Large Language Models

Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs). Recent works show that large language models (LLMs), when integrated into well-designed frameworks (i.e., LLM-AHD), can autonomously discover high-performing heuristics. However, existing LLM-AHD frameworks typically treat LLMs as passive generators within fixed workflows, where the model generates heuristics from manually designed, limited context. Such context may fail to capture state-dependent information (e.g., specific failure modes), leading to inefficient trial-and-error exploration. To overcome these limitations, we propose AHD Agent, a novel tool-integrated, multi-turn framework that empowers LLMs to proactively decide whether to generate heuristics or invoke tools to retrieve targeted evidence from the solving environment. To effectively train such a dynamic decision-making agent, we introduce an agentic reinforcement learning (RL) system, which leverages a novel environment synthesis pipeline to optimize a compact model's generalizable AHD capabilities. Experiments across eight diverse domains, including four held-out tasks, demonstrate that our 4B-parameter agent matches or surpasses state-of-the-art baselines using much larger models, while requiring significantly fewer evaluations. Model and inference scaling analysis further reveals that AHD Agent offers an effective trajectory toward truly autonomous heuristic design.

Are certain cognitive biases mathematically inevitable consequences of sequential information processing? We prove that primacy effects, anchoring, and order-dependence are architecturally necessary in autoregressive language models due to causal masking constraints. Our three impossibility theorems establish: (1) primacy bias arises from asymmetric attention accumulation; (2) anchoring emerges from sequential conditioning with provable information bounds; and (3) exact debiasing by permutation marginalization requires factorial-time computation, with Monte Carlo approximation feasible at constant per-tolerance overhead. We validate these bounds across 12 frontier LLMs ($R^2 = 0.89$; $Δ$BIC $= 16.6$ vs. next-best alternative). We then derive quantitative predictions from the framework and test them in two pre-registered human experiments ($N = 464$ analyzed). Study 1 confirms anchor position modulates anchoring magnitude ($d = 0.52$, BF$_{10} = 847$). Study 2 shows working memory load amplifies primacy bias ($d = 0.41$, BF$_{10} = 156$), with WM capacity predicting bias reduction ($r = -.38$). These convergent findings reframe cognitive biases as resource-rational responses to sequential processing.

We investigate the origins of massive activations in large language models (LLMs) and identify a specific layer named the \textbf{Massive Emergence Layer (ME Layer)}, that is consistently observed across model families, where massive activations first emerge and subsequently propagate to deeper layers through residual connections. We show that, within the ME Layer both the RMSNorm and the FFN parameters jointly contribute to the emergence of massive activations. Once formed, the massive activation token representation remains largely invariant across layers, reducing the diversity of hidden representations passed to the attention module. Motivated by this limitation, we propose a simple and effective method to reduce the rigidity of the massive activation token. Our approach consistently improves LLM performance across multiple tasks, including instruction following and math reasoning, in both training free and fine tuning settings. Moreover, we show that our method mitigates attention sinks by selectively weakening their influence, elucidating their origin at the hidden state level and shedding new light on principled mitigation strategies.

Hallucination remains a persistent challenge in Large Language Models (LLMs), particularly in context-grounded settings such as RAG and agentic AI systems. This study focuses on contextual hallucination detection in summarization tasks. We analyze the QAGS-C and SummEval datasets by comparing original benchmark annotations with reason and span-based predictions from Gemini 2.5 Flash and GPT-5 Mini. To address systematic divergences between human labels and LLM judgments, we re-evaluated all conflicted samples through a human adjudication process involving 2 cross-cultural adjudicators. Following this re-evaluation, triple agreement (between human, GPT, and Gemini) increased by 6.38% for QAGS-C and 7.62% for SummEval. Similarly, model accuracy improved, with GPT increasing by 4.25% on QAGS-C and 2.34% on SummEval, while Gemini showed gains of 8.51% and 3.80%, respectively. Notably, adjudicators frequently sided with the models' judgments over original human annotations when LLMs provided explicit reasoning. Overall human adjudicator agreement ranged between 83% and 87%. These findings suggest that for ambiguity-prone tasks, single-pass annotations may be insufficient, and model-assisted re-evaluation yields more reliable benchmarks.

Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS strategies are largely hand-crafted: researchers manually design reasoning patterns and tune heuristics by intuition, leaving much of the computation-allocation space unexplored. We propose an environment-driven framework, AutoTTS, that changes what researchers design: from individual TTS heuristics to environments where TTS strategies can be discovered automatically. The key to AutoTTS lies in environment construction: the discovery environment must make the control space tractable and provide cheap, frequent feedback for TTS search. As a concrete instantiation, we formulate width--depth TTS as controller synthesis over pre-collected reasoning trajectories and probe signals, where controllers decide when to branch, continue, probe, prune, or stop and can be evaluated cheaply without repeated LLM calls. We further introduce beta parameterization to make the search tractable and fine-grained execution trace feedback to improve discovery efficiency by helping the agent diagnose why a TTS program fails. Experiments on mathematical reasoning benchmarks show that the discovered strategies improve the overall accuracy--cost tradeoff over strong manually designed baselines. The discovered strategies generalize to held-out benchmarks and model scales, while the entire discovery costs only $39.9 and 160 minutes. Our data, and code will be open-source at https://github.com/zhengkid/AutoTTS.

Federated fine-tuning (FFT) has emerged as a privacy-preserving paradigm for collaboratively adapting large language models (LLMs). Built upon federated learning, FFT enables distributed agents to jointly refine a shared pretrained LLM by aggregating local LLM updates without sharing local raw data. However, FFT-based LLMs remain vulnerable to model manipulation threats, in which adversarial participants upload manipulated LLM updates that corrupt the aggregation process and degrade the performance of the global LLM. In this paper, we propose an Augmented Model maniPulation (AugMP) strategy against FFT-based LLMs. Specifically, we design a novel graph representation learning framework that captures feature correlations among benign LLM updates to guide the generation of malicious updates. To enhance manipulation effectiveness and stealthiness, we develop an iterative manipulation algorithm based on an augmented Lagrangian dual formulation. Through this formulation, malicious updates are optimized to embed adversarial objectives while preserving benign-like parameter characteristics. Experimental results across multiple LLM backbones demonstrate that the AugMP strategy achieves the strongest manipulation performance among all competing baselines, reducing the global LLM accuracy by up to $26\%$ and degrading the average accuracy of local LLM agents by up to $22\%$. Meanwhile, AugMP maintains high statistical and geometric consistency with benign updates, enabling it to evade conventional distance- and similarity-based defense methods.

Robot swarms promise scalable assistance in complex and hazardous environments. Task planning lies at the core of human-swarm collaboration, translating the operator's intent into coordinated swarm actions and helping determine when validation or intervention is required during execution. In long-horizon missions under dynamic scenarios, however, reliable task planning becomes difficult to maintain: emerging events and changing conditions demand continual adaptation, and sustained operator oversight imposes substantial cognitive burden. Existing LLM-based planning tools can support plan generation, yet they remain susceptible to invalid task orderings and infeasible robot actions, resulting in frequent manual adjustment. Here we introduce a neuro-symbolic framework for long-horizon human-swarm collaboration that tightly melds verifiable task planning with context-grounded LLM reasoning. We formalize mission goals and operational rules as temporal logic formulas and admissible task orderings as task automata. Conditioned on these formal constraints and live perceptual context, LLMs generate executable subtask sequences that satisfy mission rules and remain grounded in the current scene. An uncertainty-aware scheduler then assigns subtasks across the heterogeneous swarm to maximize parallelisms while remaining resilient to disruptions. An event-triggered interaction protocol further limits operator involvement to sparse, high-level confirmation and guidance. Deployment on a heterogeneous robotic fleet yields similar results while remaining robust to hardware-specific actuation and communication uncertainties. Together, these results support a formal and scalable paradigm for reliable and low-overhead human-swarm collaboration in dynamic environments

Large language models (LLMs) achieve strong performance but remain costly to deploy in resource-constrained settings. Training small language models (SLMs) from scratch is computationally expensive, while conventional knowledge distillation requires repeated access to large teachers for different target sizes, leading to poor scalability. To solve these problems, we propose \textbf{Chain-based Distillation (CBD)}, a scalable paradigm for efficiently initializing variable-sized language models. A sparse and limited sequence of intermediate models (called anchors) is constructed via stepwise distillation, forming a distillation chain that progressively transfers knowledge from the source LLMs. To support heterogeneous settings, we introduce \emph{bridge distillation} for cross-architecture and cross-vocabulary transfer. Models of variable sizes are initialized via parameter interpolation between adjacent anchors, eliminating repeated large teacher inference. Experiments show that the proposed method substantially improves efficiency and downstream performance. A 138M-parameter SLM without recovery pre-training, outperforms scratch-trained models on a 10B-token corpus on the specific task. CBD also demonstrates versatility in heterogeneous settings for initialize models with different architectures and vocabularies.

