Modern code generation models exhibit longer outputs, accelerated capability growth, and changed training dynamics, rendering traditional training methodologies, algorithms, and datasets ineffective for improving their performance. To address these training bottlenecks, we propose MicroCoder-GRPO, an improved Group Relative Policy Optimization approach with three innovations: conditional truncation masking to improve long output potential while maintaining training stability, diversity-determined temperature selection to maintain and encourage output diversity, and removal of KL loss with high clipping ratios to facilitate solution diversity. MicroCoder-GRPO achieves up to 17.6

Computerized Adaptive Testing (CAT) has proven effective for efficient LLM evaluation on multiple-choice benchmarks, but modern LLM evaluation increasingly relies on generation tasks where outputs are scored continuously rather than marked correct/incorrect. We present a principled extension of IRT-based adaptive testing to continuous bounded scores (ROUGE, BLEU, LLM-as-a-Judge) by replacing the Bernoulli response distribution with a heteroskedastic normal distribution. Building on this, we introduce an uncertainty aware ranker with adaptive stopping criteria that achieves reliable model ranking while testing as few items and as cheaply as possible. We validate our method on five benchmarks spanning n-gram-based, embedding-based, and LLM-as-judge metrics. Our method uses 2

While confidence estimation is a promising direction for mitigating hallucinations in Large Language Models (LLMs), current research dominantly focuses on single-turn settings. The dynamics of model confidence in multi-turn conversations, where context accumulates and ambiguity is progressively resolved, remain largely unexplored. Reliable confidence estimation in multi-turn settings is critical for many downstream applications, such as autonomous agents and human-in-the-loop systems. This work presents the first systematic study of confidence estimation in multi-turn interactions, establishing a formal evaluation framework grounded in two key desiderata: per-turn calibration and monotonicity of confidence as more information becomes available. To facilitate this, we introduce novel metrics, including a length-normalized Expected Calibration Error (InfoECE), and a new "Hinter-Guesser" paradigm for generating controlled evaluation datasets. Our experiments reveal that widely-used confidence techniques struggle with calibration and monotonicity in multi-turn dialogues. We propose P(Sufficient), a logit-based probe that achieves comparatively better performance, although the task remains far from solved. Our work provides a foundational methodology for developing more reliable and trustworthy conversational agents.

Calibration evaluates whether a model confidence aligns with its empirical accuracy. Existing studies often compare the calibration of different large language models using global calibration metrics such as Expected Calibration Error and Brier Score. We begin by showing, both theoretically and empirically, that such comparisons are confounded by differences in model accuracy. For fairer cross-model comparison, we then propose ACE, an accuracy-controlled evaluation framework with three complementary views: Instance-Aligned, Distribution-Aligned, and Candidate-Aligned calibration. Across multiple benchmarks, model families, and confidence elicitation methods, we use ACE to study two practically important comparison axes, small versus large models and thinking versus non-thinking models. We find that many previously reported calibration advantages under raw global metrics weaken substantially after accuracy control. We also find that ranking reversal is frequent: models favored by raw metrics often cease to be favored once accuracy is controlled. Our results show that raw global calibration metrics are not robust for cross-model comparison, and that fair calibration comparison requires accuracy-aware evaluation.

