A prompt is a natural language instruction that defines a specific task for a large language model (LLM) and serves as the primary interface for human-LLM interaction. With the growing deployment of LLMs, diverse prompt datasets are emerging from platforms such as GitHub and social media. These datasets span a wide array of applications and content types, facilitating both broader LLM utilization and improved prompt engineering. In this work, we--for the first time--have compiled an extensive list of prompt datasets sourced from various channels, representing a spectrum of downstream tasks, languages, engineering techniques, attributes, and modalities. We select key representative datasets for systematic analysis, revealing commonalities and differences in prompt construction across categories, distinguishing them from other text corpora like literature and web. We further propose a prompt optimization approach that leverages syntactic embeddings of part-of-speech and dependency structures. By identifying a centroid representation of prompts and guiding LLMs to rewrite prompts toward this centroid, our method improves the meaningfulness of model outputs. We have made our datasets and code available.

Current Chain-of-Thought (CoT) verification methods predict reasoning correctness based on outputs (black-box) or activations (gray-box), but offer limited insight into why a computation fails. We introduce a white-box method: Circuit-based Reasoning Verification (CRV). We hypothesize that attribution graphs of correct CoT steps, viewed as execution traces of the model's latent reasoning circuits, possess distinct structural fingerprints from those of incorrect steps. By training a classifier on structural features of these graphs, we show that these traces contain a powerful signal of reasoning errors. Our white-box approach yields novel scientific insights unattainable by other methods. (1) We demonstrate that structural signatures of error are highly predictive, establishing the viability of verifying reasoning directly via its computational graph. (2) We find these signatures to be highly domain-specific, revealing that failures in different reasoning tasks manifest as distinct computational patterns. (3) We provide evidence that these signatures are not merely correlational; by using our analysis to guide targeted interventions on individual transcoder features, we successfully correct the model's faulty reasoning. Our work shows that, by scrutinizing a model's computational process, we can move from simple error detection to a deeper, causal understanding of LLM reasoning.

Geometric reasoning remains a core challenge for Multimodal Large Language Models (MLLMs). Even the most advanced closed-source systems, such as GPT-O3 and Gemini-2.5-Pro, still struggle to solve geometry problems reliably, despite exhibiting strong textual reasoning abilities on tasks like the International Mathematical Olympiad (IMO). This gap suggests that the bottleneck lies in understanding geometric diagrams rather than reasoning itself. Since geometric figures can often be faithfully described in concise textual form, converting visual content into captions offers a promising direction. Motivated by this insight, we introduce CapGeo, a caption-assisted reasoning framework that bridges visual and textual modalities. Experiments show substantial improvements when models are equipped with captions: Qwen2.5-VL-72B improves from 8.6% (vision-only) to 59.0%, while Claude-Opus-4 rises from 44.8% to 73.0%. To systematically evaluate and identify high-quality geometric captioning models, we further propose CapGeo-Bench, a dataset of 4,641 curated figure-caption pairs. Crucially, CapGeo-Bench incorporates a keypoint-based evaluation metric that correlates strongly with downstream CapGeo performance, enabling reliable assessment of geometric captioning ability. Together, our framework and benchmark highlight a new pathway toward advancing geometric reasoning in MLLMs.

Reliable evaluation is fundamental to the progress of Large Language Models (LLMs), yet the evaluation process during pre-training is plagued by significant instability that obscures true learning dynamics. In this work, we systematically diagnose this instability, attributing it to two distinct sources: \textit{Parameter Instability} from training stochasticity and \textit{Evaluation Instability} from noisy measurement protocols. To counteract both sources of noise, we introduce \textbf{MaP}, a dual-pronged framework that synergistically integrates checkpoint \underline{M}erging \underline{a}nd the \underline{P}ass@k metric. Checkpoint merging smooths the parameter space by averaging recent model weights, while Pass@k provides a robust, low-variance statistical estimate of model capability. Extensive experiments show that MaP yields significantly smoother performance curves, reduces inter-run variance, and ensures more consistent model rankings. Ultimately, MaP provides a more reliable and faithful lens for observing LLM training dynamics, laying a crucial empirical foundation for LLM research.

Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky. While it may improve accuracy, we observe it often degrades reasoning quality such as logical consistency. Existing solutions to supervise reasoning, such as large-scale Process Reward Models (PRMs), are prohibitively expensive. To address this, we propose CLARity, a cost-effective RL framework that enhances reasoning quality using only a small, general-purpose LLM. CLARity integrates a consistency-aware reward mechanism with a 2-stage refine-then-monitor training pipeline to enhance reasoning consistency, and a dynamic data reformulation strategy to to better exploit limited data. Experiments demonstrate that CLARity improves response consistency by 16.5% and accuracy by 7.5% over baselines. Human evaluations further confirm holistic improvements in coherence and professionalism. Thus, CLARity offers a generalizable solution that enables smaller models to effectively guide expert models by reasoning consistency.Our code is open sourced at: https://github.com/Infinite-set/CLARity