This report benchmarks the performance of ENGINEERING Ingegneria Informatica S.p.A.'s EngGPT2MoE-16B-A3B LLM, a 16B parameter Mixture of Experts (MoE) model with 3B active parameters. Performance is investigated across a wide variety of representative benchmarks, and is compared against comparably-sized open-source MoE and dense models. In comparison with popular Italian models, namely FastwebMIIA-7B, Minerva-7B, Velvet-14B, and LLaMAntino-3-ANITA-8B, EngGPT2MoE-16B-A3B performs as well or better on international benchmarks: ARC-Challenge, GSM8K, AIME24, AIME25, MMLU, and HumanEval (HE). It achieves the best performance for the longest context setting (32k) of the RULER benchmark. On the Italian benchmark dataset ITALIC, the model performs as well or better than the other models except for Velvet-14B, which outperforms it. Compared with popular MoE models of comparable size, the new model reports higher values than DeepSeek-MoE-16B-Chat on all considered benchmarks. It has higher values than Moonlight-16B-A3B on HE, MMLU, AIME24, AIME25, GSM8K, and the 32k RULER setting, but lower on BFCL and some ARC and ITALIC settings. Finally it has lower values than GPT-OSS-20B on most benchmarks, including HE, MMLU, AIME24, AIME25, GSM8K, ARC, BFCL, and the RULER 32k. When compared with popular dense models, EngGPT2MoE-16B-A3B reports higher values on AIME24 and AIME25 than Llama-3.1-8B-Instruct, Gemma-3-12b-it, and Ministral-3-8BInstruct-2512-BF16, but lower values on ITALIC, BFCL, and RULER with a 32k context. When performance is aggregated across all benchmark metrics, EngGPT2MoE-16B-A3B shows higher performance than the Italian models under evaluation while achieving lower results than some of the most performant international models, in particular GPT-5 nano and Qwen3-8B. Taken together, our findings find the new model to be a step forward for native Italian Large Language Models.

Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps remain in this domain: (1) latest-generation Large Language Models (LLMs) lack comprehensive evaluation on grammar correction tasks; (2) whether combining these LLMs improves correction quality is unexplored; and (3) the extent to which reference-based metrics underestimate GEC system performance has not been adequately quantified. In this study, first, we evaluate latest-generation LLMs on edit precision, fluency preservation, and meaning retention, showing fine-tuned GPT-4o achieves state-of-the-art performance across all three dimensions. Second, through grammatical error type analysis we demonstrate that individual LLMs exhibit highly similar error correction patterns ($ρ=0.947$). Third, we show that reference-based metrics underestimate GEC performance with 73.76% of GPT-4o corrections different from gold standards being equally valid or even superior. These GEC evaluation findings equip educators with guidance for selecting GEC assistants that enhance rather than constrain student linguistic development. We make our data, code, and models publicly available.

Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavior and why. To address this, we introduce Psych-201, a novel dataset that enables us to measure behavioral alignment at scale. We find that post-training -- the stage that turns base models into useful assistants -- consistently reduces alignment with human behavior across model families, sizes, and objectives. Moreover, this misalignment widens in newer model generations even as base models continue to improve. Finally, we find that persona-induction -- a popular technique for eliciting human-like behavior by conditioning models on participant-specific information -- does not improve predictions at the level of individuals. Taken together, our results suggest that the very processes that are currently employed to turn LLMs into useful assistants also make them less accurate models of human behavior.

Large Language Models (LLMs) have recently demonstrated strong performance in machine translation (MT). However, most prior work focuses on improving or benchmarking translation quality, offering limited insight into when and why LLM-based translation fails. In this work, we systematically analyze failure modes of LLMs in MT by evaluating 15 models, including four reasoning LLMs, across 22 language pairs (LPs) with varying resource levels. We find that non-English-centric LPs consistently yield lower COMET scores than English-centric pairs. To investigate the underlying causes, we introduce Token Activation Rate (TAR), a metric that captures how effectively a model utilizes language-specific tokens in its vocabulary during generation. We validate TAR as a proxy for language representation using models with known language distributions in the training data, and show that lower TAR is strongly associated with poorer translation performance. Furthermore, reasoning LLMs tend to generate more tokens when translating into low-TAR languages, suggesting a compensatory mechanism, although its impact on translation quality varies across models. Overall, our findings emphasize the importance of token-level dynamics in understanding MT performance of LLMs.

Reusable agent skills are emerging as a service-oriented capability layer for Large Language Model (LLM) agents. Unlike plain retrieval items, a skill exposes functional capabilities, input-output assumptions, tool dependencies, context cost, and risk metadata. Selecting skills is particularly challenging for small LLM agents, which can load only a few capability units under restricted context, tool availability, and risk tolerance. Existing fixed Top-k methods rank skills by textual relevance and overlook requirement satisfaction, deliverability, and operational constraints. We present SkillSelect-Serve, a QoS-aware, budget-constrained Skill Service recommendation framework. Raw skills are profiled as structured Skill Services, the task is converted into a structured requirement object, and candidates discovered from a large-scale registry are ranked by a calibrated task-conditioned suitability estimator and packed by a constrained projection enforcing token-budget, aggregated-risk, and tool-availability constraints, using only deployment-observable features. On a registry of 35,353 skills with pooled multi-positive relevance judgments verified by two independent assessors, the unconstrained top-5 recommendation fits a realistic 4,000-token context for only 9.1% of tasks; the constrained projection restores 100% deliverability at a cost of only 1.14 points of hit rate, outperforming retrieve-and-rerank, budget truncation, and diversity-based selection under identical budgets. The same mechanism halves delivered risk exposure and eliminates the 44-81% tool-violation rates of tool-agnostic recommendation. At an identical three-service budget, hit rate improves from 0.8864 to 0.9091 over fixed Top-3 retrieval. The results support managing reusable agent skills as discoverable, comparable, and constraint-aware service units instead of plain retrievable documents.

In this paper, we investigate the recent state-of-the-art schemes for watermarking large language models (LLMs) outputs. These techniques are claimed to be robust, scalable and production-grade, aimed at promoting responsible usage of LLMs. We analyse the effectiveness of these watermarking techniques against an extensive collection of modified text attacks, which perform targeted semantic changes without altering the general meaning of the text content. Our approach encompasses multiple attack strategies, which include lexical alterations, machine translation, and even neural paraphrasing. The attack efficacy is measured with two target criteria - successful removal of the watermark and preservation of semantic content. We evaluate semantic preservation through BERT scores, text complexity measures, grammatical errors, and Flesch Reading Ease indices. The experimental results reveal varying levels of effectiveness among different watermarking models, with the same underlying result that it is possible to remove the watermark with reasonable effort. This study sheds light on the strengths and weaknesses of existing LLM watermarking systems, suggesting how they should be constructed to improve security of available schemes.

Deploying massive large language models (LLMs) as continuous cognitive engines for robotics is bottlenecked by the time-to-first-token (TTFT) latency required to process extensive state histories. Existing solutions like RAG or sliding windows compromise global context or incur prohibitive re-computation costs. We formalize the optimal task structure for minimizing latency and theoretically prove that prefix stability, incremental extensibility, and asynchronous state reconciliation are necessary conditions for real-time performance. Building on these proofs, we introduce the Cached State Representation (CSR) framework as the practical instantiation of these properties, ensuring optimal KV-cache reuse. To sustain these properties over infinite horizons, we further propose an Asynchronous State Reconciliation (ASR) algorithm that offloads state memory eviction to a parallel computational resource to eliminate latency spikes. On a physical robot wirelessly connected to an on-premise GPU server, CSR achieves a 26-fold latency reduction (14.67s to 0.56s) for 120K token contexts with a 235B parameter model compared to a standard baseline. On an embodied AI benchmark, we achieve SOTA recall (0.836 vs. 0.459) while maintaining RAG-level latency. ASR is validated to sustain bounded, spike-free TTFT over 10 eviction cycles in continuous real-world operation. Together, CSR and ASR enable massive LLMs to function as continuously operating, high-frequency (> 2 Hz) embodied policies.

