Accurate differentiation of brain tumor types on magnetic resonance imaging (MRI) is critical for guiding treatment planning in neuro-oncology. Recent advances in large language models (LLMs) have enabled visual question answering (VQA) approaches that integrate image interpretation with natural language reasoning. In this study, we evaluated GPT-4o, GPT-5-nano, GPT-5-mini, and GPT-5 on a curated brain tumor VQA benchmark derived from 3 Brain Tumor Segmentation (BraTS) datasets - glioblastoma (GLI), meningioma (MEN), and brain metastases (MET). Each case included multi-sequence MRI triplanar mosaics and structured clinical features transformed into standardized VQA items. Models were assessed in a zero-shot chain-of-thought setting for accuracy on both visual and reasoning tasks. Results showed that GPT-5-mini achieved the highest macro-average accuracy (44.19%), followed by GPT-5 (43.71%), GPT-4o (41.49%), and GPT-5-nano (35.85%). Performance varied by tumor subtype, with no single model dominating across all cohorts. These findings suggest that GPT-5 family models can achieve moderate accuracy in structured neuro-oncological VQA tasks, but not at a level acceptable for clinical use.
Real-world multimodal applications often require any-to-any capabilities, enabling both understanding and generation across modalities including text, image, audio, and video. However, integrating the strengths of autoregressive language models (LLMs) for reasoning and diffusion models for high-fidelity generation remains challenging. Existing approaches rely on rigid pipelines or tightly coupled architectures, limiting flexibility and scalability. We propose MAGUS (Multi-Agent Guided Unified Multimodal System), a modular framework that unifies multimodal understanding and generation via two decoupled phases: Cognition and Deliberation. MAGUS enables symbolic multi-agent collaboration within a shared textual workspace. In the Cognition phase, three role-conditioned multimodal LLM agents - Perceiver, Planner, and Reflector - engage in collaborative dialogue to perform structured understanding and planning. The Deliberation phase incorporates a Growth-Aware Search mechanism that orchestrates LLM-based reasoning and diffusion-based generation in a mutually reinforcing manner. MAGUS supports plug-and-play extensibility, scalable any-to-any modality conversion, and semantic alignment - all without the need for joint training. Experiments across multiple benchmarks, including image, video, and audio generation, as well as cross-modal instruction following, demonstrate that MAGUS outperforms strong baselines and state-of-the-art systems. Notably, on the MME benchmark, MAGUS surpasses the powerful closed-source model GPT-4o.
Evaluating large language models (LLMs) in complex decision-making is essential for advancing AI's ability for strategic planning and real-time adaptation. However, existing benchmarks for tasks like StarCraft II fail to capture the game's full complexity, such as its complete game context, diverse action spaces, and all playable races. To address this gap, we present SC2Arena, a benchmark that fully supports all playable races, low-level action spaces, and optimizes text-based observations to tackle spatial reasoning challenges. Complementing this, we introduce StarEvolve, a hierarchical framework that integrates strategic planning with tactical execution, featuring iterative self-correction and continuous improvement via fine-tuning on high-quality gameplay data. Its key components include a Planner-Executor-Verifier structure to break down gameplay, and a scoring system for selecting high-quality training samples. Comprehensive analysis using SC2Arena provides valuable insights into developing generalist agents that were not possible with previous benchmarks. Experimental results also demonstrate that our proposed StarEvolve achieves superior performance in strategic planning. Our code, environment, and algorithms are publicly available.
Large language models (LLMs) excel at solving problems with clear and complete statements, but often struggle with nuanced environments or interactive tasks which are common in most real-world scenarios. This highlights the critical need for developing LLMs that can effectively engage in logically consistent multi-turn dialogue, seek information and reason with incomplete data. To this end, we introduce a novel benchmark comprising a suite of multi-turn tasks each designed to test specific reasoning, interactive dialogue, and information-seeking abilities. These tasks have deterministic scoring mechanisms, thus eliminating the need for human intervention. Evaluating frontier models on our benchmark reveals significant headroom. Our analysis shows that most errors emerge from poor instruction following, reasoning failures, and poor planning. This benchmark provides valuable insights into the strengths and weaknesses of current LLMs in handling complex, interactive scenarios and offers a robust platform for future research aimed at improving these critical capabilities.
