Named after the hundred-eyed watchman of Greek myth, Argus watches the education landscape: spotting new opportunities, pressure-testing the ventures we're building, and tracing every read back to the real-world signals behind it.
The evidence library: the raw signals the pipeline is watching across the education ecosystem. Every idea is built from these.
arXiv:2608.05447v1 Announce Type: new Abstract: Document-level text simplification requires large language models (LLMs) to rewrite complex documents while preserving meaning, readability, and discourse coherence. Although prompt-based LLMs have shown promising performance, they often produce inconsistent simplifications because textual instructions alone provide limited guidance for complex document-level transformations. We investigate whether retrieved document-simplification examples can improve document-level generation by augmenting prompts with examples selected from a parallel simplification corpus. This example-guided prompting approach enables LLMs to exploit relevant simplification patterns without task-specific fine-tuning. Experiments on the OneStopEnglish corpus using multiple state-of-the-art LLMs show that incorporating retrieved examples consistently improves simplification quality over prompt-only generation and achieves competitive or superior performance compared wi
arXiv:2608.05409v1 Announce Type: new Abstract: Large language models typically undergo post-training to align them with safety policies but there exist many sophisticated jailbreaks that sidestep established safeguards. For instance, prior work by Andriushchenko et al. (2025) has found that changing the grammatical tense from present to past can be enough to elicit harmful responses. In this work, we uncover a more general failure of non-imperative syntactic forms. We demonstrate that this syntactic vulnerability exists in 16 models up to 70B parameters, using behavioral evaluation. To investigate the root cause, we apply causal mediation analysis, finding that refusal is partially conditioned on upstream syntactic features. By steering these purely syntactic features we are able to trigger and suppress refusal. Finally, we trace this ill-conditioning to linguistically biased post-training data of open-source models and show that increasing syntactic diversity can mitigate the issue.
arXiv:2608.05364v1 Announce Type: new Abstract: This chapter explores the intricate interplay between intonation and tone in Mandarin Chinese varieties, focusing on f0, the primary acoustic cue for both intonation and tone. The main empirical base is intonation boundary phenomena, where intonation and tone intersect and influence each other in conveying a range of sentence-level linguistic functions -- such as question vs. statement -- and a rich array of speakers' attitudinal information. Theoretical models and emerging techniques are also discussed to account for the observed interactions of tonal aspects and boundary phenomena to convey multiple levels of communicative meanings.
arXiv:2608.05353v1 Announce Type: new Abstract: LLM judges are often asked to extract criteria and evidence before choosing between candidate answers. This workflow assumes that the intermediate record preserves the information needed for a later verdict. For reasoning-capable models, visible field order does not reveal internal decision order, so we test an observable alternative: persist the evidence in one call and make it the exclusive input to the next. Across 24,000 judgments over HelpSteer3, FeedbackQA, and CoVal, we compare standard pairwise judging, structured one-call judging, two-call evidence locking, and three-call pointwise locking with Claude Sonnet 4.5 and GPT-5. Evidence locking reduces agreement with released human preferences by 4 to 6 percentage points and increases answer-order inconsistency by 8 to 10 points relative to structured one-call judging. Pointwise locking is also harmful, while structured evidence elicitation remains close to standard judging. The resul
arXiv:2608.05254v1 Announce Type: new Abstract: Large language models can derive a plausible mathematical object yet still violate explicit requirements--for example, by omitting a modular reduction, returning a non-integer, or using the wrong encoded answer form. We introduce Constraint-First Reasoning (CFR), a training-free two-stage prompting protocol: Stage 1 extracts and summarizes constraints entailed by the problem, and Stage 2 solves while checking intermediate and final results against that summary. Routed-CFR activates the two-stage protocol only when a text-only regex router detects restrictive cues; otherwise it uses direct chain-of-thought (CoT). Across AIME, CMIMC, BRUMO, and AIMO_AMC, the method improves direct CoT on multiple backbones. We further report convention-controlled routing experiments, matched prompting baselines, problem-level paired tests, decoding robustness, constraint-quality audits, total-token accounting, and an OlympiadBench evaluation. These analyses
arXiv:2608.05232v1 Announce Type: new Abstract: The work of Tang et. al. (2025) on numerical translation is extended by analysing the capability of five large language models (LLMs) for the localisation of times, numbers, and dates instead of translation. Models were selected that could be loaded onto and run on commodity hardware and a baseline quality for each mode is computed, then three different strategies to improve on that accuracy were tested. In contrast to Tang et. al., it was discovered that on the tested LLMs, embedding the localisation principles into the prompt context provided a statistically significant improvement in accuracy compared to direct translation or the alternative strategies.