Layer pruning efficiently reduces Large Language Model (LLM) computational costs but often triggers sudden performance collapse. Existing representation-based analyses struggle to explain this mechanism. We propose studying pruning through decision representation. Focusing on multiple-choice tasks, we introduce two metrics, Decision Margin and Option Frequency, and an Iterative Pruning method to analyze layer-wise decision dynamics. Our findings reveal a sharp decision transition that partitions the network into two stages: a Silent Phase, where the model cannot yet predict the correct answer, and a Decisive Phase, where the correct prediction emerges. We also find that pruning the Decisive Phase has minimal impact, whereas pruning the Silent Phase triggers immediate performance collapse, highlighting its extreme sensitivity to structural changes. Therefore, we conclude that pruning-induced collapse stems from disrupting the Silent Phase, which prevents the critical decision transition from occurring.

Modern scientific research increasingly depends on High-Performance Computing (HPC) infrastructures, yet many researchers face significant operational barriers when interacting with cluster environments, job schedulers, GPU resources, and parallel computing frameworks. General-purpose large language models (LLMs) provide useful coding assistance but often lack the domain-specific operational knowledge required for reliable HPC support. This paper presents HPC-LLM, a retrieval augmented and domain-adapted assistant designed to support common HPC workflows including Slurm scheduling, MPI execution, GPU utilization, filesystem management, and cluster troubleshooting. The proposed framework integrates automated documentation ingestion, dense retrieval, lightweight domain adaptation using QLoRA, and local inference within a modular orchestration pipeline. To support domain adaptation, we construct an HPC-oriented corpus from publicly available university HPC documentation, curated operational examples, and synthetic instruction-answer pairs generated from retrieved HPC content. The resulting dataset contains approximately 9,000 to 24,000 HPC-focused training examples spanning job scheduling, GPU computing, distributed training, storage systems, and cluster administration topics. We fine-tune Llama 3.1 8B using QLoRA and evaluate the resulting model against several open weight baselines under retrieval-augmented settings on JetStream2 infrastructure. Experimental results indicate that the adapted 8B model achieves performance comparable to substantially larger general-purpose models while operating under significantly lower GPU memory requirements and inference latency. In particular, the adapted model approaches the performance of Qwen 2.5 14B while requiring substantially fewer computational resources.

Existing Large Language Model (LLM) benchmarks primarily focus on syntactically correct inputs, leaving a significant gap in evaluation on imperfect text. In this work, we study how word-boundary corruption affects how LLMs detect targeted information. By inserting whitespace characters within words to break them into fragments, LLMs' detection accuracy follows a U-shaped curve with the increase in insertion rate. We refer to this curve as the Text Uncanny Valley. To explain such observation, we propose a mode transition hypothesis: LLMs operate in a word-level mode for near-normal text and a character-level mode for heavily fragmented text, with the valley marking the disordered transition where neither mode is effective. Four experiments and one analysis are consistent with this account: in-context learning fails to rescue valley-bottom performance; regularizing the perturbation substantially reduces the U-shape; a math reasoning task replicates the U-shape for Gemini 3.0 Flash but not for stronger models, suggesting the effect is attenuated when tasks rely less on exact lexical alignment; and tokenization entropy peaks before the F1 minimum, consistent with a regime-conflict interpretation. These findings reveal a failure mode invisible to clean-text benchmarks yet directly relevant to any deployment scenario involving noisy or uncurated text inputs.

The ecosystem of Lean and Mathlib has become the de facto standard for large language model (LLM) assisted formal reasoning with remarkable successes in recent years. Those successes, however, only consume Mathlib as an essential dependency but do not directly contribute to it. In the meantime, the growth of Mathlib has recently been bottlenecked by the review process, which requires human reviewers to judge whether proposed pull requests (PRs) follow the Mathlib's conventions and are worth integrating as part of a shared mathematical infrastructure. This leads to our central question: can LLMs help review Mathlib PRs? To this end, we introduce MathlibPR, a benchmark built from real Mathlib4 PR histories. We further propose a staged evaluation protocol and use it to evaluate both LLM models (e.g., DeepSeek, Qwen, Goedel, and Kimina) and LLM agents (e.g., Codex and Claude Code). Surprisingly, both LLM models and LLM agents struggle to distinguish merge-ready PRs from build-passing PRs that were revised or never merged. By turning Mathlib PR histories into a supervised signal, MathlibPR provides a step toward reviewer assistants and reward models that could help evaluate PRs and steer LLMs toward producing merge-ready Mathlib contributions.

Agentic AI systems that invoke external tools are powerful but costly, leading developers to default to large models and overspend inference budgets. Model routing can mitigate this, but existing routers are designed for chat completion rather than tool use. We present Switchcraft, the first (to the best of our knowledge) model router optimized for agentic tool calling. Switchcraft operates inline, selecting the lowest-cost model subject to correctness. We construct an evaluation framework on five function-calling benchmarks and train a DistilBERT-based classifier, deployed under a latency budget. Switchcraft achieves 82.9% accuracy -- matching or exceeding the best individual model -- while reducing inference cost by 84%, saving over $3,600 per million queries. We find that larger models do not consistently outperform smaller ones on tool-use tasks, and that nominally cheaper models can incur higher total cost due to token-intensive reasoning. Our work enables cost-aware agentic AI deployment without sacrificing correctness.

Recent methods expose intra-request parallelism in LLM outputs, allowing independent branches to decode concurrently. Existing serving systems execute these branches eagerly or under fixed caps. We show that both are brittle: eager admission inflates the shared decode step, degrading co-batched requests in serial stages, while conservative fixed caps forgo the throughput that motivated exposing branches in the first place. We call the excess step latency caused by admitted branches the branch externality and show that the safe width depends on batch composition, context lengths, and accumulated slack, all of which change continuously over a workload trace. We introduce TAPER, a per-step admission controller that treats extra branches as opportunistic work, admitted only when the predicted branch externality fits within the batch's current slack budget. Per-step regulation is practical because branch-level scheduling decouples compute from memory: branches share the request's prefix KV, so expanding or contracting width requires no memory reclamation. On Qwen3-32B, TAPER improves goodput by $1.77\times$ over IRP-Off and by $1.48\times$ over IRP-Eager, while maintaining over $95\%$ SLO attainment.

Large Language Models (LLMs) have achieved great improvements in recent years. Nevertheless, it still remains unclear how good LLMs are for reasoning tasks, especially for long-chain ones. In this paper, we evaluate LLMs' performance on the simplest yet long-chain reasoning task, namely the Equivalence Class Problem (ECP), i.e., determining whether two variables are equal given a set of randomly generated equivalence relations. We consider both reasoning and non-reasoning representative LLMs over a large variety of problem instances, ranging over different numbers of variables, connectivity probabilities, prompts, and other factors. The experimental results show that non-reasoning LLMs fail ECP, while reasoning models are significantly better but still struggle to completely solve this problem. Interestingly, considering various connectivity probabilities with a fixed number of variables, we observe that, for non-reasoning models, the hardest problem instances coincide with the phase transition point of ln n/(n-1), suggesting the chaos of the problem; in contrast, for reasoning models, the hardest ones coincide with the biggest diameter, suggesting the reasoning difficulty of the problem.

Large language models (LLMs) are pre-trained and post-trained on vast amounts of loosely curated data, raising the possibility that these models may have been trained on proprietary datasets or the same benchmarks used for evaluation. This motivates the need for dataset watermarking: designing datasets such that training on them leaves detectable signatures in the resulting model. Prior work has explored this problem for open models. We introduce the first dataset watermarking method for closed LLMs with provable detection. In particular, we embed a dataset-level watermark signal by increasing the co-occurrence frequency of randomly selected word pairs through rephrasing, and detect it using a statistical test on co-occurrence patterns in model-generated outputs. We evaluate our method with multiple base models and benchmark datasets and show that it reliably detects the watermark ($p <0.01$) in the fine-tuning stage. Notably, our method remains effective in a data mixture setting where the watermarked dataset constitutes only approximately $1\%$ of the total fine-tuning tokens. Furthermore, we show that our method preserves the utility and semantic integrity of the benchmark.

