arXiv:2610.41391v1 Announce Type: new Abstract: Growing submission volumes have renewed interest in using large language models (LLMs) to support peer review. It remains unclear how such evaluation should be structured, how much the model matters, and whether LLM scores predict research impact. We evaluate five paradigms across three input representations and three LLMs on 232 stratified ICLR 2025 submissions. Direct absolute rating matches comparative ranking on rank correlation with human scor
arXiv:2610.41435v1 Announce Type: new Abstract: Given that AI agents can search the web broadly and deeply in real time, it is tempting to conclude that their outputs account for recent world events. We show that this conclusion does not hold in practice. While agents can search and easily find recent changes, the correctness of their responses depends on whether they search and what they search for. Popular agentic search benchmarks like BrowseComp cannot expose failures wherein agents do not r
arXiv:2610.41480v1 Announce Type: new Abstract: Fine-tuning a language model changes how it responds, but where is this fine-tuned behavior instantiated? To better understand this, we evaluate whether the change in model behavior arises only during the generation of the answer tokens where the change manifests, or whether altered processing of previous tokens causes it via the attention mechanism. For this, we patch the KV cache from a LoRA fine-tuned model into the unmodified base model, and vi
arXiv:2610.41482v1 Announce Type: new Abstract: Recursive textual memory can carry earlier errors into later updates, yet task performance alone does not establish memory reliability. We define self-consistency bias as the persistence of incorrect claims already present in the incoming memory. We present KEEPER, a comparative analysis of four auxiliary objectives along information-content and update-sensitivity axes within a shared recursive interface, examining how supervision targets relate to
arXiv:2610.41487v1 Announce Type: new Abstract: Long-context diffusion repeatedly pays for both token interaction and feed-forward computation. We formulate these costs as two separate budgets: the edges available to an attention graph and the experts activated for each token. This view connects local, dilated, and global attention with conditional expert computation without assuming that sparsity alone preserves document-level information. We specify normalized masked attention, distinguish den
arXiv:2610.41552v1 Announce Type: new Abstract: This study investigates the effectiveness of large pre-trained language models (LLMs) for knowledge entity relation extraction (KERE) from academic papers. Existing studies have examined individual types of LLM-based strategies and evaluated model performance using metrics such as precision and recall. To provide a broader evaluation, this study investigates multiple strategies, including closed-source LLM-based CoT prompting, LoRA-adapted open-sou
arXiv:2610.41553v1 Announce Type: new Abstract: Automatic assessment of textual CEFR levels is an important task in educational natural language processing. However, accurate CEFR level prediction remains challenging due to the naturally imbalanced distribution of CEFR levels and the ambiguous boundaries between adjacent levels. To address these challenges, we propose a unified training objective that combines focal loss with supervised contrastive learning. Focal loss mitigates class imbalance
arXiv:2610.41561v1 Announce Type: new Abstract: This study examines digital sovereignty in professional translation through a screening of computer-assisted translation tools and translation management systems, and a case study of migrating a translator's workstation from Windows to Linux. The framework combines three principles - Control, Continuity and Exit - with three practical requirements: native Linux operation, independence from mandatory external services, and independent access to esse
arXiv:2610.41574v1 Announce Type: new Abstract: Unlike autoregressive (AR) models, diffusion language models (DLMs) permit parallel token updates, flexible generation, and bidirectional attention, but leading systems rely on costly pretraining or full-model fine-tuning. We present Build Your Own DLM (BYOD), a generalizable LoRA-only recipe for parameter-efficient AR-to-DLM conversion. Without architecture-specific tuning, BYOD induces diffusion generation in Gemma 2 9B, Llama 3.1 8B, Qwen2.5 7B,
arXiv:2610.41576v1 Announce Type: new Abstract: We release Saidzoda-Tajik-LFM-2.6B, a Tajik adaptation of the 2.6B-parameter hybrid model LFM2.5-2.6B-Base, built for tool calling in Tajik on modest hardware. The recipe has two stages: LoRA continued pretraining (CPT) on 1,485,319 cleaned Tajik web documents for 3 epochs, then one epoch of supervised fine-tuning (SFT) on a mix of machine-translated Tajik tool calls, English tool calls kept as replay, and Tajik instructions. On a 174-item tool-cal
arXiv:2610.41661v1 Announce Type: new Abstract: Activation steering is an inference-time technique used to control or modify the behavior, tone, or safety properties of a large language model (LLM) without retraining the model's weights or editing its input prompt, but simply by adding a vector to its residual-stream activations. However, activation steering also changes the generated text in unintended ways, unrelated to intended behavior change, that are not well understood. Prior work has mea
arXiv:2610.37720v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models offer scalable capacity for Web applications, but uneven routing creates computation and communication bottlenecks. Existing placement and replication methods redistribute this workload, yet additional expert copies compete with token-related buffers for limited GPU memory. We present LRMoE, a memory-aware MoE training system that jointly recalibrates backward demand and balances the retained workload. During
arXiv:2610.37731v1 Announce Type: new Abstract: Model discrepancy may prevent a single calibration parameter from reproducing a physical response across the context domain. In addition, uncertainties in observations and contexts affect calibration and must be accounted for and quantified. We construct a family of localized posteriors by weighting observation likelihoods according to their proximity to a target context. Gaussian localization weights incorporate context uncertainty through covaria
arXiv:2610.37732v1 Announce Type: new Abstract: Many uses of language models end in a typed decision: a choice among a closed set of options, whose probabilities code can act on. Reading those probabilities from one forward pass is fast but often wrong on decisions that take several steps, such as arithmetic, counting, and date comparison. Letting the model think first fixes most of these errors, but costs seconds per decision instead of milliseconds. To pay for thinking only where it helps, Thi