Background: Event-based surveillance (EBS) systems use online news to complement traditional public health surveillance in early outbreak detection. Anomaly detection in EBS systems, however, generally fails to fully harness the information in news systematically and reproducibly, which hinders quality improvement and evaluation of EBS. We developed a systematic anomaly detection approach in EBS and applied it to evaluate the ability of the BioCaster EBS system to detect outbreaks caused by the SARS-CoV-2 Omicron variant. Methods: We describe a four-step approach to anomaly detection in EBS and illustrate this approach through a case study. We collected event entities extracted from 133,897 news articles reporting COVID-19 in 104 countries from the BioCaster EBS system between September 1 and December 11, 2021. We constructed news indicators based on the frequencies of 13 event entities and combinations of entities, generated news signals prospectively using Bayesian online change point detection models and assessed the accuracy and timeliness of different signals against labelled outbreak data. Findings: Monitoring the frequency of news articles reporting COVID-19 provided signals with a timely sensitivity of 0·4615 and a positive predictive value of 0·3014, while monitoring the frequency of event entities closely related to the Omicron variant (e.g., “unclassified pathogen” and “international travel”) improved accuracy. Timeliness and sensitivity were further improved in some settings by simultaneously monitoring multiple news indicators at the cost of additional false signals. Interpretation: An aberration detection approach based on statistical monitoring of indicators constructed from event entities was able to detect outbreaks of the Omicron variant in a timely and accurate manner. This anomaly detection approach is systematic and reproducible and can be applied to different EBS systems, enabling quality improvement and evaluation of EBS systems.

Despite scaling to massive context windows, Large Language Models (LLMs) struggle with multi-hop reasoning due to inherent position bias, which causes them to overlook information at certain positions. Whether these failures stem from an inability to locate evidence (recognition failure) or integrate it (synthesis failure) is unclear. We introduce Multi-Focus Attention Instruction (MFAI), a semantic probe to disentangle these mechanisms by explicitly steering attention towards selected positions. Across 5 LLMs on two multi-hop QA tasks (MuSiQue and NeoQA), we identify the "Weakest Link Effect": in our 18-document, 3-bucket setting, multi-hop reasoning performance collapses to the level of the least visible evidence, governed by absolute position rather than the linear distance between facts. While matched MFAI resolves recognition bottlenecks, improving accuracy by up to 11.49% in low-visibility positions, misleading MFAI yields divergent effects modulated by task topology: entity-centric tasks with vertical reasoning chains are vulnerable, whereas event-centric tasks with horizontal evidence structures are more resilient. Finally, we demonstrate that "thinking" models utilizing System-2 reasoning effectively locate and integrate the required information, matching gold-only baselines even in noisy, long-context settings. Supplementary experiments on 2WikiMultiHopQA, extended 3-4 hop counts, and a 32B model confirm these findings generalize across datasets, reasoning depths, and model scales.

Although artificial intelligence (AI) now matches or exceeds human performance across numerous cognitive tasks, creativity remains a highly contested frontier. As AI systems based on large language models (LLMs) are increasingly adopted in research and innovation, it is essential to understand and augment their creativity. Here we demonstrate that multi-agent LLM teams not only surpass single agents, but also substantially outperform human teams in creativity (Cohen's d=1.50) across 4,541 multi-agent LLM ideas and 341 human-team ideas on six diverse problem-solving tasks. This advantage is driven by novelty while maintaining comparable usefulness. To investigate the generative processes in both groups, we represent conversations as paths through semantic space using neural language model representations. Both LLM and human teams produce more creative ideas when conversations range widely rather than staying centered on a single theme (low global coherence). However, the additional patterns that predict creativity differ: LLM teams benefit from efficient exploration (high semantic spread, shorter paths), while human teams benefit from maintaining smooth conversational flow (high local coherence, frequent pivots). Additionally, we identify model choice and discussion structure as orthogonal design levers that together explain 26.8

Multi-agent debate (MAD) is widely used to improve large language model (LLM) performance through test-time scaling, yet recent work shows that vanilla MAD often underperforms simple majority vote despite higher computational cost. Studies show that, under homogeneous agents and uniform belief updates, debate preserves expected correctness and therefore cannot reliably improve outcomes. Drawing on findings from human deliberation and collective decision-making, we identify two key mechanisms missing from vanilla MAD: (i) diversity of initial viewpoints and (ii) explicit, calibrated confidence communication. We propose two lightweight interventions. First, a diversity-aware initialisation that selects a more diverse pool of candidate answers, increasing the likelihood that a correct hypothesis is present at the start of debate. Second, a confidence-modulated debate protocol in which agents express calibrated confidence and condition their updates on others' confidence. We show theoretically that diversity-aware initialisation improves the prior probability of MAD success without changing the underlying update dynamics, while confidence-modulated updates enable debate to systematically drift to the correct hypothesis. Empirically, across six reasoning-oriented QA benchmarks, our methods consistently outperform vanilla MAD and majority vote. Our results connect human deliberation with LLM-based debate and demonstrate that simple, principled modifications can substantially enhance debate effectiveness.