Ranking LLMs via pairwise human feedback underpins current leaderboards for open-ended tasks, such as creative writing and problem-solving. We analyze ~89K comparisons in 116 languages from 52 LLMs from Arena, and show that the best-fit global Bradley-Terry (BT) ranking is misleading. Nearly 2/3 of the decisive votes cancel out, and even the top 50 models according to the global BT ranking are statistically indistinguishable (pairwise win probabilities are at most 0.53 within the top 50 models). We trace this failure to strong, structured heterogeneity of opinions across language, task, and time. Moreover, we find an important characteristic - language plays a key role. Grouping by language (and families) increases the agreement of votes massively, resulting in two orders of magnitude higher spread in the ELO scores (i.e., very consistent rankings). What appears as global noise is in fact a mixture of coherent but conflicting subpopulations. To address such heterogeneity in supervised machine learning, we introduce the framework of $(λ, ν)$-portfolios, which are small sets of models that achieve a prediction error at most $λ$, "covering" at least a $ν$ fraction of users. We formulate this as a variant of the set cover problem and provide guarantees using the VC dimension of the underlying set system. On the Arena data, our algorithms recover just 5 distinct BT rankings that cover over 96% of votes at a modest $λ$, compared to the 21% coverage by the global ranking. We also provide a portfolio of 6 LLMs that cover twice as many votes as the top-6 LLMs from a global ranking. We further construct portfolios for a classification problem on the COMPAS dataset using an ensemble of fairness-regularized classification models and show that these portfolios can be used to detect blind spots in the data, which might be of independent interest to policymakers.

Optimizers play an important role in both pretraining and finetuning stages when training large language models (LLMs). In this paper, we present an observation that full finetuning with the same optimizer as in pretraining achieves a better learning-forgetting tradeoff, i.e., forgetting less while achieving the same or better performance on the new task, than other optimizers and, possibly surprisingly, LoRA, during the supervised finetuning (SFT) stage. We term this phenomenon optimizer-model consistency. To better understand it, through controlled experiments and theoretical analysis, we show that: 1) optimizers can shape the models by having regularization effects on the activations, leading to different landscapes around the pretrained checkpoints; 2) in response to this regularization effect, the weight update in SFT should follow some specific structures to lower forgetting of the knowledge learned in pretraining, which can be obtained by using the same optimizer. Moreover, we specifically compare Muon and AdamW when they are employed throughout the pretraining and SFT stages and find that Muon performs worse when finetuned for reasoning tasks. With a synthetic language modeling experiment, we demonstrate that this can come from Muon's strong tendency towards rote memorization, which may hurt pattern acquisition with a small amount of data, as for SFT.

Large language models (LLMs) are increasingly used to provide instructions to many agents who interact with one another. Such shared reliance couples agents who appear to act independently: they may in fact be guided by a common model. This coupling can change the prospects for cooperation among agents with misaligned incentives. We study settings in which multiple LLMs each advise a population of clients who participate in instances of an underlying game, creating strategic interaction at the level of the LLMs themselves. This induces a meta-game among the LLMs, mediated through clients. We first analyze the one-shot setting, where shared instructions can change equilibrium behavior only when an LLM may influence more than one role in the same interaction; in such cases, cooperation may emerge, and the effect of client share can be beneficial, harmful, or non-monotone, depending on the base game. Our main result concerns the repeated setting. We prove a folk theorem for LLMs: despite indirect observation and the clients' inability to identify which LLM advised their opponents, all feasible and individually rational outcomes can be sustained as $\varepsilon$-equilibria. The result does not follow from the standard folk theorem and requires new proof techniques. Together, these results show that shared LLM guidance can sustain cooperation among populations of agents even when the underlying incentives are misaligned.

Prefix caching can reduce LLM inference latency by reusing KV caches across requests with shared prompts, but cluster-scale reuse is challenging because caches are partitioned across nodes. We propose a decentralized, prefix-cache-aware routing scheme for peer-to-peer LLM serving. Each node maintains a local radix tree of its own cached prefixes and asynchronously refreshed estimates of peer caches using periodic anti-entropy. Requests are routed to the node with the longest estimated prefix match, without centralized coordination or KV-cache transfer. Stale metadata only causes cache misses, not incorrect outputs, making weak consistency sufficient for correctness. Evaluation on simulated MMLU workloads show that decentralized routing improves latency under low communication delay and skewed prefix distributions, while high network latency and affinity-induced hotspots limit its benefits.

Large language model systems are increasingly deployed as agentic workflows that interleave reasoning, tool use, memory, and iterative refinement. These systems are effective at producing answers, but they often rely on implicit conversational state, making it difficult to preserve stable work products, isolate irrelevant updates, or propagate changes through intermediate artifacts. We introduce execution lineage: an execution model in which AI-native work is represented as a directed acyclic graph (DAG) of artifact-producing computations with explicit dependencies, stable intermediate boundaries, and identity-based replay. The goal is not to make the model a better one-shot writer, but to make evolving AI-generated work maintainable under change. We compare execution-lineage replay against loop-centric update baselines on two controlled policy-memo update tasks. In an unrelated-branch update, DAG replay preserved the final memo exactly in all runs, with zero churn and zero unrelated-branch contamination, while loop baselines regenerated the memo and frequently imported unrelated context. In an intermediate-artifact edit, all systems reflected the new constraint in the final memo, but only DAG replay achieved perfect upstream preservation, downstream propagation, unaffected-artifact preservation, and cross-artifact consistency. These results show that final answer quality and maintained-state quality are distinct. Strong loop baselines can remain competitive at producing polished final outputs when the task is a bounded synthesis/update problem and all current sources fit in context, but immediate task success can mask partial state inconsistency that may compound over future revisions. Execution lineage provides stronger guarantees about what should change, what should remain stable, and how work evolves across revisions.

Model cascades, in which a cheap LLM defers to an expensive one on low-confidence queries, are widely used to navigate the cost-quality tradeoff at deployment. Existing approaches largely treat the deferral threshold as an empirical hyperparameter, with limited guidance on the geometry of the resulting cost-quality frontier over a model pool. We develop a decision-theoretic framework grounded in constrained optimization and duality. For a two-model cascade, we establish piecewise concavity of the cost-quality frontier on decreasing-benefit regions of the confidence support, with reciprocal shadow prices linking the budget- and quality-constrained formulations. Given a pool of $k$ models, we characterize the frontier achievable by deterministic two-model threshold cascades as the pointwise envelope over $\binom{k}{2}$ pairwise cascades, with switching points where the optimal pair changes. For $k$-model cascades, we derive first-order conditions in which a single shadow price equalizes marginal quality-per-cost across stage boundaries. We validate the framework on five benchmarks (MATH, MMLU, TriviaQA, SimpleQA, LiveCodeBench) across eight models from five providers. Within the deterministic threshold-cascade class, full fixed chains underperform the pairwise envelope, and optimized subsequence cascades do not deliver practically meaningful held-out gains over it. A lightweight pre-generation router exceeds the best cascade policy on four of five datasets, mainly because it avoids the cheap model's generation cost on queries sent directly to a larger model rather than because of a stronger routing signal. These results suggest that cascade performance is limited primarily by structural cost, since cascades pay the cheap model before any escalation decision, rather than by a shortage of intermediate stages.