arXiv:2610.37739v1 Announce Type: new Abstract: Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collection of such problems is still missing, and evaluating them on research-level problems remains challenging. We introduce OpenFrontiers, a cross-disciplinary resource that combines a structured corpus of open research problems with a retrospective benchmark of recently resolved problems in mathematics. The corpus records problem st
arXiv:2610.37786v1 Announce Type: new Abstract: Web agents require diverse, executable, and resettable website environments for reproducible training and evaluation. Human-assisted mirrors demand per-site engineering, while generative construction can diverge from specified real websites. Capture-and-replay preserves observations, with interaction coverage constrained by captured content and replay capabilities. We present WebAnything, a fully automated framework that reconstructs source-grounde
arXiv:2610.37809v1 Announce Type: new Abstract: LLM agents that answer questions over Web knowledge graphs are increasingly wrapped in checks derived from the graph's ontology, on the assumption that a formal schema makes a reliable judge. Yet a checker can be wrong as well: it can miss errors, and it can flag correct answers and push the agent into "fixing" them. Whether a curated ontology is worth its cost as such a judge, and how it compares with an ontology an LLM writes or a schema mined fr
arXiv:2610.37830v1 Announce Type: new Abstract: AI agents can now write software from a plain-English description, but code that runs is not the same as code that does what was asked. This gap matters most for smart contracts, the programs behind Web3 applications that move money on a blockchain and cannot be fixed once deployed. We ask how to check whether an AI-written contract behaves as it should, and where the requested behavior gets lost. We design an evaluation built on execution rather t
arXiv:2610.37849v1 Announce Type: new Abstract: AI agents that share a secret convention can coordinate through messages that look innocent, so a monitor that reads only the messages can miss them. We propose a behavioural test: a partner that uses a code reacts to the exact wording of a message, whereas an uninvolved agent placed in its seat does not. Partner--Outsider Positive Listening (PoPLi) is the difference between the two agents in how much their action changes when the message is reword
arXiv:2610.37851v1 Announce Type: new Abstract: Existing scientific-agent benchmarks rarely evaluate whether agents can reconstruct the exact molecular structures and generation workflows specified by sequencing protocols, a capability critical for analyzing customized sequencing assays. We introduce LibStructBench, a document-grounded benchmark for reconstructing sequencing-library structures and molecular workflows. Our experiments show that frontier agents often produce approximately correct
arXiv:2610.37859v1 Announce Type: new Abstract: Language-model agents differ fundamentally from prior intelligent systems in their ability to learn from natural language in context. This capability enables agents to iteratively refine their answers in response to feedback, a prevalent mode of operation in modern agentic workflows. However, the community primarily ranks models by metrics such as Pass@1 or Pass@K, which cannot capture how they utilize feedback on prior attempts. We introduce Seq@K
arXiv:2610.37867v1 Announce Type: new Abstract: Food similarity underlies retrieval, recommendation, substitution, and other food computing tasks, yet food representations are typically evaluated by identity preservation. We ask what happens to food similarity beyond identity: how different visual representations organize foods into relational neighborhoods, what culinary relationships these neighborhoods reveal or obscure, and how consistently these structures emerge across representations. Ind
arXiv:2610.37875v1 Announce Type: new Abstract: Accurate AI assistance can improve immediate judgments while reducing opportunities to practise the operations needed for independent performance. Verification Learning Theory (VLT) formalises this possibility for claim-evaluation practice followed by correct, independent, rule-specific feedback. The model links perceived assistant reliability to evidence checking and links the history of those checks to retained rule use. Its strict form assumes t
arXiv:2610.37896v1 Announce Type: new Abstract: Subjective judgments such as offensiveness often vary substantially across individuals, motivating pluralistic modeling approaches that incorporate annotators' socio-demographic information to capture this variation. However, prior findings on the benefits of socio-demographic information for pluralistic modeling are mixed, calling for a systematic analysis of both its effectiveness and the mechanisms through which it improves prediction. In this w
arXiv:2610.37905v1 Announce Type: new Abstract: Public disclosure repositories such as SEC EDGAR support informed investment through web access to corporate filings. Supporting their review with language model agents requires discovering unstated deficiencies across related documents, acquiring missing company facts, and verifying that requested revisions satisfy evidence-backed requirements. Existing financial question-answering evaluations provide limited evidence of these interactive capabili
arXiv:2610.37906v1 Announce Type: new Abstract: Spiking reservoir computing combines the training efficiency of fixed recurrent reservoirs with the energy efficiency of event-driven inference, where computation is triggered by sparse spikes rather than executed densely at every timestep. However, existing spiking reservoirs almost exclusively rely on Leaky Integrate-and-Fire (LIF) neurons, whose low-pass dynamics limit their ability to distinguish information encoded at different temporal freque
arXiv:2610.37919v1 Announce Type: new Abstract: Large language model agents are increasingly used for scientific discovery. However, existing benchmarks mix law inference with programming, score data fitting instead of prediction on unseen inputs, and do not separate empirical evidence from pretrained priors. We introduce SciGame, a controlled benchmark that converts scientific literature into structured scientific cards. Each card yields a pair of Original and dimensionally consistent Counterfa
arXiv:2610.37923v1 Announce Type: new Abstract: Across human history, knowledge has undergone several transitions, from orality to writing and then to digital archives. At each transition, humans established new conventions to preserve knowledge for the new era. Nowadays, as research agents are increasingly deployed for laboratory experiments, knowledge is crossing another boundary: from records written for humans to those for machines. In this work, we introduce VerifiedLab, a multi-agent harne