Large language model agents can discover alphas, yet current methods have three weaknesses. The search cannot adapt during the run, automation usually ends at alpha generation while library selection and model choice stay manual, and alpha discovery can read the test window through loop feedback or code problems. We present AutoScientist-Quant, a self evolving search process that regards quantitative research as one budgeted search problem. A single controller conditions every decision on the remaining budget, choosing at each round whether to improve, combine, pivot, or stop, which node to expand, how many alphas to generate, and how to retrieve past trajectories from the shared memory. The same core then selects from the library and tunes the model, closing the loop from hypothesis to deployable strategy. We also review the evaluation pipeline reused from prior work, fix two lookahead problems, and keep the feedback window disjoint from the held out test window, so every comparison tests true generalization. On CSI universes, the framework attains the best value of nearly every metric in every setting, and these conclusions hold across several backbones and markets.

Large language model (LLM) simulations of human behavior have the potential to revolutionize the social and behavioral sciences, if and only if they faithfully reflect real human behaviors. Current evaluations are fragmented, based on bespoke tasks and metrics, creating a patchwork of incomparable results. To address this, we introduce SimBench, the first large-scale, standardized benchmark for a robust, reproducible science of LLM simulation. By unifying 20 diverse datasets covering tasks from moral decision-making to economic choice across a large global participant pool, SimBench provides the necessary foundation to ask fundamental questions about when, how, and why LLM simulations succeed or fail. We show that, while even the best LLMs today have limited simulation ability (score: 40.80/100), performance scales log-linearly with model size. Simulation performance is not improved by increased inference-time compute. We discover an alignment-simulation trade-off: instruction-tuning improves performance on low-entropy (consensus) questions but degrades it on high-entropy (diverse) ones. Models particularly struggle when simulating specific demographic groups. Finally, we demonstrate that simulation ability correlates most strongly with deep, knowledge-intensive reasoning (MMLU-Pro, r=0.939). By making progress measurable, we aim to accelerate the development of more faithful LLM simulators.

The "alignment tax" of post-training is typically framed as a drop in task accuracy. We show it also involves a severe loss of calibration, making models overconfident, less reliable, and model outputs less diverse. We show that this trade-off can be navigated effectively via a simple post-hoc intervention: interpolating between a model's weights before and after alignment. Crucially, this is not a strict trade-off. We find that the process consistently reveals Pareto-optimal interpolations - models that improve accuracy beyond both parents while substantially recovering the calibration lost during alignment. Our work demonstrates that simple model merging provides a computationally efficient method for mitigating the full scope of the alignment tax, yielding models that are more capable and more reliable.

Large language models excel at complex instructions yet struggle to deviate from their helpful assistant persona, as post-training instills strong priors that resist conflicting instructions. We introduce system prompt strength, a training-free method that treats prompt adherence as a continuous control. By contrasting logits from target and default system prompts, we isolate and amplify the behavioral signal unique to the target persona by a scalar factor alpha. Across five diverse benchmarks spanning constraint satisfaction, behavioral control, pluralistic alignment, capability modulation, and stylistic control, our method yields substantial improvements: up to +8.5 strict accuracy on IFEval, +45pp refusal rate on OffTopicEval, and +13