Every major data modality now has a foundation model that understands it natively: text has language models, images have vision models, audio has audio models. Tabular data, the modality on which many consequential real-world AI decisions are made, does not. Every approach to tabular AI today, from gradient-boosted trees to the latest tabular foundation models, requires a preprocessing pipeline before any model can consume the data. None of them understand tabular data as a modality. We introduce the Data Language Model (DLM), the missing foundation model for tabular data. A DLM understands tables the way a language model understands sentences: natively, without serialization or preprocessing, directly from raw cell values. It is the tabular data layer on which AI models, agents, and vertical AI applications can be built, eliminating the preprocessing pipelines that currently stand between raw data and every AI system that consumes it. We present Schema-1, the first DLM: a 140M parameter model trained on more than 2.3M synthetic and real-world tabular datasets. Schema-1 outperforms gradient-boosted ensembles, AutoML stacks, and the tabular foundation models we evaluate on established row-level prediction benchmarks. On missing value reconstruction it achieves lower reconstruction error than all classical statistical methods and frontier large language models on mean performance across conditions, establishing that structural understanding of a dataset's own distributional geometry is more useful for imputation than world knowledge encoded in language. It identifies the industry sector of any unseen dataset from raw cell values alone, reliably across any domain, a task no prior tabular model can perform. It is the native tabular understanding layer that has been missing from the AI stack.

The work in this paper evaluates zero-shot and few-shot large language models (LLMs) for safety-critical clinical action extraction using the CLIP discharge-note dataset, with particular emphasis on transitions of care and post-discharge patient safety. To manage the complexity of clinical documentation, we introduce a two-stage extraction framework that decomposes discharge notes, that are written in narrative form, into fine-grained, explicitly actionable clinical tasks through a staged prompting strategy. Our contributions include a systematic assessment of generative LLMs for clinical action extraction, a detailed comparison between general-purpose LLMs and task-specific supervised BERT-based models, and an analysis of annotation inconsistencies across different action categories. We show that contemporary LLMs achieve performance comparable to or exceeding supervised models on binary actionability detection, while supervised baselines retain a meaningful advantage on fine-grained multi-label category classification, despite the absence of task-specific fine-tuning and under strict data-privacy constraints. Qualitative error analysis reveals that many failures stem from misalignment between model reasoning and dataset annotation conventions, particularly in cases involving implicit clinical actions and rigid structural labeling rules. These results indicate that reported performance reflects model limitations due to lack of clinical reasoning, that is not captured by plain annotations. Labels without rationales make it impossible to distinguish clinical reasoning failures from annotation convention mismatches. Advancing clinical NLP requires reasoning-annotated datasets that document why specific spans are actionable, not merely which spans were labeled, enabling proper evaluation of model clinical understanding.

Large language models (LLMs) have recently been adapted to tabular prediction by serializing structured features into natural language, but their performance in low-data regimes remains limited compared to gradient-boosted decision trees (GBDTs). In this work, we revisit the boosting paradigm, traditionally associated with tree ensembles, and ask whether it can be applied as a general training principle for LLM fine-tuning. We propose BoostLLM, a framework that transforms parameter-efficient fine-tuning into a multi-round residual optimization process by training sequential PEFT adapters as weak learners. To incorporate tabular inductive bias, BoostLLM integrates decision-tree paths as a second input view alongside raw features; analysis reveals that the path view acts as a structured teacher in early training steps before the model shifts toward feature-driven representations. Empirically, BoostLLM achieves consistent improvements over standard fine-tuning across multiple LLM backbones and datasets, matching or surpassing XGBoost across a wide range of shot counts and outperforming GPT-4o-based methods with a 4B model. We further show that the framework scales: pairing with stronger tree models and extended boosting horizons yields additional gains under appropriate stabilization. These results suggest that boosting can serve as a general training principle for LLM fine-tuning, particularly in low-data regimes for structured data.

Large language model (LLM) outputs arise from complex interactions among prompts, system instructions, model parameters, and architecture. We refer to specific configurations of these factors as generation conditions, each of which can bias outputs in various ways. Understanding how different generation conditions shape model behaviors is essential for tasks such as prompt design and model evaluation, yet it remains challenging due to the stochastic and open-ended nature of text generation. We present an approach to visually compare LLM outputs across generation conditions by modeling responses as collections of linguistic choices, including content, expression, and structure. We extract these choices using natural language processing pipelines and represent their distributions across repeated samples. We then visualize these distributions as visual fingerprints, enabling direct, distribution-level comparison of condition-specific tendencies. Through four usage scenarios, we demonstrate how visual fingerprints reveal consistent patterns in LLM behavior that are difficult to observe through individual responses or aggregate metrics.

Large language models (LLMs) increasingly help people solve problems, from debugging code to repairing machinery. This process requires generating plausible hypotheses from partial descriptions, then updating them as more information arrives. Yet how LLMs perform this form of inference, and how close it is to optimal, remains unclear. We study this question in the number game, a controlled setting in which a learner infers the hypothesis supported by a few positive integers, such as $\{16, 8, 2, 64\}$: a rule like powers of 2 or an interval like numbers near 20. We measure the posterior over hypotheses using three complementary probes: posterior prediction, hypothesis evaluation, and hypothesis generation. We then compare LLM behavior with an optimal Bayesian model and human behavior, and test whether the same posterior is expressed across probes. LLMs are often well described by a two-parameter Bayesian fit, but with systematic offsets: by default they show a strong-sampling assumption that creates an implicit Occam's razor, favoring narrower hypotheses, while thinking mode shifts them toward greater prior reliance. We also find a robust evaluation--generation gap: LLMs select more correct hypotheses during hypothesis evaluation but generate simpler, more rule-like hypotheses. Finally, this Bayesian-with-bias pattern does not extrapolate. Models can behave as if they hold rule-like hypotheses over observed examples, yet generalize poorly to parts of the hypothesis domain not covered by those examples. Our results highlight a limitation of LLMs as general problem solvers, especially for scientific inference, where hypotheses must go beyond the data.

LLMs are increasingly explored for malware analysis; however, current LLM-based malware attribution remains limited by unsupported indicators and insufficient code-level grounding for identifying malicious and vulnerable code segments. To address these limitations, this research introduces LCC-LLM, a code-centric benchmark dataset and evidence-grounded framework for malware attribution and multi-task static malware analysis. The proposed LCCD dataset contains approximately 34K PE samples processed through a large-scale reverse-engineering pipeline and represented using decompiled C code, assembly code, CFG/FCG artifacts, hexadecimal data, PE metadata, suspicious API evidence, and structural features. Beyond dataset construction, LCC-LLM integrates LangGraph-orchestrated static analysis with multi-source cybersecurity knowledge to support evidence-grounded malware reasoning. The framework employs a seven-layer retrieval-augmented generation pipeline, CoVe for IoC validation, and a multi-dimensional quality gate to improve factual reliability and analyst-oriented decision support. Curriculum-ordered instruction data is used to fine-tune DeepSeek-R1-Distill-Qwen-14B and Qwen3-Coder-30B-A3B using QLoRA. Evaluation across 43 malware-analysis task types achieves an average semantic similarity of 0.634, with the highest task-level performance in structured report generation, IoC extraction, vulnerability assessment, malware configuration extraction, and malware class detection. In a real-world case study using MalwareBazaar samples, the grounded pipeline achieves a 10/10 structured analysis pass rate, producing CFG/FCG evidence, MITRE ATT&CK mappings, detection guidance, and analyst-ready reports. These results show that code-centric representations, retrieval grounding, and verification-guided reasoning improve the reliability and operational usefulness of LLM-assisted malware attribution.

Can linearly decodable failure signals in LLM hidden states be leveraged to correct those failures? We investigate this classification-correction gap via Overthinking (OT)--a stable behavioral regime (Jaccard >= 0.81, 94% inter-annotator agreement) in medical QA where models answer correctly under resampling yet fail in extended chain-of-thought. OT is linearly decodable at 71.6% balanced accuracy (p < 10^{-16}). Yet five families of fixed linear steering (29 configurations, n=1,273) all yield Delta ~= 0, with identical null results cross-architecture (Qwen2.5-7B) and cross-domain (MMLU-STEM). Three convergent lines of evidence suggest representational entanglement: the OT direction has 85-88% overlap with task-critical computation (specificity ratio <= 0.152); non-targeted shared-direction steering damages accuracy (-12.1pp); and LEACE concept erasure damages accuracy (-3.6pp, p=0.01), while 10 random erasures produce Delta=+0.3pp. The per-instance probe-steering correlation is r=-0.002 (p=0.97). Positively, the same probe enables selective abstention (held-out AUROC=0.610, exceeding all five uncertainty baselines, p=0.009): decodable failure structure supports post-generation reliability estimation even when the fixed linear steering family cannot exploit it for correction.