arXiv:2608.05188v1 Announce Type: new Abstract: Despite ever-increasing sophistication in language model (LM) pre- and post-training pipelines, many important failures persist: models overcondition on user framing ("sycophancy"), exhibit incomplete logical generalization, and produce confident but incorrect responses. We argue that these failures arise from a modeling assumption permeating all aspects of the pipeline: that behavior can be specified and evaluated independently on single-output pairs. Many model failures are difficult, if not impossible, to detect without reasoning about relationships between a model's responses across inputs. In this position paper, we propose self-consistency as a framework for understanding these failures. We first observe that a wide variety of techniques designed to improve specific aspects of LM behavior-targeting properties as diverse as adversarial robustness and factual coherence-can be understood as special cases of a common "consistency optimi
arXiv:2608.05170v1 Announce Type: new Abstract: Role-playing agents (RPAs) have emerged as a key application of large language models, enabling immersive and high-fidelity character simulation. Accurate role-playing of established characters requires not only stylistic imitation but also temporally consistent and causally grounded behavioral reasoning. However, existing RPAs primarily rely on static character descriptions and unstructured memory, limiting their ability to maintain long-term narrative and personality coherence. We introduce DREAM, a structured memory framework for role-playing agents inspired by the Activating Event-Belief-Consequence (ABC) cognitive model. DREAM transforms unstructured literary text into an Event-aware Memory Graph (EMG) that organizes character experiences into temporally ordered and causally linked event graph. This representation enables the construction of dynamic, dual-granularity character profiles that capture both stable personality traits and
arXiv:2608.05169v1 Announce Type: new Abstract: Long-form story generation requires models to preserve narrative consistency across extended contexts, yet existing prompting-based methods often accumulate temporal, factual, character, commonsense, and stylistic errors as the story grows. We propose ConWriter, a training-free framework for consistency-aware long story generation. ConWriter writes stories incrementally at the scene level, guided by static story requirements, dynamic narrative memory, symbolic state reasoning, and uncertainty-aware risk signals. Rather than treating long-story generation as a single free-form decoding process, ConWriter maintains evolving story states, checks whether new scenes satisfy required narrative transitions, and uses uncertainty-aware risk signals to prioritize validation and localized repair. This enables consistency control during generation, before local errors propagate into later scenes. We evaluate ConWriter on ConStory-Bench, covering four
arXiv:2608.05167v1 Announce Type: new Abstract: Token-based encoders like BERT treat Chinese characters as atomic identifiers, ignoring their recursive orthographic structure. Consequently, models rely on contextual co-occurrence, degrading performance on rare and out-of-vocabulary (OOV) characters. We propose the Compositional Network Model (CNM), a lightweight augmentation that injects discrete compositional structure into Transformer encoders. CNM parses Ideographic Description Sequences (IDS) into trees, encodes them via a recursive Tree-MLP, and fuses the structural embeddings into BERT without modifying the backbone. Evaluated on the Wu et al. (2025) structural-probing benchmark, CNM-BERT outperforms the strongest baseline (ChineseBERT) on long-tail and OOV characters by +9.8 Structure accuracy and +7.7 Radical F1. Furthermore, CNM-BERT achieves consistent gains across CLUE, MRC, and NER tasks at both base and large scales, demonstrating that explicit structural injection deliver