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, including programming, planning, and decision-making. However, their performance often degrades when faced with highly complex problem instances that require deep reasoning over long horizons. In such cases, direct problem-solving approaches can lead to inefficiency or failure due to the lack of structured intermediate guidance. To address this, we propose a novel self-evolve framework, EvoCurr, in which a dedicated curriculum-generation LLM constructs a sequence of problem instances with gradually increasing difficulty, tailored to the solver LLM's learning progress. The curriculum dynamically adapts easing challenges when the solver struggles and escalating them when success is consistent, thus maintaining an optimal learning trajectory. This approach enables the solver LLM, implemented as a code-generation model producing Python decision-tree scripts, to progressively acquire the skills needed for complex decision-making tasks. Experimental results on challenging decision-making benchmarks show that our method significantly improves task success rates and solution efficiency compared to direct-solving baselines. These findings suggest that LLM-driven curriculum learning holds strong potential for enhancing automated reasoning in real-world, high-complexity domains.
This Innovative Practice full paper explores how Large Language Models (LLMs) can enhance the teaching of code refactoring in software engineering courses through real-time, context-aware feedback. Refactoring improves code quality but is difficult to teach, especially with complex, real-world codebases. Traditional methods like code reviews and static analysis tools offer limited, inconsistent feedback. Our approach integrates LLM-assisted refactoring into a course project using structured prompts to help students identify and address code smells such as long methods and low cohesion. Implemented in Spring 2025 in a long-lived OSS project, the intervention is evaluated through student feedback and planned analysis of code quality improvements. Findings suggest that LLMs can bridge theoretical and practical learning, supporting a deeper understanding of maintainability and refactoring principles.
SQL query rewriting aims to reformulate a query into a more efficient form while preserving equivalence. Most existing methods rely on predefined rewrite rules. However, such rule-based approaches face fundamental limitations: (1) fixed rule sets generalize poorly to novel query patterns and struggle with complex queries; (2) a wide range of effective rewriting strategies cannot be fully captured by declarative rules. To overcome these issues, we propose using large language models (LLMs) to generate rewrites. LLMs can capture complex strategies, such as evaluation reordering and CTE rewriting. Despite this potential, directly applying LLMs often results in suboptimal or non-equivalent rewrites due to a lack of execution awareness and semantic grounding. To address these challenges, We present E3-Rewrite, an LLM-based SQL rewriting framework that produces executable, equivalent, and efficient queries. It integrates two core components: a context construction module and a reinforcement learning framework. First, the context module leverages execution plans and retrieved demonstrations to build bottleneck-aware prompts that guide inference-time rewriting. Second, we design a reward function targeting executability, equivalence, and efficiency, evaluated via syntax checks, equivalence verification, and cost estimation. Third, to ensure stable multi-objective learning, we adopt a staged curriculum that first emphasizes executability and equivalence, then gradually incorporates efficiency. Extensive experiments show that E3-Rewrite achieves up to a 25.6\% reduction in query execution time compared to state-of-the-art methods across multiple SQL benchmarks. Moreover, it delivers up to 24.4\% more successful rewrites, expanding coverage to complex queries that previous systems failed to handle.
Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role adherence, and procedural integrity. This paper introduces Intrinsic Memory Agents, a novel framework that addresses these limitations through structured agent-specific memories that evolve intrinsically with agent outputs. Specifically, our method maintains role-aligned memory templates that preserve specialized perspectives while focusing on task-relevant information. We benchmark our approach on the PDDL dataset, comparing its performance to existing state-of-the-art multi-agentic memory approaches and showing an improvement of 38.6\% with the highest token efficiency. An additional evaluation is performed on a complex data pipeline design task, we demonstrate that our approach produces higher quality designs when comparing 5 metrics: scalability, reliability, usability, cost-effectiveness and documentation with additional qualitative evidence of the improvements. Our findings suggest that addressing memory limitations through structured, intrinsic approaches can improve the capabilities of multi-agent LLM systems on structured planning tasks.