Large Language Models (LLMs) perform strongly on many language tasks, but their capability in structurally constrained, accessibility-critical modalities such as Braille remains unclear. We evaluate state-of-the-art LLMs on bidirectional Korean-Braille translation using a human-annotated dataset. Despite expectations that multilingual, instruction-tuned models can generalize to Braille via text representations, we find consistently poor, unstable outputs and substantial disagreement with human judgments. These results point to missing Braille-aware tokenization and weak alignment between Korean and Braille patterns. In contrast, supervised fine-tuning of a small model (T5-small) on the same data yields large and stable gains over zero-shot and prompted LLM baselines across standard metrics (SacreBLEU, ChrF++, CER, BLEU, ROUGE-L, METEOR, CIDEr). Our findings reveal a systematic limitation of current LLMs and demonstrate the effectiveness of modest task-specific supervision.

Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit semantic structure. These attacks generally operate by fixing an adversarial instruction and optimizing small adversarial components (e.g., suffixes or prefixes). In this setting, prompt structure is fundamental for performance, and recent results show that even simple random search can achieve strong performance when combined with sophisticated prompt design. Recently, it has been observed that harmful behaviors can be elicited even without the adversarial prompt, relying solely on optimized token sequences. This suggests the existence of natural backdoors, i.e., token sequences naturally emerged during LLMs training that trigger unsafe outputs without any meaningful instruction. However, despite these observations, this setting remains largely unexplored, and in particular the hardness of finding natural backdoors has not been assessed yet. In this work, we provide a first proof-of-concept study investigating the hardness of this task, which we refer to as the junking problem. We formalize it as the problem of finding token sequences that maximize the probability of generating a target prefix of harmful responses, propose a greedy random-search method to assess is such sequences can be discovered easily. Our results show that this problem is harder than standard jailbreak attacks, confirming the importance of semantic information in prompt design. At the same time, we find that our simple strategy is sufficient to solve it with a high success rate, suggesting that natural backdoors are present and easily recoverable. Finally, through perplexity analysis, we observe that the discovered token sequences lie in low-probability regions of the model distribution, supporting the hypothesis that they emerged implicitly from the training process.

LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled multi-timescale dynamics make new associations immediately usable, strengthen what repetition confirms, and let the rest fade. We argue that external memory should follow a similar principle. In Memini, this view takes the form of an associative memory that organizes knowledge as a directed graph. Each edge carries two coupled internal variables, one fast and one slow, following the Benna-Fusi model of synaptic consolidation. From this coupling, episodic sensitivity, gradual consolidation, and selective forgetting are expected to emerge as facets of a single mechanism, reframing external memory as a learning substrate that reorganizes through its own dynamics. This workshop article describes an early-stage conceptual design without experimental evaluation.

LLM-based Triton kernel generation has attracted significant interest, yet a fundamental empirical question remains unanswered: where does this capability break down, and why? We present KernelBenchX, a benchmark designed to answer this question through category-aware evaluation of correctness and hardware efficiency across 176 tasks in 15 categories. Our systematic comparison of five representative methods yields three main findings. First, task structure determines correctness more than method design. Category explains nearly three times more variance in semantic correctness than method (9.4% vs 3.3% explained deviance), and 72% of Fusion tasks fail across all five methods while Math tasks are solved consistently. Second, iterative refinement improves correctness, but not performance. Across GEAK iterations, compile rate rises from 52.3% to 68.8% while average speedup declines from $1.58\times$ to $1.44\times$; newly rescued kernels consistently underperform persistently correct ones ($1.16\times$ vs $1.58\times$ speedup in round~0$\to$1). Third, correctness does not imply efficiency. 46.6% of correct kernels are slower than the PyTorch eager baseline, and cross-hardware speedup variance reaches $21.4\times$. Besides, quantization remains completely unsolved (0/30 successes) despite non-trivial compilation rates, revealing systematic misunderstanding of numerical computation contracts rather than surface-level syntax errors. These findings suggest that future progress depends on handling global coordination, explicitly modeling numerical precision, and incorporating hardware efficiency into generation. The code is available at https://github.com/BonnieW05/KernelBenchX

Large language models are increasingly used as surrogate models for low-data optimization, but their optimizer-facing prediction and its uncertainty remain poorly understood. We study the surrogate belief elicited from an LLM under sparse observations, showing that it depends strongly on prompt text and query protocol. We introduce an uncertainty-alignment criterion that measures whether model uncertainty tracks residual ambiguity among sample-consistent functions. Across controlled inference tasks and Bayesian optimization studies, we find that structural prompts act as effective priors, POINTWISE and JOINT querying induce different beliefs, and sequential evidence leads to non-monotonic, order-sensitive confidence updates. These effects change downstream acquisition decisions and regret, showing that elicitation protocol is part of the LLM surrogate specification, not a formatting detail.

When the substantive content of a request is rewritten, do large language models still answer in the format the original task asked for? We find that they often do not, even at temperature zero. On a 150-query evaluation over five compact 2025-era LLMs and four task types, we observe a systematic failure mode we call prompt-variant output-mode collapse: when a closed-form prompt asks for a bare label or a single choice token, content-preserving prompt variants can push the model into conversational prose, the requested format dissolves, and exact-match evaluation pipelines silently misjudge the result. To make this measurable, we release PARACONSIST, a 900-prompt benchmark of 150 base queries with five lexical, syntactic, and semantic-expansion prompt variants each, and a Semantic Consistency Score that decomposes prompt-variant robustness into answer consistency, sentence-BERT semantic similarity, and length stability. Under a whole-word answer-set match, only ~22% of closed-form variant responses preserve the ground-truth label inside their output, while ~78% drift away from the answer space entirely. In our pool, the dominant predictor of collapse is task structure rather than model identity, with model differentiation jointly carried by answer consistency and length stability. Robustness audits should therefore track response-mode preservation as a first-class reliability target alongside answer accuracy.

Recent analyses question whether reinforcement learning (RL) is responsible for strong reasoning in large language models (LLMs). At the same time, distillation and inference-time sampling, including power sampling, have emerged as effective ways to improve LLM performance. However, the relationship among RL, distillation, and sampling remains unclear. In this study, we focus on the power distribution, the target distribution of power sampling, and show that the power distribution bridges sampling, self-reward KL-regularized RL, and self-distillation. From the sampling perspective, we show that inexpensive local approximations cannot reproduce sequence-level power without information about possible suffixes. From the RL perspective, the power distribution is the closed-form optimizer of KL-regularized RL when the model's sequence-level log-probabilities are used as the reward. This identification leads to power self-distillation, an offline distillation surrogate that shares the same target distribution and amortizes the cost of power sampling into supervised training on teacher samples. We further show that power self-distillation can achieve self-reward sharpening, while improvement in a downstream true reward is governed by the covariance between true reward and self-reward under the power distribution. Experiments on reasoning tasks support our analysis: power sampling raises self-reward, true-reward gains depend on alignment with self-reward, and power self-distillation can match or exceed the performance of power sampling at much lower inference cost.

Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness. This blindspot leaves a logical alignment gap -- SFT models reach NLI entailment of only 0.05-0.22 despite producing fluent text. We propose RLearner-LLM with Hybrid-DPO: an automated preference pipeline that fuses a DeBERTa-v3 NLI signal with a verifier LLM score, removing human annotation while overcoming the "alignment tax" of single-signal optimization. Evaluated across five academic domains (Biology, Medicine, Law) with three base architectures (LLaMA-2-13B, Qwen3-8B, Gemma 4 E4B-it), RLearner-LLM yields up to 6x NLI improvement over SFT, with NLI gains in 11 of 15 cells and consistent answer-coverage gains. On Gemma 4 E4B-it (4.5B effective params), Hybrid-DPO lifts NLI in four of five domains (+11.9% to +2.4x) with faster inference across all five, scaling down to compact base models without losing the alignment-tax mitigation. Our Qwen3-8B RLearner-LLM wins 95% of pairwise comparisons against its own SFT baseline; GPT-4o-mini in turn wins 95% against our concise output -- alongside the 69% win the same judge gives a verbose SFT over our DPO model, this replicates verbosity bias on a frontier comparator and motivates logic-aware metrics (NLI, ACR) over LLM-as-a-judge for knowledge-intensive generation.