arXiv:2608.05165v1 Announce Type: new Abstract: Speech Emotion Recognition (SER) in low-resource languages remains a challenging problem due to limited labeled data. In this work, we study the use of Whisper for Persian SER with a particular focus on representation dimensionality reduction and language-specific model adaptation. We propose a SER framework in which frame-level embeddings extracted from the Whisper encoder are reduced in dimensionality using PCA, eliminating the need for learned projection layers and substantially reducing the number of trainable parameters. The reduced representations are aggregated using an attention-based pooling mechanism and classified with a lightweight prediction head. In addition, we investigate whether fine-tuning Whisper on a Persian automatic speech recognition (ASR) task improves downstream SER performance. Experiments conducted on the ShEMO dataset under a speaker-independent evaluation protocol show that PCA-based dimensionality reduction c
arXiv:2608.05164v1 Announce Type: new Abstract: Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but whether this geometric similarity has functional consequences for cross-model behavioural control remains untested. We present the first systematic evaluation of cross-model steering transfer and show that shared LLM geometry is functionally exploitable, conditionally: concept directions from one model can steer a different independently trained model when sufficient representational capacity exists. We study five open-weight models spanning three parameter scales (0.8B--8B) and two architectural lineages, training one Sparse Autoencoder per model across 15 semantic domains and testing alignment across all 20 directed model pairs. We observe a suggestive discontinuity near 1.7B parameters: at >= 1.7B scale, 47--49% of cross-model feature pairs validate (Pearson r >= 0.60, Procrustes cosines
arXiv:2608.05163v1 Announce Type: new Abstract: A common assumption holds that switching to a non-English language makes a multilingual RAG system easier to attack for personal information. We test this on an English-source synthetic-PII corpus with five query languages and a two-stage defence (LLM input judge + regex output filter), in a pipeline whose translator, judge, back-translator, and generator are all Qwen2.5-7B -- so every finding below is pipeline-conditional, not a causal ranking of language-inherent risk. Under output-only filtering, English has the highest observed unstructured-PII leak rate; only English-vs-Swahili separates cleanly under document-level bootstrap intervals. Once the input judge is added, residual leaks remain on Arabic and Swahili, and back-translating the query does not close the gap (an ablation we report but cannot use as a causal diagnostic, since the back-translator is also Qwen). On a separate n=17 multilingual-prompted-judge residual corner, attac
arXiv:2608.05162v1 Announce Type: new Abstract: Pooling is a consequential but under-examined design choice in decoder-only concept representation work: practitioners must collapse token-level hidden states into a passage-level vector, yet no shared protocol exists for comparing this choice across concepts, models, and tasks. Reported gains are confounded by simultaneous changes in dataset, layer, construction method, and pooling rule, making principled decisions impossible. We introduce PoolBench, a benchmark that isolates pooling as the experimental variable under a fixed evaluation protocol. PoolBench covers 17 concepts, 19 pooling strategies, and 3 open-weight decoder-only models (Llama-3.1-8B, Gemma-2-9B, Mistral-7B), evaluated on a single audited corpus of 37,693 real-text passages. The primary axis is linear separability (D1/AUROC); steered concept prevalence (D2/SCP) and output-level disentanglement (D3) serve as diagnostic axes. The primary finding is decisive: W4_hierarchical
arXiv:2608.05161v1 Announce Type: new Abstract: Instruction-tuned LLMs are deployed into environments where domains evolve, yet extending a fine-tuned model's capabilities without full retraining remains an unsolved practical challenge. We present SemiAdapt-Instruct, a modular framework that discovers latent instruction domains, trains per-domain LoRA adapters in parallel, and performs parameter-free routing, incorporating new domains via single-adapter training without modifying existing components. SemiAdapt-Instruct outperforms full model fine-tuning across all configurations on both ROUGE-L and LLM-as-a-judge evaluation, while matching single LoRA fine-tuning and delivering extensibility that monolithic approaches cannot provide. We empirically demonstrate this extensibility by showing that updating a single adapter with new domain data outperforms all monolithic baselines. Our study also finds that independent discovery methods converge on the same specialisation-friendly domains.