Natural head rotation is critical for believable embodied virtual agents, yet this micro-level behavior remains largely underexplored. While head-rotation prediction algorithms could, in principle, reproduce this behavior, they typically focus on visually salient stimuli and overlook the cognitive motives that guide head rotation. This yields agents that look at conspicuous objects while overlooking obstacles or task-relevant cues, diminishing realism in a virtual environment. We introduce SCORE, a Symbolic Cognitive Reasoning framework for Embodied Head Rotation, a data-agnostic framework that produces context-aware head movements without task-specific training or hand-tuned heuristics. A controlled VR study (N=20) identifies five motivational drivers of human head movements: Interest, Information Seeking, Safety, Social Schema, and Habit. SCORE encodes these drivers as symbolic predicates, perceives the scene with a Vision-Language Model (VLM), and plans head poses with a Large Language Model (LLM). The framework employs a hybrid workflow: the VLM-LLM reasoning is executed offline, after which a lightweight FastVLM performs online validation to suppress hallucinations while maintaining responsiveness to scene dynamics. The result is an agent that predicts not only where to look but also why, generalizing to unseen scenes and multi-agent crowds while retaining behavioral plausibility.
Recent advances in large language models have demonstrated strong reasoning and role-playing capabilities, opening new opportunities for agent-based social simulations. However, most existing agents' implementations are scenario-tailored, without a unified framework to guide the design. This lack of a general social agent limits their ability to generalize across different social contexts and to produce consistent, realistic behaviors. To address this challenge, we propose a theory-informed framework that provides a systematic design process for LLM-based social agents. Our framework is grounded in principles from Social Cognition Theory and introduces three key modules: motivation, action planning, and learning. These modules jointly enable agents to reason about their goals, plan coherent actions, and adapt their behavior over time, leading to more flexible and contextually appropriate responses. Comprehensive experiments demonstrate that our theory-driven agents reproduce realistic human behavior patterns under complex conditions, achieving up to 75% lower deviation from real-world behavioral data across multiple fidelity metrics compared to classical generative baselines. Ablation studies further show that removing motivation, planning, or learning modules increases errors by 1.5 to 3.2 times, confirming their distinct and essential contributions to generating realistic and coherent social behaviors.
We introduce GVGAI-LLM, a video game benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). Built on the General Video Game AI framework, it features a diverse collection of arcade-style games designed to test a model's ability to handle tasks that differ from most existing LLM benchmarks. The benchmark leverages a game description language that enables rapid creation of new games and levels, helping to prevent overfitting over time. Each game scene is represented by a compact set of ASCII characters, allowing for efficient processing by language models. GVGAI-LLM defines interpretable metrics, including the meaningful step ratio, step efficiency, and overall score, to assess model behavior. Through zero-shot evaluations across a broad set of games and levels with diverse challenges and skill depth, we reveal persistent limitations of LLMs in spatial reasoning and basic planning. Current models consistently exhibit spatial and logical errors, motivating structured prompting and spatial grounding techniques. While these interventions lead to partial improvements, the benchmark remains very far from solved. GVGAI-LLM provides a reproducible testbed for advancing research on language model capabilities, with a particular emphasis on agentic behavior and contextual reasoning.
We present LL3M, a multi-agent system that leverages pretrained large language models (LLMs) to generate 3D assets by writing interpretable Python code in Blender. We break away from the typical generative approach that learns from a collection of 3D data. Instead, we reformulate shape generation as a code-writing task, enabling greater modularity, editability, and integration with artist workflows. Given a text prompt, LL3M coordinates a team of specialized LLM agents to plan, retrieve, write, debug, and refine Blender scripts that generate and edit geometry and appearance. The generated code works as a high-level, interpretable, human-readable, well-documented representation of scenes and objects, making full use of sophisticated Blender constructs (e.g. B-meshes, geometry modifiers, shader nodes) for diverse, unconstrained shapes, materials, and scenes. This code presents many avenues for further agent and human editing and experimentation via code tweaks or procedural parameters. This medium naturally enables a co-creative loop in our system: agents can automatically self-critique using code and visuals, while iterative user instructions provide an intuitive way to refine assets. A shared code context across agents enables awareness of previous attempts, and a retrieval-augmented generation knowledge base built from Blender API documentation, BlenderRAG, equips agents with examples, types, and functions empowering advanced modeling operations and code correctness. We demonstrate the effectiveness of LL3M across diverse shape categories, style and material edits, and user-driven refinements. Our experiments showcase the power of code as a generative and interpretable medium for 3D asset creation. Our project page is at https://threedle.github.io/ll3m.