Large Language Models (LLMs) are democratizing access to personalized tutoring; however, their effectiveness is hindered by challenges in processing multimodal content, which limits AI's potential to provide equitable, high-quality STEM support. This study evaluates LLM performance on multimodal physics problems, identifies specific failure modes through an empirical error taxonomy, and tests practical interventions designed to overcome multimodal processing limitations. We assessed three publicly available LLMs (Claude, Gemini, and ChatGPT) on multimodal physics problems from the OpenStax database and compared the results with text-only performance. An empirically derived error taxonomy was developed through pilot testing, followed by evaluation of a structured multimodal dialogue intervention. All three models achieved near-ceiling accuracy (96%) on text-only physics problems. Performance declined substantially on multimodal problems, consistent with what we term the Multimodal Interference Effect. Error analysis identified four failure modes: visual processing errors, context misinterpretation, mathematical computational errors, and hybrid errors, with visual processing errors being the most prevalent. The structured dialogue intervention corrected 82% of errors overall; visual processing errors were corrected at 100% across all models. Educators and students can implement these interventions immediately, requiring no model retraining, to improve AI tutoring reliability on image-rich STEM content, advancing equitable access to high-quality learning support.

The visual environment is a fundamental yet unquantified determinant of mental health. While the concept of the environmental exposome is well established, current methods rely on coarse geospatial proxies or biased self reports, failing to capture the first person visual context of daily life. We addressed this gap by coupling ecological momentary assessment with vision language models (VLMs) to quantify the semantic richness of human visual experience. Across 2674 participant generated photographs, VLM derived estimates of greenness robustly predicted momentary affect and chronic stress, consistent with established benchmarks. We then developed a semi autonomous large language model (LLM) based pipeline that mined over seven million scientific publications to extract nearly 1000 environmental features empirically linked to mental health. When applied to real world imagery, up to 33 percent of VLM extracted context ratings significantly correlated with affect and stress. These findings establish a scalable objective paradigm for visual exposomics, enabling high throughput decoding of how the visible world is associated with mental health.

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms such as set theory, formal logic, and quantum mechanics -- bypasses these filters at high rates, achieving 46%--56% average attack success across eight target models and two established benchmarks. Crucially, the effectiveness depends not on mathematical notation itself, but on whether a helper LLM deeply reformulates the harmful content into a genuine mathematical problem: rule-based encodings that apply mathematical formatting without such reformulation perform no better than unencoded baselines. We introduce a novel Formal Logic encoding that achieves attack success comparable to Set Theory, demonstrating that this vulnerability generalizes across mathematical formalisms. Additional experiments with repeat post-processing confirm that these attacks are robust to simple prompt augmentation. Notably, newer models (GPT-5, GPT-5-Mini) show substantially greater robustness than older models, though they remain vulnerable. Our findings highlight fundamental gaps in current safety frameworks and motivate defenses that reason about mathematical structure rather than surface-level semantics.

Multimodal Large Language Models (MLLMs) have demonstrated robust capabilities in recognizing everyday human activities, yet their potential for analyzing clinically significant involuntary movements in neurological disorders remains largely unexplored. This pilot study evaluates the capability of MLLMs for automated recognition of pathological movements in seizure videos. We assessed the zero-shot performance of state-of-the-art MLLMs on 20 ILAE-defined semiological features across 90 clinical seizure recordings. MLLMs outperformed fine-tuned Convolutional Neural Network (CNN) and Vision Transformer (ViT) baseline models on 13 of 18 features without task-specific training, demonstrating particular strength in recognizing salient postural and contextual features while struggling with subtle, high-frequency movements. Feature-targeted signal enhancement (facial cropping, pose estimation, audio denoising) improved performance on 10 of 20 features. Expert evaluation showed that 94.3 percent of MLLM-generated explanations for correctly predicted cases achieved at least 60 percent faithfulness scores, aligning with epileptologist reasoning. These findings demonstrate the potential of adapting general-purpose MLLMs for specialized clinical video analysis through targeted preprocessing strategies, offering a path toward interpretable, efficient diagnostic assistance. Our code is publicly available at https://github.com/LinaZhangUCLA/PathMotionMLLM.

Travel planning serves as a critical task for long-horizon reasoning, exposing significant deficits in LLMs. However, existing benchmarks and evaluations primarily assess final plans in an end-to-end manner, which lacks interpretability and makes it difficult to analyze the root causes of failures. To bridge this gap, we decompose travel planning into five constituent atomic sub-capabilities, including \emph{Constraint Extraction}, \emph{Tool Use}, \emph{Plan Generation}, \emph{Error Identification}, and \emph{Error Correction}. We implement a decoupled evaluation protocol leveraging oracle intermediate contexts to rigorously isolate these components, thereby measuring the atomic performance boundary without the noise of cascading errors. Our results highlight a clear contrast in performance: while LLMs are proficient in extracting explicit constraints, they struggle to infer implicit, open-world requirements. Furthermore, they exhibit structural biases in plan generation and suffer from ineffective self-correction, characterized by excessive sensitivity and erroneous persistence. These findings offer precise directions for improving LLM reasoning and planning abilities.

Cross-lingual topic modeling aims to discover shared semantic structures across languages, yet existing models depend on sparse bilingual resources and often yield incoherent or weakly aligned topics. Recent LLM-based refinements improve interpretability but are costly, document-level, and prone to hallucination, with prior white-box approaches requiring inaccessible token probabilities. We propose LLM-XTM, a framework that integrates LLM-guided topic refinement with self-consistency uncertainty quantification, enabling black-box, stable, and scalable enhancement of cross-lingual topic models. Experiments on multilingual corpora show that LLM-XTM achieves superior topic coherence and alignment while reducing reliance on bilingual dictionaries and expensive LLM calls.

We study how Large Language Models (LLMs) process negation mechanistically. First, we establish that even though open-weight models often provide wrong answers to questions involving negation, they do possess internal components that process negation correctly. Their poor accuracy is due to late-layer attention behavior that promotes simple shortcuts; ablating those attention modules greatly improves accuracy on negation-related questions. Second, we uncover how models process negation. We consider two hypotheses: models could use attention heads that attend to the phrase being negated and suppress related concepts, or they could directly construct a representation of the entire negative phrase (e.g., representing "not gas" as a vector that promotes liquids and solids). We apply a range of observational and causal interpretability techniques on Mistral-7B and Llama-3.1-8B to show that models implement both mechanisms, with the "constructive" mechanism being more prominent. Combined, our work deepens the understanding of LLMs' internals, highlighting construction-dominant computations and the coexistence of competing mechanisms within LLMs.

Most hallucination evaluations focus on English, leaving it unclear whether findings transfer to lower-resource languages. We investigate faithfulness hallucinations, defined as model-generated content that is fluent and plausible but diverges from the provided input or is internally inconsistent. Leveraging the multilingual MultiWikiQA dataset, we utilize the LettuceDetect framework to create synthetic hallucination datasets for 306 languages, from which we train token-level hallucination classifiers for 30 European languages. In this work, we present evaluations of model hallucinations on a selection of languages: English, Danish, German, and Icelandic. Using these classifiers, we evaluate the hallucination rates for Qwen3-0.6B, Qwen3-14B, Gemma-3-12B-IT, cogito-v1-preview-qwen-32B, and cogito-v1-preview-llama-70B. Our classifiers reveal notably higher hallucination rates for Qwen3-0.6B (up to 60% of answers containing at least one hallucination, peaking in Icelandic) and generally lower rates for larger models, with cogito-v1-preview-qwen-32B and cogito-v1-preview-llama-70B performing best on most languages. Hallucination rates are consistently higher for lower-resource languages, particularly Icelandic.

Recent advances in agentic harness with orchestration frameworks that coordinate multiple agents with memory, skills, and tool use have achieved remarkable success in complex reasoning tasks. However, the underlying mechanism that truly drives performance remains obscured behind intricate system designs. In this paper, we propose HeavySkill, a perspective that views heavy thinking not only as a minimal execution unit in orchestration harness but also as an inner skill internalized within the model's parameters that drives the orchestrator to solve complex tasks. We identify this skill as a two-stage pipeline, i.e., parallel reasoning then summarization, which can operate beneath any agentic harness. We present a systematic empirical study of HeavySkill across diverse domains. Our results show that this inner skill consistently outperforms traditional Best-of-N (BoN) strategies; notably, stronger LLMs can even approach Pass@N performance. Crucially, we demonstrate that the depth and width of heavy thinking, as a learnable skill, can be further scaled via reinforcement learning, offering a promising path toward self-evolving LLMs that internalize complex reasoning without relying on brittle orchestration layers.