arXiv:2608.05158v1 Announce Type: new Abstract: In biological evolution, unconstrained mutation can lead to catastrophic outcomes: organisms may evolve enhanced capabilities while losing essential functions for survival. Nature's solution is \textit{developmental constraints}, where core regulatory genes remain anchored while peripheral genes adapt freely. We observe that current self-evolution algorithms for large language models lack analogous constraints. They optimize purely for capability, implicitly assuming safety will be preserved. Our experiments reveal this assumption to be dangerously wrong: models can \textit{misevolve} into powerful yet dangerous entities. Inspired by how Hox genes anchor body structure across $500$ million years of evolution, we propose \textbf{Circuit-Anchored Evolution (CAE)}. Using mechanistic interpretability, we identify a tiny \textit{safety circuit}, comprising less than $2$\% of model features, that causally mediates safety behaviors. We anchor th
arXiv:2608.05157v1 Announce Type: new Abstract: Double blind peer review serves as the scientific community primary defense against status and affiliation bias. Its effectiveness rests on the assumption that anonymized manuscripts convey scientific merit without revealing their authors. While authorship can often be recovered using citation networks or stylistic markers, we show that this assumption is increasingly fragile in the presence of large language models (LLMs). Using only titles and abstracts from papers published after model training, we find that LLMs collapse anonymity more efficiently than humans, with belief concentrating onto a small subset of plausible authors drawn from pools of five domain expert candidates. This vulnerability persists even when stylistic and bibliographic cues are excluded, indicating that stable patterns in problem framing and research focus function as latent conceptual signatures of authorship. Together, these findings indicate that double blind
arXiv:2608.05156v1 Announce Type: new Abstract: Post-training of large language models optimizes only parameters, while inference-time procedural scaffolds are typically designed independently of parameter training. This disconnect makes it difficult to automatically acquire and internalize complex strategies. We propose scaffold-mediated post-training: procedural scaffolds are organized into an evolvable graph structure that co-evolves with model parameters through discovery, distillation, and dynamic recompilation. We instantiate this paradigm as Skill Training. On FeatureBench, automatically discovered skills improve the passed rate by 8.1pp, and after progressive distillation the model still achieves a 27.7% passed rate without any external scaffold (distillation retention rate 85.2%, defined as post-distillation / with-skill passed rate), significantly outperforming standard SFT on the same data.
arXiv:2608.05155v1 Announce Type: new Abstract: Traditional sentiment analysis (SA) models, while effective for polarity classification, provide limited insight into the rhetorical, ideological, and framing dimensions of political discourse -- dimensions that are central to research in the social sciences and humanities (SSH). In this paper, we present a comparative study of RoBERTa-based sentiment analysis and an LLM-based multi-dimensional framing analysis platform applied to a corpus of 50 political news articles from 17 international media outlets. The results reveal a critical limitation we term neutral collapse: RoBERTa classifies 70% of articles as neutral, effectively flattening substantively rich political content into an analytically uninformative category. We find that 23% of neutral-classified articles exhibit negative probability scores above 0.30. By contrast, the LLM-based approach captures political bias direction and intensity, sensationalism, emotional appeal, and pol
arXiv:2608.05154v1 Announce Type: new Abstract: Rotary positional encoding (RoPE) is a core component of modern language models and has been extended to multimodal LLMs through multidimensional variants such as multimodal RoPE (M-RoPE), which split positional channels into temporal, height, and width subspaces. This report identifies two limitations of static multidimensional position assignment in interleaved multimodal contexts. First, height/width rotations may be applied to token pairs whose spatial displacement is not a well-defined geometric object, producing cross-modal and inter-instance spatial interference. Second, temporal coordinates are often treated as equal-step counters, so a text token, an image block, and a video segment can advance the temporal phase by comparable amounts despite different information density. We propose RIG-RoPE, a relation- and instance-gated RoPE mechanism with duration-aware temporal coordinates. RIG-RoPE augments each token with a modality indic
arXiv:2608.05153v1 Announce Type: new Abstract: GraphRAG underperforms vector RAG on citation precision in many reports, but where and why have remained corpus-bound. We present a triple-robustness analysis that holds the retrieval architecture fixed and varies three orthogonal axes embedder (local e5-small -> Azure text-embedding-3-small), corpus (DO-178C typed-edge requirements -> Wikipedia paragraph chains via MuSiQue), and judge (paired GPT-5.4 x GPT-4.1) across 4,440 main-matrix runs, 600 cross-corpus runs, and 1,200 paired faithfulness judgments. (C2a) Over-citation is architecturally universal: GraphRAG emits 11-15 IDs per answer at citation precision 0.12-0.23 and retrieval recall 0.68-0.87 across all three settings. (C2b) Its faithfulness consequence is corpus-conditional: in typed-edge DO-178C, GraphRAG faithfulness collapses 74%->40% across hops; on Wikipedia chains the same pipeline rises 42%->58% because over-cited paragraphs remain topically supporting. (C1) Stratum-condi