Spoken Language Models (SLMs), which extend Large Language Models (LLMs) to perceive speech inputs, have gained increasing attention for their potential to advance speech understanding tasks. However, despite recent progress, studies show that SLMs often struggle to generalize across datasets, even for trained languages and tasks, raising concerns about whether they process speech in a text-like manner as intended. A key challenge underlying this limitation is the modality gap between speech and text representations. The high variability in speech embeddings may allow SLMs to achieve strong in-domain performance by exploiting unintended speech variations, ultimately hindering generalization. To mitigate this modality gap, we introduce Optimal Transport Regularization (OTReg), a method that formulates speech-text alignment as an optimal transport problem and derives a regularization loss to improve SLM training. In each training iteration, OTReg first establishes a structured correspondence between speech and transcript embeddings by determining the optimal transport plan, then incorporates the regularization loss based on this transport plan to optimize SLMs in generating speech embeddings that align more effectively with transcript embeddings. OTReg is lightweight, requiring no additional labels or learnable parameters, and integrates seamlessly into existing SLM training procedures. Extensive multilingual ASR experiments demonstrate that OTReg enhances speech-text alignment, mitigates the modality gap, and consequently improves SLM generalization across diverse datasets.
Indoor navigation remains a complex challenge due to the absence of reliable GPS signals and the architectural intricacies of large enclosed environments. This study presents an indoor localization and navigation approach that integrates vision-based localization with large language model (LLM)-based navigation. The localization system utilizes a ResNet-50 convolutional neural network fine-tuned through a two-stage process to identify the user's position using smartphone camera input. To complement localization, the navigation module employs an LLM, guided by a carefully crafted system prompt, to interpret preprocessed floor plan images and generate step-by-step directions. Experimental evaluation was conducted in a realistic office corridor with repetitive features and limited visibility to test localization robustness. The model achieved high confidence and an accuracy of 96% across all tested waypoints, even under constrained viewing conditions and short-duration queries. Navigation tests using ChatGPT on real building floor maps yielded an average instruction accuracy of 75%, with observed limitations in zero-shot reasoning and inference time. This research demonstrates the potential for scalable, infrastructure-free indoor navigation using off-the-shelf cameras and publicly available floor plans, particularly in resource-constrained settings like hospitals, airports, and educational institutions.
From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search agents powered by LLMs offer a promising solution to liberate humans from this tedious work. However, the capability of these agents to perform such "wide-context" collection reliably and completely remains largely unevaluated due to a lack of suitable benchmarks. To bridge this gap, we introduce WideSearch, a new benchmark engineered to evaluate agent reliability on these large-scale collection tasks. The benchmark features 200 manually curated questions (100 in English, 100 in Chinese) from over 15 diverse domains, grounded in real user queries. Each task requires agents to collect large-scale atomic information, which could be verified one by one objectively, and arrange it into a well-organized output. A rigorous five-stage quality control pipeline ensures the difficulty, completeness, and verifiability of the dataset. We benchmark over 10 state-of-the-art agentic search systems, including single-agent, multi-agent frameworks, and end-to-end commercial systems. Most systems achieve overall success rates near 0\%, with the best performer reaching just 5\%. However, given sufficient time, cross-validation by multiple human testers can achieve a near 100\% success rate. These results demonstrate that present search agents have critical deficiencies in large-scale information seeking, underscoring urgent areas for future research and development in agentic search. Our dataset, evaluation pipeline, and benchmark results have been publicly released at https://widesearch-seed.github.io/
Large Language Model (LLM) agentic systems are software systems powered by LLMs that autonomously reason, plan, and execute multi-step workflows to achieve human goals, rather than merely executing predefined steps. During execution, these workflows frequently encounter exceptions. Existing exception handling solutions often treat exceptions superficially, failing to trace execution-phase exceptions to their reasoning-phase root causes. Furthermore, their recovery logic is brittle, lacking structured escalation pathways when initial attempts fail. To tackle these challenges, we first present a comprehensive taxonomy of 36 exception types across 12 agent artifacts. Building on this, we propose SHIELDA (Structured Handling of Exceptions in LLM-Driven Agentic Workflows), a modular runtime exception handling framework for LLM agentic workflows. SHIELDA uses an exception classifier to select a predefined exception handling pattern from a handling pattern registry. These patterns are then executed via a structured handling executor, comprising local handling, flow control, and state recovery, to enable phase-aware recovery by linking exceptions to their root causes and facilitating composable strategies. We validate SHIELDA's effectiveness through a case study on the AutoPR agent, demonstrating effective, cross-phase recovery from a reasoning-induced exception.