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing and difficulty scaling. We introduce a four-stage Data Processing Framework encompassing collection, processing, filtering, and verification, incorporating Automatic Difficulty Filtering via an LLM-based predict-calibrate-select framework that leverages multi-dimensional difficulty metrics across five weighted dimensions to retain challenging problems while removing simplistic ones. The resulting MicroCoder dataset comprises tens of thousands of curated real competitive programming problems from diverse platforms, emphasizing recency and difficulty. Evaluations on strictly unseen LiveCodeBench demonstrate that MicroCoder achieves 3x larger performance gains within 300 training steps compared to widely-used baseline datasets of comparable size, with consistent advantages under both GRPO and its variant training algorithms. The MicroCoder dataset delivers obvious improvements on medium and hard problems across different model sizes, achieving up to 17.2

Large Language Model (LLM) agents deployed for real-world tasks face a fundamental dilemma: user requests are underspecified, yet agents must decide whether to act on incomplete information or interrupt users for clarification. Existing approaches either rely on brittle confidence thresholds that require task-specific tuning, or fail to account for the varying stakes of different decisions. We introduce a decision-theoretic framework that resolves this trade-off through the Value of Information (VoI), enabling agents to dynamically weigh the expected utility gain from asking questions against the cognitive cost imposed on users. Our inference-time method requires no hyperparameter tuning and adapts seamlessly across contexts-from casual games to medical diagnosis. Experiments across four diverse domains (20 Questions, medical diagnosis, flight booking, and e-commerce) show that VoI consistently matches or exceeds the best manually-tuned baselines, achieving up to 1.36 utility points higher in high-cost settings. This work provides a parameter-free framework for adaptive agent communication that explicitly balances task risk, query ambiguity, and user effort.

Parameter-efficient fine-tuning methods like Low-Rank Adaptation (LoRA) have become essential for deploying large language models, yet their static parameter allocation remains suboptimal for inputs of varying complexity. We present Flexi-LoRA, a novel framework that dynamically adjusts LoRA ranks based on input complexity during both training and inference. Through empirical analysis across question answering, mathematical reasoning, and speech tasks, we demonstrate that maintaining consistency between training and inference dynamics is important for effective adaptation, particularly for sequential reasoning tasks. Our findings reveal that input-dependent parameter allocation achieves higher performance with fewer parameters by optimally matching rank configurations to question complexity. Furthermore, task-specific dependency on rank dynamics varies, with mathematical reasoning tasks exhibiting higher dependency than QA tasks. Successful adaptation manifests not only in correctness but also in reasoning quality and instruction adherence. Flexi-LoRA consistently outperforms static LoRA while using fewer parameters, with performance gains more pronounced on tasks requiring strict reasoning chains. Our approach realizes key benefits of mixture-of-experts frameworks through a more streamlined implementation, reducing parameter redundancy while improving model capabilities. We provide comprehensive empirical studies across diverse tasks, establishing a basis for future work in input-adaptive and efficient fine-tuning approaches.

When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send the query to a powerful proprietary LLM providers to achieving state-of-the-art performance and risk data exposure, or relying on smaller, local models guarantees data privacy but often results in a degradation of task performance. Prior approaches have relied on static pipelines that use LLM rewriting, which shatters linguistic coherence and indiscriminately removes privacy-sensitive information, including task-critical content. We reformulate this challenge (Privacy-Conscious Delegation) as a sequential decision-making problem and introduce a novel reinforcement learning (RL) framework called Privacy-R1 to solve it. Our framework trains an agent to dynamically route text chunks, learning a policy that optimally balances the trade-off between privacy leakage and task performance. It implicitly distinguishes between replaceable Personally Identifiable Information (PII) (which it shields locally) and task-critical PII (which it strategically sends to the remote model for maximal utility). To validate our approach in complex scenarios, we also introduce a new medical dataset with high PII density. Our framework achieves a new state-of-the-art on the privacy-utility frontier, demonstrating the necessity of learned, adaptive policies for deploying LLMs in sensitive environments. Dataset can be found at: https://github.com/zackhuiiiii/Privacy-R1.