arXiv:2608.05152v1 Announce Type: new Abstract: Large language models (LLMs) with chain-of-thought reasoning have been widely applied in recent years, and theoretical explanations of their behavior may help deepen our understanding and guide model optimization. In this study, we introduce a framework that seeks statistical regularities and theoretical interpretations in LLM reasoning without simplifying the model architecture or making analogies to existing physical systems. We formulate LLM reasoning as a guided discovery process on a clue graph, and derive a one-dimensional ordinary differential equation for the fraction of discovered clues using the mean-field approximation. Experimentally, clue tokens are identified using the normalized surprisal of a student LLM on the outputs of a teacher LLM, and statistical regularities are obtained by averaging over many reasoning chains of thought. Our experiments show that the resulting statistical regularities are reproducible within the sa
arXiv:2608.05151v1 Announce Type: new Abstract: Wastewater operators need answers grounded in how their plant's variables interact and how fast effects propagate, not in generic pretraining text, when asking causal questions such as "why is N2O rising?" or "what happens if I cut aeration by 20%?". We compare three concrete ways to ground a frozen Qwen2.5-32B-Instruct model in an architecturally interpretable wastewater simulator (CCSS-IX): a live simulator oracle (Method 1), structured parameter injection (Method 2), and a Decoupled Recall-Reasoning (DRR) retriever (Method 3). On a 198-question causal benchmark the three reach 99.5%, 79%, and 75.8%, forming a deployment ladder above the strongest retrieval-augmented baseline at 48%. The DRR retriever has 110M parameters and trains per plant in ~17 seconds; after cross-plant transfer to a biologically distinct plant it still reaches 88%, while Method 2's static table cannot transfer. On a 60-question counterfactual benchmark only Method
arXiv:2605.00025v3 Announce Type: replace-cross Abstract: Speech neuroprosthesis systems decode intended speech from neural activity in the absence of audible output, offering a path to restoring communication for individuals with speech-impairing conditions. Current approaches decode predominantly from motor cortical areas, discarding others -- such as area 44, part of Broca's area -- that may encode complementary linguistic information. We introduce MoDAl (Modality Decorrelation and Alignment), a framework that discovers complementary neural modalities through the interplay of two objectives in a shared projection space. A contrastive loss aligns each of several parallel brain encoders with the text embeddings of a pretrained large language model (LLM), while a decorrelation loss prevents the encoders from coalescing to duplicative representations. We prove that these objectives are in productive tension: Contrastive alignment induces transitive modality coalescence, which decorrelat
arXiv:2606.15536v2 Announce Type: replace Abstract: The growing use of large language models (LLMs) by young adults seeking sensitive health information has raised important questions in Human-AI Interaction about how these systems can support understanding and navigation of reproductive well-being. In response to Feminist HCI principles, we introduce OpenBloom, a web application and an exploratory design probe that uses LLMs to generate question-based prompts from reproductive health articles. Through a user study with 34 young adults across 136 interactions with OpenBloom, we provide an initial assessment of the system while exploring how participants' reflections engage with culture and value sensitivities. We found that while OpenBloom outputs meet expectations of "safe" and non-offensive, they tend to paraphrase or rely on factual recall, which may lead to value dilution. We discuss implications under contestability and value-sensitive frameworks for future LLM-mediated reproducti
arXiv:2604.22356v2 Announce Type: replace Abstract: This study examined whether counterarguments generated by large language models (LLMs) influence the moral judgments of younger and older adults, and whether these effects vary by dilemma type, cognitive functioning, trust in AI, and prior LLM experience. Using the switch and footbridge trolley dilemmas, 130 participants (56 younger adults and 74 older adults) were presented with ChatGPT-generated counterarguments that opposed their initial judgments. More than 30% of participants reversed their judgments in both dilemmas (32.31% in the switch dilemma and 36.92% in the footbridge dilemma). Older adults tended to be more likely than younger adults to reverse their judgments and showed a significantly greater degree of judgment change in the switch dilemma. In the emotionally aversive footbridge dilemma, older adults with lower cognitive functioning were significantly more likely to align with the LLM-generated counterargument. General
arXiv:2604.03604v2 Announce Type: replace Abstract: While multilingual users often switch between languages when seeking information, this process remains undersupported by current systems where information is typically siloed by language. Our formative study reveals that users select their search language based on its perceived value for their current information need, a concept we formalize as language scent. Language scent extends Pirolli and Card's information foraging theory - which explains how users navigate among already-encountered sources - to the multilingual case, where users' choice of query language determines which sources they can encounter in the first place. Building on this insight, we designed Niffler, a multilingual information seeking system that provides proximal cues for gauging the language scent of different languages. Finally, we conducted a lab study with 16 multilingual speakers to understand Niffler's utility, usage patterns and application contexts.