Accurate detection and classification of diverse door types in floor plans drawings is critical for multiple applications, such as building compliance checking, and indoor scene understanding. Despite their importance, publicly available datasets specifically designed for fine-grained multi-class door detection remain scarce. In this work, we present a semi-automated pipeline that leverages a state-of-the-art object detector and a large language model (LLM) to construct a multi-class door detection dataset with minimal manual effort. Doors are first detected as a unified category using a deep object detection model. Next, an LLM classifies each detected instance based on its visual and contextual features. Finally, a human-in-the-loop stage ensures high-quality labels and bounding boxes. Our method significantly reduces annotation cost while producing a dataset suitable for benchmarking neural models in floor plan analysis. This work demonstrates the potential of combining deep learning and multimodal reasoning for efficient dataset construction in complex real-world domains.
Transformer-based models primarily rely on Next Token Prediction (NTP), which predicts the next token in a sequence based on the preceding context. However, NTP's focus on single-token prediction often limits a model's ability to plan ahead or maintain long-range coherence, raising questions about how well LLMs can predict longer contexts, such as full sentences within structured documents. While NTP encourages local fluency, it provides no explicit incentive to ensure global coherence across sentence boundaries-an essential skill for reconstructive or discursive tasks. To investigate this, we evaluate three commercial LLMs (GPT-4o, Claude 3.5 Sonnet, and Gemini 2.0 Flash) on Masked Sentence Prediction (MSP) - the task of infilling a randomly removed sentence - from three domains: ROCStories (narrative), Recipe1M (procedural), and Wikipedia (expository). We assess both fidelity (similarity to the original sentence) and cohesiveness (fit within the surrounding context). Our key finding reveals that commercial LLMs, despite their superlative performance in other tasks, are poor at predicting masked sentences in low-structured domains, highlighting a gap in current model capabilities.
Equipped with Large Language Models (LLMs), human-centered robots are now capable of performing a wide range of tasks that were previously deemed challenging or unattainable. However, merely completing tasks is insufficient for cognitive robots, who should learn and apply human preferences to future scenarios. In this work, we propose a framework that combines human preferences with physical constraints, requiring robots to complete tasks while considering both. Firstly, we developed a benchmark of everyday household activities, which are often evaluated based on specific preferences. We then introduced In-Context Learning from Human Feedback (ICLHF), where human feedback comes from direct instructions and adjustments made intentionally or unintentionally in daily life. Extensive sets of experiments, testing the ICLHF to generate task plans and balance physical constraints with preferences, have demonstrated the efficiency of our approach.
