaluating financial numerical and multimodal reasoning in multilingual Indic contexts. FinVQA spans English, Hindi, Bengali, Marathi, Gujarati, and Tamil, and comprises 18,900 samples across 14 financial domains. The dataset captures diverse reasoning paradigms under realistic constraints, and is structured across three difficulty levels (easy, moderate, hard) and four question formats: multiple choice, fill-in-the-blank, table matching, and true/false. To address these challenges, we propose FIND, a framework that combines supervised fine-tuning with constraint-aware decoding to promote faithful numerical reasoning, robust multimodal grounding, and structured decision-making. Together, FinVQA and FIND establish a rigorous evaluation and modeling paradigm for high-stakes multilingual multimodal financial reasoning.
LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
PDF ↗Comprehensive understanding of time series remains a significant challenge for Large Language Models (LLMs). Current research is hindered by fragmented task definitions and benchmarks with inherent ambiguities, precluding rigorous evaluation and the development of unified Time Series Reasoning Models (TSRMs). To bridge this gap, we formalize Time Series Reasoning (TSR) via a four-level taxonomy of increasing cognitive complexity. We introduce HiTSR, a **hi**erarchical **t**ime **s**eries **r**easoning dataset comprising 83k samples with diverse task combinations and verified Chain-of-Thought (CoT) trajectories. Leveraging HiTSR, we propose LLaTiSA, a strong TSRM that integrates visualized patterns with precision-calibrated numerical tables to enhance the temporal perception of Vision-Language Models (VLMs). Through a multi-stage curriculum fine-tuning strategy, LLaTiSA achieves superior performance and exhibits robust out-of-distribution generalization across diverse TSR tasks and real-world scenarios. We will publicly release the code, dataset, and model weights.
OPINE: A Prior-calibrated Scoring Framework for LLM-based Multi-label Scientific Opinion Classification
PDF ↗Scientific opinion classification based on discourse functions provides a structured semantic basis for analytical tasks such as gap identification and hypothesis generation. However, this task is uniquely challenged by the multi-label nature of scientific expressions and AIMRaD structural constraints. Existing LLM-based methods typically rely on direct label generation, which obscures decision logic, or treat discourse information as passive context rather than a structural prior. We propose OPINE, a multi-stage framework that reformulates classification as a controllable *scoring-calibration-refinement* pipeline. By decoupling textual evidence from decision logic, OPINE generates independent label-wise affinity scores calibrated by AIMRaD priors. To resolve the multi-label challenge, we introduce a quantile-based decoding rule to naturally capture co-existing roles, alongside a pairwise refinement mechanism to mitigate confusion between similar categories. We contribute a new benchmark of 18 discourse functions across diverse sections. Experimental results show that OPINE generally outperforms strong baselines, reaching F1 scores of 63.20%, 53.68%, and 63.22% under Micro, Macro, and Example settings, respectively. Our analysis reveals that integrating discourse structures as explicit priors is superior to conventional passive context integration, while pairwise refinement successfully mitigates confusion between functionally similar categories. The code and dataset are available at https://github.com/znoodle63/OPINE.
GPS trajectories encode rich behavioral information about how people move, organize activities, and form daily routines. Recent advances in large language models (LLMs) raise a natural question: can such models infer and summarize travel behavior directly from mobility traces? This paper introduces TravelBehaviorQA, a large-scale benchmark dataset that reframes trajectory analysis as a language-based behavioral understanding task. The dataset links raw GPS trajectories with human-grounded question-answering (QA) pairs that capture travel intensity, temporal structure, activity patterns, mode usage, and behavioral routines. Unlike prior mobility datasets focused on prediction or classification, TravelBehaviorQA emphasizes semantic interpretation through a unified mix of deterministic and open-ended questions. In this benchmark, we construct over 143k QA instances spanning users and years, and evaluate a broad range of state-of-the-art LLMs under controlled settings. Our results reveal substantial gaps between factual extraction and genuine behavioral reasoning, showing that model scale alone is insufficient and that trajectory representation is a primary bottleneck. TravelBehaviorQA exposes critical limitations of current models and establishes a rigorous benchmark for advancing language-based understanding of human mobility behavior.
Multi-agent debate (MAD) is an emerging approach to improving the reasoning capabilities of large language models (LLMs). Existing MAD methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is decided by majority voting in the last round. However, this consensus-based design faces several limitations. First, multiple rounds of communication increases token overhead and limits scalability. Second, due to the inherent conformity of LLMs, agents that initially produce correct responses may be influenced by incorrect ones during the debate process, causing error propagation. Third, majority voting introduces randomness and unfairness in the decision-making phase, and can degrade the reasoning performance. To address these issues, we propose Free-MAD, an alternative and novel MAD framework that eliminates the need for consensus among agents. Free-MAD introduces a novel score-based decision mechanism that evaluates the entire debate trajectory rather than relying on the last round only. This mechanism tracks how each agent’s reasoning evolves, enabling more accurate and fair outcomes. In addition, Free-MAD reconstructs the debate phase by introducing anti-conformity, a mechanism that enables agents to mitigate excessive influence from the majority. Experiments on eight benchmark datasets demonstrate that Free-MAD significantly improves reasoning performance while requiring only a single-round debate and thus reducing token costs. We also show that compared to existing MAD approaches, Free-MAD exhibits improved robustness in real-world attack scenarios.
Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve. In practice, RL progress often slows when task difficulty becomes poorly aligned with model capability or when training is dominated by a narrow set of recurring problem patterns.To jointly address these issues, we propose SCALER (Synthetic sCalable Adaptive Learning Environment for Reasoning), a framework that sustains effective learning signals through adaptive environment design.SCALER introduces a scalable synthesis pipeline that converts real-world programming problems into verifiable reasoning environments with controllable difficulty and unbounded instance generation, enabling RL training beyond finite datasets while preserving strong correctness guarantees. Building on this, SCALER further employs an adaptive multi-environment RL strategy that dynamically adjusts instance difficulty and curates the active set of environments to track the model’s capability frontier and maintain distributional diversity. This co-adaptation prevents reward sparsity, mitigates overfitting to narrow task patterns, and supports sustained improvement throughout training. Extensive experiments show that SCALER consistently outperforms other RL baselines across diverse reasoning benchmarks and exhibits more stable, long-horizon training dynamics.
Prompt tuning has achieved remarkable progress in vision–language models (VLMs) and is recently being adopted for audio–language models (ALMs). However, its generalization ability in ALMs remains largely underexplored. We observe that conventional prompt tuning for ALMs also suffers from the Base–New Tradeoff, and we identify that this issue stems from the disrupted semantic structure of the embedding space. To address this issue, we propose Semantically Expanded Prompt Tuning (SEPT)—a plug-and-play framework that explicitly regularizes the prompt embedding space by incorporating semantic neighbors generated by large language models. SEPT introduces a novel semantic expansion loss with margin constraints that promote intra-class compactness and inter-class separability, thereby enhancing the semantic structure of the prompt embedding space. For comprehensive evaluation, we establish the first benchmark setup for prompt generalization in ALMs, covering both base-to-new generalization and cross-dataset transferability. Extensive experiments demonstrate that SEPT consistently improves generalization performance across multiple prompt tuning baselines, while maintaining computational cost during inference.
The application of physics formulas is a fundamental human capability in numerical reasoning. While existing datasets often rely on implicit mathematical knowledge, they rarely explicitate the underlying formulas. To address this, we introduce FormulaReasoning, a new benchmark for formula-based numerical reasoning comprising 5,324 questions requiring calculations grounded in external physics principles. We provide high-quality, fine-grained annotations in English and Chinese—including formula structures, parameter names, symbols, values, and units—curated through manual effort and LLM-assisted validation. Additionally, we provide a consolidated formula database as an external knowledge source. To further challenge model performance, we develop an extended version of the dataset by coupling multiple questions. We evaluate various architectural and methodological frameworks, including retrieval-augmented methods, modular reasoning (formula generation, parameter extraction, and calculation), and preference-based optimization. Our analysis identifies critical challenges in formula-based reasoning, highlighting significant opportunities for future methodological advancement.
XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content
PDF ↗Large Language Models (LLMs) can generate content spanning ideological rhetoric to explicit instructions for violence. However, existing safety evaluations often rely on simplistic binary labels (safe/unsafe), overlooking the nuanced spectrum of risk these outputs pose. To address this, we present XGUARD, a benchmark and evaluation framework designed to assess the severity of extremist content generated by LLMs on a multi-level grading. It includes 3,840 red-teaming prompts generated using templates informed by real-world extremist scenarios from social media, forums, and news. The framework categorizes model responses into five danger levels (0–4) defined by degree of extremist endorsement, enabling nuanced analysis of failure frequency and severity. We introduce the interpretable Attack Severity Curve (ASC) to visualize vulnerabilities and compare defense mechanisms across threat intensities. Using XGUARD, we evaluate five popular LLMs and two lightweight defense strategies, revealing key insights into current safety gaps and trade-offs between robustness and expressive freedom. Our work underscores the value of graded safety metrics for building trustworthy LLMs. The code and dataset is available at https://github.com/Abishethvarman/XGUARD
TRUST: Towards Robust Social Bot Detection via Uncertainty-Guided Pseudo-Labeling and Graph Structure Purification
PDF ↗Social bots threaten online platforms by mimicking human behavior and forming deceptive connections, enabling the dissemination of misinformation while evading detection. Existing graph-based detection models leverage graph neural networks (GNNs) to capture relational structures and multimodal user features. However, such models are vulnerable to deceptive message propagation, where bots deliberately interact with legitimate users. These interactions create heterophilous edges–connections between nodes with different labels (i.e. human and bot)–which undermine the homophily assumption that connected users typically share similar characteristics. In this work, we propose a novel framework to mitigate deceptive message propagation through node-level uncertainty estimation and graph structure purification. The framework comprises three key components: (1) Node uncertainty estimation employs evidential deep learning with an error-sensitive uncertainty loss to obtain calibrated node-wise uncertainty; (2) Uncertainty-guided pseudo-label generation assigns pseudo-labels to low-uncertainty nodes using a dynamic threshold; (3) Graph structure purification selectively disconnects heterophilous edges identified between differently labeled nodes. Extensive experiments on three benchmark datasets and six GNN backbones demonstrate that our framework consistently enhances detection performance and serves as an effective general-purpose enhancement module for social bot detection.