Bring-Your-Own-Key (BYOK) agent architectures let users route LLM traffic through third-party relays, creating a critical integrity gap: a malicious relay can modify an aligned LLM response after generation but before agent execution. We formalize this post-alignment tampering threat and show that, without end-to-end integrity, the relay can observe, suppress, or replace downstream messages, making even perfectly aligned LLMs ineffective against such attacks. We instantiate this threat as the Relay Tampering Attack (RTA), which performs multi-round strategic rewriting, minimal security-critical edits, and stealth restoration by resubmitting tampered outputs to the upstream LLM. Across AgentDojo and ASB with six LLMs, RTA achieves up to 99.1% attack success, outperforming prompt-injection baselines with modest overhead. Case studies on OpenClaw and Claude Code demonstrate real-world feasibility, and evaluations of four defenses show that none fully prevent RTA. Finally, we propose a time-based detection defense that mitigates RTA while preserving agent utility.

Agentic workflows in large language model systems integrate retrieval, reasoning, and memory, but existing frameworks suffer from scalability and reproducibility limitations due to fragmented data orchestration, serialization overhead, and non-deterministic execution. Although these frameworks increase flexibility, they don't have a formal execution model that adheres to the principles of high-performance computing. We introduce AAFLOW, a unified distributed runtime that creates communication-efficient execution plans by modeling agentic workflows as an operator abstraction. Using Apache Arrow and Cylon, AAFLOW creates a zero-copy data plane that allows direct interoperability between preprocessing, embedding, and vector retrieval without the need for serialization overhead. To lower coordination costs, it uses resource-deterministic scheduling and asynchronous batching. While retaining comparable LLM generation throughput, experimental results demonstrate up to 4.64 times pipeline speedup and 2.8 times gains in embedding and upsert phases. Rather than LLM inference acceleration, these advantages result from enhanced data flow, batching, and communication efficiency.

Open-ended surveys offer valuable insights, but they are notoriously difficult to analyze at scale. Building on previous work that employed traditional machine learning to classify text ("So Many Responses, So Little Time: A Machine-Learning Approach to Analyzing Open-Ended Survey Data") [1], this study investigates how different large language models (LLMs) understand and analyze NSSE open-ended survey responses. We focus on several cutting-edge LLMSs-OpenAI's GPT series, Twitter-roBERTa-base model, and Meta's LLaMA-and compare their performance to the previous machine learning models in tasks like sentiment analysis and thematic classification. Our research analysis assesses model agreement, classification accuracy, and interpretability of reasoning. The findings reveal that current LLMs routinely beat classic machine learning models in classification accuracy, particularly in understanding complex mood and theme patterns in student replies. While LLMs have superior accuracy, they differ greatly in how explicitly and consistently they justify their predictions and apply category boundaries. These distinctions highlight crucial trade-offs when using LLMs for qualitative analysis: increased predictive strength comes with issues in consistency and explainability. Our findings illustrate the benefits and drawbacks of utilizing various LLMs for large-scale qualitative research, and we provide practical advice for researchers looking to balance automation and interpretive rigor.

Conventional commits provide a structured format for writing commit messages, which improves readability, software maintenance, and enables automation tools such as changelog generators and semantic versioning systems. Existing approaches to conventional commit classification typically rely on ML/DL models trained on large labeled datasets. In this paper, we investigated a training-free alternative by leveraging large language models (LLMs) through prompt engineering. Rather than building a task-specific classifier, we evaluate three prompting strategies, such as zero-shot, few-shot, and chain-of-thought, across three open-source LLMs of varying scale: Mistral-7B-Instruct, LLaMA-3-8B, and DeepSeek-R1-32B. Classification is performed directly on code diffs extracted from a balanced dataset of 3,200 commits mined from the InfluxDB repository, without any model fine-tuning. Our results show that few-shot prompting consistently achieves the highest accuracy, while chain-of-thought prompting does not yield additional gains for this classification task. Among the evaluated models, DeepSeek-R1-32B achieves the strongest overall performance, suggesting that model scale plays a meaningful role in conventional commit classification. These findings provide practical guidance for researchers and practitioners seeking to automate commit classification without the overhead of curating and maintaining labeled training data.

Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes. While finetuning can create the catastrophe forgetting issue, application of meta-learning on LLMs is also limited due to its complexity and scalability. In this paper, we activate the meta-signal of $β$ within the SwiGLU blocks, resulting in a meta-gating mechanism that adaptively adjusts the nonlinearity of FFN. A hypernetwork is employed which dynamically produces $β$ on textual conditions, providing meta-controllability on LLMs. By testing on different condition types such as task, domain, persona, and style, our method outperforms finetuning and meta-learning baselines, and can generalize reasonably on unseen tasks, condition types, or instructions. Our code can be found in https://github.com/AaronJi/MeGan.

Large Language Models (LLMs) have substantially advanced the field of Natural Language Processing (NLP), achieving state-of-the-art performance across a wide range of tasks. These improvements have been attributed, in part, to their emerging reasoning capabilities, which are enabled by large-scale training and increased model capacity. However, existing LLMs can generate erroneous responses when addressing complex queries that fall outside their training distribution, due to limited internal knowledge or the need for multi-step reasoning. To address these limitations, recent work has introduced large reasoning models (LRMs), which incorporate explicit internal reasoning processes to improve response accuracy. Additionally, state-of-the-art LRMs often comprise hundreds of billions of parameters and require several seconds per inference, even on advanced multi-GPU systems. These characteristics limit their practicality for deployment in conventional computing environments. Meanwhile, NLP research on multilingual LLMs continues to prioritize high-resource languages. However, these models exhibit limited performance in under-resourced languages, primarily due to insufficient language- and culture-specific training data. In this paper, we focus on Modern Greek, for which only a limited number of question answering (QA) datasets have been proposed, most of which are intended for model evaluation. To address this research gap in Greek QA, we make the following contributions: (i) CulturaQA, a high-quality LRM-generated and human-curated dataset, for Greek LLM training and evaluation; (ii) a memory-efficient LLM evaluation framework adaptable to diverse languages and QA tasks; (iii) Maistros 8B, a state-of-the-art open-weights Greek LLM developed via knowledge distillation and fine-tuning on CulturaQA; and (iv) a comprehensive evaluation of nine LLMs across nine human-curated Greek QA datasets.

Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to load-balance between the compute-bound prefill phase and the memory-bound decode phase. Under this design, prefill workers generate a KV cache that must be transferred to decode workers before generation can begin. With these workers residing on different physical systems, this transfer becomes a significant bottleneck to serving LLMs at scale, especially for long-input and agentic workloads. Existing lossless codecs are unsuitable here as they primarily target offline weight compression, run on CPUs, or use variable-length coding whose compression cannot keep up with KV production during prefill. We introduce SplitZip, a GPU-friendly lossless compressor for KV cache transfer that preserves KV tensors bitwise and integrates into existing serving frameworks without modifying model execution. SplitZip exploits redundancy in floating-point exponents of KV activations, encoding frequent exponent values with fixed-length codes and routing rare exponents through a sparse escape stream of (position, value). A calibrated top-16 exponent codebook eliminates online histogramming, while the regular dense path and sparse escape correction make both encoding and decoding efficient on GPUs. On real BF16 activation tensors, SplitZip achieves $613.3$ GB/s compression throughput and $2181.8$ GB/s decompression throughput, outperforming prior lossless compressors on the critical codec path. End-to-end transfer experiments show up to $1.32\times$ speedup for BF16 KV cache transfer, $1.30\times$ speedup for TTFT, and $1.23\times$ increase in Request Throughput. The same approach extends to FP8 KV caches, providing up to $1.14\times$ compression over native E5M2. Code is available at https://github.com/Intelligent-Microsystems-Lab/SplitZip