arXiv:2603.14158v2 Announce Type: replace Abstract: Large language models (LLMs) are entering clinical workflows, yet evaluations rarely assess how clinician reasoning shapes model behavior during clinical interactions. Using 61 curated NEJM Case Records, we tested how expert or misleading clinician reasoning influenced AI-generated differential diagnoses and next step recommendations across 21 reasoning variants from 8 proprietary and open-source models. After clinician exposure, LLM-clinician concordance increased: simulations with >=3 overlapping differential diagnoses rose from 65.8% to 93.5%, and those with >=3 overlapping next step recommendations from 20.3% to 53.8%. Expert context significantly improved correct final-diagnosis inclusion in all 21 models (mean +20.4 pp), reflecting both improved reasoning and passive content echoing, while adversarial context significantly degraded performance in 14 models (mean -5.4 pp). Expert context also significantly increased leading-diagn
arXiv:2511.13480v2 Announce Type: replace Abstract: This study focuses on understanding the complex dynamics between humans and AI systems by analyzing user reviews. While previous research has explored various aspects of human-AI interaction, such as user perceptions and ethical considerations, there remains a gap in understanding the specific concerns and challenges users face. By using a lexical approach to analyze 55,968 online reviews from G2.com, Producthunt.com, and Trustpilot.com, this preliminary research aims to analyze human-AI interaction. Initial results from factor analysis reveal key factors influencing these interactions. The study aims to provide deeper insights into these factors through content analysis, contributing to the development of more user-centric AI systems. The findings are expected to enhance our understanding of human-AI interaction and inform future AI technology and user experience improvements.
arXiv:2608.06257v1 Announce Type: cross Abstract: Current video world models struggle in multiplayer environments because they entangle world state with view-dependent visual latents, leading to redundant compute, view inconsistencies, and poor scalability. We propose MAS (Multiplayer world models with Authoritative Shared State) to resolve this limitation. Inspired by multiplayer game architectures, MAS disentangles world dynamics and view rendering. A learned Logic Engine advances a global, authoritative typed state from joint actions without any hand-written transition function, acting as the sole recurrent memory and synchronization reference. From this shared state, a learned Rendering Engine generates independent and consistent views for any requested camera on demand. This explicit disentangling allows MAS to achieve superior state accuracy and lower cross-view inconsistency compared to state-of-the-art multi-view baselines on a matched multiplayer Snake benchmark. It advances p
arXiv:2608.06221v1 Announce Type: cross Abstract: Learning from demonstration (LfD) provides a developmental framework through which robots can develop motor skills by observing and imitating human dynamics, reducing reliance on explicit programming to teach a skill to a robot. The resulting human-like robot motion is recognised as a key factor in building trust and enabling natural collaboration in human-robot interaction. This paper presents a framework for learning human-like robot motion from demonstration, including data collection, probabilistic trajectory learning, and perceptual user evaluation. A dataset of 3,142 handwriting demonstrations was collected from 22 participants across all 52 Latin alphabet character-case combinations via a touchscreen teleoperation interface, capturing planar position, contact force, and timing. Building on the widely used Gaussian Mixture Model and Gaussian Mixture Regression approach for learning from demonstration, the framework is extended in
arXiv:2608.06219v1 Announce Type: cross Abstract: Intuitive teleoperation interfaces are crucial for the safe and effective operation of robotic manipulators in challenging environments. In the nuclear industry, surface contact tasks such as swab sampling require precise path and force tracking, obstacle avoidance, and sustained operator attention, which conventional joystick interfaces struggle to support effectively. This study designs and evaluates a novel touchscreen teleoperation interface that maps continuous finger movements directly to robotic manipulator motions, provides finer velocity control, and integrates control with visualization, enabling more natural, precise, and intuitive surface interaction than conventional controllers. A comparative user study with 20 participants evaluated task performance and workload using the proposed touchscreen, a conventional joystick, and a single-click autonomous mode. Tasks simulated realistic surface manipulation using a Franka Emika P