Medical diagnostics is a high-stakes and complex domain that is critical to patient care. However, current evaluations of large language models (LLMs) are fundamentally misaligned with real-world clinical practice. Most of them rely on static benchmarks derived from public medical exam items, which tend to overestimate model performance and ignore the difference between textbook cases and the ambiguous, varying conditions in the real world. Recent efforts toward dynamic evaluation offer a promising alternative, but their improvements are limited to superficial perturbations and a narrow focus on accuracy. To address these gaps, we propose DyReMe, a dynamic benchmark for medical diagnostics that better reflects real clinical practice. Unlike static exam-style questions, DyReMe generates fresh, consultation-like cases that introduce distractors such as differential diagnoses and common misdiagnosis factors. It also varies expression styles to mimic diverse real-world query habits. Beyond accuracy, DyReMe evaluates LLMs on three additional clinically relevant dimensions: veracity, helpfulness, and consistency. Our experiments demonstrate that this dynamic approach yields more challenging and realistic assessments, revealing significant misalignments between the performance of state-of-the-art LLMs and real clinical practice. These findings highlight the urgent need for evaluation frameworks that better reflect the demands of trustworthy medical diagnostics.

Effectiveness of speech emotion recognition in real-world scenarios is often hindered by noisy environments and variability across datasets. This paper introduces a two-step approach to enhance the robustness and generalization of speech emotion recognition models through improved representation learning. First, our model employs EDRL (Emotion-Disentangled Representation Learning) to extract class-specific discriminative features while preserving shared similarities across emotion categories. Next, MEA (Multiblock Embedding Alignment) refines these representations by projecting them into a joint discriminative latent subspace that maximizes covariance with the original speech input. The learned EDRL-MEA embeddings are subsequently used to train an emotion classifier using clean samples from publicly available datasets, and are evaluated on unseen noisy and cross-corpus speech samples. Improved performance under these challenging conditions demonstrates the effectiveness of the proposed method.

Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify context management as the central bottleneck -- extended histories cause agents to overlook critical evidence or become distracted by irrelevant information, thus failing to replan or reflect from previous mistakes. To address this, we propose COMPASS (Context-Organized Multi-Agent Planning and Strategy System), a lightweight hierarchical framework that separates tactical execution, strategic oversight, and context organization into three specialized components: (1) a Main Agent that performs reasoning and tool use, (2) a Meta-Thinker that monitors progress and issues strategic interventions, and (3) a Context Manager that maintains concise, relevant progress briefs for different reasoning stages. Across three challenging benchmarks -- GAIA, BrowseComp, and Humanity's Last Exam -- COMPASS improves accuracy by up to 20% relative to both single- and multi-agent baselines. We further introduce a test-time scaling extension that elevates performance to match established DeepResearch agents, and a post-training pipeline that delegates context management to smaller models for enhanced efficiency.

Large Vision-Language Models (LVLMs) with only 7B parameters have shown promise as automated judges in chart comprehension tasks. However, tiny models (<=2B parameters) still perform poorly as judges, limiting their real-world use in resource-constrained settings. To address this, we propose two approaches to ensure cost-efficient evaluation: (i) multi-criteria prompting, which combines separate evaluation criteria into a single query, and (ii) domain-adaptive transfer learning, in which we fine-tune a 2B-parameter LVLM on synthetic judgments in a chart dataset to create the ChartJudge. Experiments show that multi-criteria prompting exposes robustness gaps, which led to a huge drop in performance for 7B models, including specialized LVLM judges like LLaVA-Critic. In addition, we find that our tiny LVLM (ChartJudge) can effectively transfer knowledge from one dataset to another to make it a more specialized model. Our fine-grained analysis across chart types and query complexities offers actionable insights into trade-offs between model size, prompt design, and transferability, enabling scalable, low-cost evaluation for chart reasoning tasks.

Artificial Intelligence (AI) is starting to transform the research process as we know it by automating the discovery of new solutions. Given a task, the typical AI-driven approach is (i) to generate a set of diverse solutions, and then (ii) to verify these solutions and select one that solves the problem. Crucially, this approach assumes the existence of a reliable verifier, i.e., one that can accurately determine whether a solution solves the given problem. We argue that systems research, long focused on designing and evaluating new performance-oriented algorithms, is particularly well-suited for AI-driven solution discovery. This is because system performance problems naturally admit reliable verifiers: solutions are typically implemented in real systems or simulators, and verification reduces to running these software artifacts against predefined workloads and measuring performance. We term this approach as AI-Driven Research for Systems (ADRS), which iteratively generates, evaluates, and refines solutions. Using penEvolve, an existing open-source ADRS instance, we present case studies across diverse domains, including load balancing for multi-region cloud scheduling, Mixture-of-Experts inference, LLM-based SQL queries, and transaction scheduling. In multiple instances, ADRS discovers algorithms that outperform state-of-the-art human designs (e.g., achieving up to 5.0x runtime improvements or 50% cost reductions). We distill best practices for guiding algorithm evolution, from prompt design to evaluator construction, for existing frameworks. We then discuss the broader implications for the systems community: as AI assumes a central role in algorithm design, we argue that human researchers will increasingly focus on problem formulation and strategic guidance. Our results highlight both the disruptive potential and the urgent need to adapt systems research practices in the age of AI.