Hallucination remains a major challenge for the safe and trustworthy deployment of large language models (LLMs) in factual content generation. Prior work has explored confidence estimation as an effective approach to hallucination detection, but often relies on post-hoc self-consistency methods that require computationally expensive sampling. Verbalized confidence offers a more efficient alternative, but existing approaches are largely limited to short-form question answering (QA) tasks and do not generalize well to open-ended generation. In this paper, we propose LoVeC (Long-form Verbalized Confidence), a novel reinforcement learning (RL)–based method that trains LLMs to append an on-the-fly numerical confidence score to each generated statement during long-form generation. The confidence score serves as a direct and interpretable signal of the factuality of generation. We introduce two evaluation settings, free-form tagging and iterative tagging, to assess different verbalized confidence estimation methods. Experiments on three long-form QA datasets show that our RL-trained models achieve better calibration and generalize robustly across domains. Also, our method is highly efficient, being 20 × faster than traditional self-consistency methods while achieving better calibration.

Large language models (LLMs) are increasingly deployed as code generators, where silently wrong programs pose real safety and reliability risks. Reliable uncertainty estimation (UE) is essential for selective prediction, human-in-the-loop review, and downstream agentic decisions. Yet most existing code UE methods are inherited from natural language (NL) generation and ignore properties that make code distinct. We argue that code differs from NL in three ways: a single wrong token can break an entire program (token fragility); algorithmic intent and concrete implementation can disagree independently (intent-code gap); and programs can be executed (executability). We instantiate these properties as three orthogonal uncertainty axes: lexical (Top-K token entropy), algorithmic (pseudo-code consistency), and functional (behavioral consistency). Across five code LLMs, our three-axis ensemble improves average AUROC from 0.696 for the strongest NL-derived baseline to 0.776 (+8.1 points). Notably, on Qwen3-14B, our single-pass Top-K token entropy matches the strongest multi-pass baseline while being over 3x cheaper; across models, it remains a competitive low-cost signal. These results suggest that code UE deserves code-specific design rather than direct NL ports.

Large Language Models (LLMs) are prone to hallucination, particularly in long-form generations. A promising direction to mitigate hallucination is to teach LLMs to express uncertainty explicitly when they lack sufficient knowledge. However, existing work lacks direct and fair evaluation of LLMs' ability to express uncertainty effectively in long-form generation. To address this gap, we first introduce UNCLE, a benchmark designed to evaluate uncertainty expression in both long- and short-form question answering (QA). UNCLE covers five domains and includes more than 1,000 entities, each with paired short- and long-form QA items. Our dataset is the first to directly link short- and long-form QA through aligned questions and gold-standard answers. Along with UNCLE, we propose a suite of new metrics to assess the models' capabilities to selectively express uncertainty. We then demonstrate that current models fail to convey uncertainty appropriately in long-form generation. We further explore both prompt-based and training-based methods to improve models' performance, with the training-based methods yielding greater gains. Further analysis of alignment gaps between short- and long-form uncertainty expression highlights promising directions for future research using UNCLE.

Large Language Models (LLMs) are expected to be predictable and trustworthy to support reliable decision-making systems. Yet current LLMs often show inconsistencies in their judgments. In this work, we examine \textit{logical preference consistency} as a foundational requirement for building more dependable LLM systems, ensuring stable and coherent decision-making while minimizing erratic or contradictory outputs.To quantify the logical preference consistency, we propose a universal evaluation framework based on three fundamental properties: , and .Through extensive experimentation across diverse LLMs, we demonstrate that these properties serve as strong indicators of judgment robustness.Furthermore, we introduce a data refinement and augmentation technique, REPAIR, that enhances logical consistency while maintaining alignment with human preferences. Finally, we show that improving consistency leads to better performance in LLM-driven logic-based algorithms, reinforcing stability and coherence in decision-making systems.