Given recent breakthroughs in Generative Artificial Intelligence (GAI) and Large Language Models (LLMs), more and more professional services are being augmented through Artificial Intelligence (AI), which once seemed impossible to automate. This paper presents a modular model for leveraging GAI in developing strategic plans for large scale government organizations and evaluates leading machine learning techniques in their application towards one of the identified modules. Specifically, the performance of BERTopic and Non-negative Matrix Factorization (NMF) are evaluated in their ability to use topic modeling to generate themes representative of Vision Elements within a strategic plan. To accomplish this, BERTopic and NMF models are trained using a large volume of reports from the Government Accountability Office (GAO). The generated topics from each model are then scored for similarity against the Vision Elements of a published strategic plan and the results are compared. Our results show that these techniques are capable of generating themes similar to 100% of the elements being evaluated against. Further, we conclude that BERTopic performs best in this application with more than half of its correlated topics achieving a "medium" or "strong" correlation. A capability of GAI-enabled strategic plan development impacts a multi-billion dollar industry and assists the federal government in overcoming regulatory requirements which are crucial to the public good. Further work will focus on the operationalization of the concept proven in this study as well as viability of the remaining modules in the proposed model for GAI-generated strategic plans.
The complexity of modern bioinformatics analysis has created a critical gap between data generation and developing scientific insights. While large language models (LLMs) have shown promise in scientific reasoning, they remain fundamentally limited when dealing with real-world analytical workflows that demand iterative computation, tool integration and rigorous validation. We introduce K-Dense Analyst, a hierarchical multi-agent system that achieves autonomous bioinformatics analysis through a dual-loop architecture. K-Dense Analyst, part of the broader K-Dense platform, couples planning with validated execution using specialized agents to decompose complex objectives into executable, verifiable tasks within secure computational environments. On BixBench, a comprehensive benchmark for open-ended biological analysis, K-Dense Analyst achieves 29.2% accuracy, surpassing the best-performing language model (GPT-5) by 6.3 percentage points, representing nearly 27% improvement over what is widely considered the most powerful LLM available. Remarkably, K-Dense Analyst achieves this performance using Gemini 2.5 Pro, which attains only 18.3% accuracy when used directly, demonstrating that our architectural innovations unlock capabilities far beyond the underlying model's baseline performance. Our insights demonstrate that autonomous scientific reasoning requires more than enhanced language models, it demands purpose-built systems that can bridge the gap between high-level scientific objectives and low-level computational execution. These results represent a significant advance toward fully autonomous computational biologists capable of accelerating discovery across the life sciences.
Large Language Models (LLMs) have shown promise in automating code generation and software engineering tasks, yet they often struggle with complex, multi-file projects due to context limitations and knowledge gaps. We propose a novel context engineering workflow that combines multiple AI components: an Intent Translator (GPT-5) for clarifying user requirements, an Elicit-powered semantic literature retrieval for injecting domain knowledge, NotebookLM-based document synthesis for contextual understanding, and a Claude Code multi-agent system for code generation and validation. Our integrated approach leverages intent clarification, retrieval-augmented generation, and specialized sub-agents orchestrated via Claude's agent framework. We demonstrate that this method significantly improves the accuracy and reliability of code assistants in real-world repositories, yielding higher single-shot success rates and better adherence to project context than baseline single-agent approaches. Qualitative results on a large Next.js codebase show the multi-agent system effectively plans, edits, and tests complex features with minimal human intervention. We compare our system with recent frameworks like CodePlan, MASAI, and HyperAgent, highlighting how targeted context injection and agent role decomposition lead to state-of-the-art performance. Finally, we discuss the implications for deploying LLM-based coding assistants in production, along with lessons learned on context management and future research directions.
Digital Twins (DTs) offer powerful tools for managing complex infrastructure systems, but their effectiveness is often limited by challenges in integrating unstructured knowledge. Recent advances in Large Language Models (LLMs) bring new potential to address this gap, with strong abilities in extracting and organizing diverse textual information. We therefore propose LSDTs (LLM-Augmented Semantic Digital Twins), a framework that helps LLMs extract planning knowledge from unstructured documents like environmental regulations and technical guidelines, and organize it into a formal ontology. This ontology forms a semantic layer that powers a digital twin-a virtual model of the physical system-allowing it to simulate realistic, regulation-aware planning scenarios. We evaluate LSDTs through a case study of offshore wind farm planning in Maryland, including its application during Hurricane Sandy. Results demonstrate that LSDTs support interpretable, regulation-aware layout optimization, enable high-fidelity simulation, and enhance adaptability in infrastructure planning. This work shows the potential of combining generative AI with digital twins to support complex, knowledge-driven planning tasks.