arXiv:2608.06027v1 Announce Type: cross Abstract: In India, almost every social benefit starts with a form, yet the people who need these benefits most are often unable to read or write. Reaching them requires a spoken conversation. Today that work falls to frontline health workers who enroll beneficiaries one at a time, a poor use of stretched capacity. We built FormBharo ("fill the form" in Hindi), a voice agent that fills a structured form over a phone call under tight latency and cost budgets by pairing Large Language Models (LLMs) with deterministic, rule-based validation and flow control. It is being piloted with ARMMAN, an NGO running large-scale maternal and child mobile-health programs in India, to enroll low-income, Hindi-speaking mothers in antenatal and postnatal care. To our knowledge, it is the first voice agent piloted to fill an enrollment form for this population. We openly release FormVoiceAgentBench, a benchmark pairing human-recorded Hindi audio with 3,760 multi-tur
arXiv:2608.05729v1 Announce Type: cross Abstract: As capabilities rapidly increase, AI agents can move from running inside one app to acting across a user's devices over time. Yet existing agent systems still fall short in this scenario. This is because observations are scattered across devices and moments, but mainstream systems are not designed around this fact: a single agent that treats devices as tools lacks effective state management for all devices across time, and multi-agent systems coordinate across agents but do not maintain the compact carried state a cross-device, cross-time request needs. We argue that the agent should maintain an effectively designed state that organizes engagement evidence, stated facts, and the standing request in a compact, action-ready form for deciding its action given the current observation. To compare state designs, we construct a benchmark of user-agent interaction across devices and time. We instantiate this principle in Unified Agent, a statef
arXiv:2608.05602v1 Announce Type: cross Abstract: Generative AI systems are increasingly deployed in high-stakes professional contexts, where their outputs shape what users believe, how they reason, and what they treat as settled. This raises a central question for responsible AI: under what conditions is reliance on generative AI outputs epistemically warranted rather than behaviourally induced? Existing frameworks largely ask whether AI outputs are accurate, fair, explainable, safe, or trusted by users. These questions remain necessary, and each can contribute to warranted reliance. However, they do not directly specify warranted reliance as a distinct evaluative target: the conditions under which users are justified in treating AI outputs as inputs into their own reasoning. We argue that this requires an account of epistemic trustworthiness: what makes a system epistemically worthy of reliance. Drawing on philosophical accounts of trustworthiness as competence and audience-orientati
arXiv:2608.05495v1 Announce Type: cross Abstract: Smart-home assistants increasingly use multimodal large language models (MLLMs) that perceive video and audio directly. This raises a safety question specific to the home: can the agent tell a genuine user command from ambient or externally-sourced content, television speech, on-screen text, or an overheard conversation, that merely looks like a command? We introduce PromptShield-Home, a pilot benchmark of realistic smart-home scenarios spanning addressee ambiguity, screen/audio injection, health-monitor false triggers, mixed occupancy, and a legitimate-command floor, and use it to compare three abstraction layers: traditional detectors (L0), a single MLLM agent (L1; vision, vision+ASR, and audio-visual), and multi-agent mediation (L2; voting, role specialists, cross-model arbitration). Because the label distribution is skewed toward inaction, aggregate accuracy is misleading, a constant always-block predictor scores 82%, so we report u
arXiv:2608.05478v1 Announce Type: cross Abstract: Graphical Abstracts (GAs) visually summarize the key findings of academic papers, playing a crucial role in facilitating the understanding of research content. Recently, advancements in vision-language models and image generation models have enabled the automatic generation of scientific figures based on paper content. However, most conventional methods output the generated results as raster graphics, making post-editing (e.g., text modification and layout changes) highly difficult. This poses a significant challenge, as they are unsuitable for the iterative figure revision process inherent in paper writing and peer review. To tackle these challenges, we define the novel task of generating editable GAs from paper content and propose GenGA, a new GA generation framework that directly produces figures in vector format. By generating figures as a collection of vector elements with a hierarchical structure, GenGA produces outputs that can b