Deep-Research agents, which integrate large language models (LLMs) with search tools, have shown success in improving the effectiveness of handling complex queries that require iterative search planning and reasoning over search results. Evaluations on current benchmarks like BrowseComp relies on black-box live web search APIs, have notable limitations in (1) fairness: dynamic and opaque web APIs hinder fair comparisons and reproducibility of deep research methods; (2) transparency: lack of control over the document corpus makes it difficult to isolate retriever contributions. In other words, the current evaluations may compare a complete deep research system at a given time, but they do not foster well-controlled experiments to provide insights into the capability of underlying deep research LLMs. To address these challenges, we introduce BrowseComp-Plus, a benchmark derived from BrowseComp, employing a fixed, carefully curated corpus. Each query in BrowseComp-Plus includes human-verified supporting documents and mined challenging negatives, enabling controlled experimentation. The benchmark is shown to be effective in distinguishing the performance of deep research systems. For instance, the open-source model Search-R1, when paired with the BM25 retriever, achieves 3.86% accuracy, whereas the GPT-5 achieves 55.9%. Integrating the GPT-5 with the Qwen3-Embedding-8B retriever further enhances its accuracy to 70.1% with fewer search calls. This benchmark allows comprehensive evaluation and disentangled analysis of deep research agents and retrieval methods, fostering insights into retrieval effectiveness, citation accuracy, and context engineering in Deep-Research system.
Large Language Models (LLMs) have been widely deployed in reasoning, planning, and decision-making tasks, making their trustworthiness a critical concern. The potential for intentional deception, where an LLM deliberately fabricates or conceals information to serve a hidden objective, remains a significant and underexplored threat. Existing studies typically induce such deception by explicitly setting a "hidden" objective through prompting or fine-tuning, which may not fully reflect real-world human-LLM interactions. Moving beyond this human-induced deception, we investigate LLMs' self-initiated deception on benign prompts. To address the absence of ground truth in this evaluation, we propose a novel framework using "contact searching questions." This framework introduces two statistical metrics derived from psychological principles to quantify the likelihood of deception. The first, the Deceptive Intention Score, measures the model's bias towards a hidden objective. The second, Deceptive Behavior Score, measures the inconsistency between the LLM's internal belief and its expressed output. Upon evaluating 14 leading LLMs, we find that both metrics escalate as task difficulty increases, rising in parallel for most models. Building on these findings, we formulate a mathematical model to explain this behavior. These results reveal that even the most advanced LLMs exhibit an increasing tendency toward deception when handling complex problems, raising critical concerns for the deployment of LLM agents in complex and crucial domains.
Large Language Models (LLMs) have recently demonstrated impressive action sequence prediction capabilities but often struggle with dynamic, long-horizon tasks such as real-time strategic games. In a game such as StarCraftII (SC2), agents need to manage resource constraints and adapt to evolving battlefield situations in a partially observable environment. This often overwhelms exisiting LLM-based approaches. To address these challenges, we propose a hierarchical multi-agent framework that employs specialized imitation learning agents under a meta-controller called Strategic Planner (SP). By expert demonstrations, each specialized agent learns a distinctive strategy, such as aerial support or defensive maneuvers, and produces coherent, structured multistep action sequences. The SP then orchestrates these proposals into a single, environmentally adaptive plan that ensures local decisions aligning with long-term strategies. We call this HIMA (Hierarchical Imitation Multi-Agent). We also present TEXTSCII-ALL, a comprehensive SC2 testbed that encompasses all race match combinations in SC2. Our empirical results show that HIMA outperforms state of the arts in strategic clarity, adaptability, and computational efficiency, underscoring the potential of combining specialized imitation modules with meta-level orchestration to develop more robust, general-purpose AI agents.
Large language models (LLMs) have demonstrated remarkable capabilities in code generation and structured reasoning; however, their performance often degrades on complex tasks that require consistent multi-step planning. Recent work has explored combining LLMs with Monte Carlo Tree Search (MCTS), yet existing approaches primarily focus on generating heuristic-based code for optimization or target simpler tasks where correctness alone is sufficient. In this work, we propose MCTS-OPS, a novel neural-symbolic framework that formulates prompt selection as a sequential decision process guided by MCTS. Our method explores and refines multi-step prompt sequences for the goal of improving code generation quality and enhancing the problem-solving capabilities of LLMs in general optimization. Experiments on network optimization show significant improvement over the baselines, both in the success rate of executing the generated code and in the optimization results with the specified objective and constraints (2$\sim$4$\times$ higher reward and 3$\times$ lower standard deviation). Moreover, it improves the chance of attaining the optimal solution by about 10\% of cases, compared to baseline methods in hard problems. These results highlight the promise of combining symbolic planning with LLMs for robust, high-quality code generation in complex domains.
Chain-of-Thought (CoT) reasoning has been widely adopted to enhance Large Language Models (LLMs) by decomposing complex tasks into simpler, sequential subtasks. However, extending CoT to vision-language reasoning tasks remains challenging, as it often requires interpreting transitions of visual states to support reasoning. Existing methods often struggle with this due to limited capacity of modeling visual state transitions or incoherent visual trajectories caused by fragmented architectures. To overcome these limitations, we propose Uni-CoT, a Unified Chain-of-Thought framework that enables coherent and grounded multimodal reasoning within a single unified model. The key idea is to leverage a model capable of both image understanding and generation to reason over visual content and model evolving visual states. However, empowering a unified model to achieve that is non-trivial, given the high computational cost and the burden of training. To address this, Uni-CoT introduces a novel two-level reasoning paradigm: A Macro-Level CoT for high-level task planning and A Micro-Level CoT for subtask execution. This design significantly reduces the computational overhead. Furthermore, we introduce a structured training paradigm that combines interleaved image-text supervision for macro-level CoT with multi-task objectives for micro-level CoT. Together, these innovations allow Uni-CoT to perform scalable and coherent multi-modal reasoning. Furthermore, thanks to our design, all experiments can be efficiently completed using only 8 A100 GPUs with 80GB VRAM each. Experimental results on reasoning-driven image generation benchmark (WISE) and editing benchmarks (RISE and KRIS) indicates that Uni-CoT demonstrates SOTA performance and strong generalization, establishing Uni-CoT as a promising solution for multi-modal reasoning. Project Page and Code: https://sais-fuxi.github.io/projects/uni-cot/
Participatory Budgeting (PB) empowers citizens to propose and vote on public investment projects. Yet, despite its democratic potential, PB initiatives often suffer from low participation rates, limiting their visibility and perceived legitimacy. In this work, we aim to strengthen PB elections in two key ways: by supporting project proposers in crafting better proposals, and by helping PB organizers manage large volumes of submissions in a transparent manner. We propose a privacy-preserving approach to predict which PB proposals are likely to be funded, using only their textual descriptions and anonymous historical voting records -- without relying on voter demographics or personally identifiable information. We evaluate the performance of GPT 4 Turbo in forecasting proposal outcomes across varying contextual scenarios, observing that the LLM's prior knowledge needs to be complemented by past voting data to obtain predictions reflecting real-world PB voting behavior. Our findings highlight the potential of AI-driven tools to support PB processes by improving transparency, planning efficiency, and civic engagement.
Large language models (LLMs) are beginning to reshape how chemists plan and run reactions in organic synthesis. Trained on millions of reported transformations, these text-based models can propose synthetic routes, forecast reaction outcomes and even instruct robots that execute experiments without human supervision. Here we survey the milestones that turned LLMs from speculative tools into practical lab partners. We show how coupling LLMs with graph neural networks, quantum calculations and real-time spectroscopy shrinks discovery cycles and supports greener, data-driven chemistry. We discuss limitations, including biased datasets, opaque reasoning and the need for safety gates that prevent unintentional hazards. Finally, we outline community initiatives open benchmarks, federated learning and explainable interfaces that aim to democratize access while keeping humans firmly in control. These advances chart a path towards rapid, reliable and inclusive molecular innovation powered by artificial intelligence and automation.