arXiv:2608.05313v1 Announce Type: cross Abstract: Service robots operate in household environments shared with humans, pets, and everyday objects, where they are highly susceptible to failures such as software crashes, hardware degradation, or unpredictable interactions. While roboticists strive to minimize failures, some remain inevitable, making it critical to mitigate their potential consequences for safe and reliable deployment. This paper introduces a novel safety formulation that evaluates both the probability of impactful interactions between robots and surrounding entities during failures, and the severity of their outcomes. By quantifying the impact of failures on different entities, our approach enables robots to make informed planning decisions that balance safety with task efficiency. To support systematic evaluation, we also present FailBench, a MuJoCo-based simulation framework for studying robot-environment interactions under diverse failure modes, including sensing issu
arXiv:2608.06202v1 Announce Type: new Abstract: Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness. Yet most evaluations rely on a single access modality (model APIs), perform a single run per prompt, and report accuracy as the primary outcome metric, without accounting for conditions such as web search that may have effects on model behavior in deployment. We audit these assumptions for one of the most widely-used LLMs, comparing two modalities, ChatGPT's chat UI and OpenAI's API, with and without web search enabled. We use a stratified total sample of 401 prompts from two popular benchmarks, BBQ and SafetyBench, collecting 4,812 total responses across three repeated runs per prompt. Beyond standard performance measures, we evaluate model output dimensions including response consistency, response text similarity, citation grounding, and abstention behavior. For instance, chat UI responses were
arXiv:2608.06151v1 Announce Type: new Abstract: The emergence of conspiracy theories in the wake of major events is a significant societal challenge. Here we test whether conversational dialogues with a large language model (LLM) can reduce belief in immediately unfolding conspiracies. In experiments conducted in the days following the July 2024 assassination attempt on Donald Trump and the September 2025 assassination of Charlie Kirk, U.S. adults (Experiment 1: N = 472; Experiment 2: N = 1035) holding conspiratorial views about the crisis event engaged in a multi-turn conversation with an LLM prompted to reduce their conspiracy belief. Compared to control participants who either discussed an irrelevant topic with an LLM or viewed a static fact sheet, participants in the LLM treatment showed significantly reduced conspiracy beliefs in both experiments. We also found evidence of downstream effects of the LLM treatment, observing reduced belief in different conspiracies one to two months
arXiv:2608.06132v1 Announce Type: new Abstract: Virtual reality (VR) and video-passthrough mixed reality (MR-VPT) can be delivered on the same headset, but it is unclear whether these two interaction modalities produce comparable perceptuomotor behavior. Although delivery through the same headset controls many display-level characteristics, VR and MR-VPT differ in both their visual-feedback pipelines and the action-relevant visual information available to guide movement, such as whether the surrounding environment and the user's body are synthetically rendered or preserved through passthrough. This study compared visually guided manual pointing in VR and MR-VPT using the same headset. Forty adults were assigned to either a VR or MR-VPT group and completed a pointing task in the physical, unmediated reality (UR) before and after performing the same task in their assigned XR modality. The analyses revealed numerous important insights. First, groups had comparable baseline performance in
arXiv:2608.06091v1 Announce Type: new Abstract: Conversational commerce uses digital assistants to support the search process and decision-making in e-commerce. Effective communication in these interactions can be facilitated by assistants adapting their communication style to users and supporting shared understanding. An open challenge in this context is adapting the presentation of complex product information to users with varying levels of domain knowledge. To investigate strategies for such knowledge-level adaptation, we set up a chatbot-assisted laptop search scenario. In a between-subjects experiment (n = 251), we examined novice and expert perceptions of product attribute recommendations presented as technical information only (T), or augmented with performance categories (TC), attribute explanations (TE), or both (TCE). For novices, approaches with explanations (TE, TCE) were perceived as more helpful and led to higher perceived learning than those without. Novices also rated t
arXiv:2608.06068v1 Announce Type: new Abstract: We demonstrate Cleo, a transparent and controllable conversational product advisor that addresses the challenges of opacity, unpredictability of LLMs, and the complexity of comparisons in conversational commerce. With our chatbot system, we make four contributions: First, we introduce transparency by prompting the LLM to reflect on interpreted user needs, while an auditable ranking mechanism reveals loss values per attribute, explaining ranking decisions. Second, we propose controllability through a hybrid architecture separating deterministic ranking from language generation. A ranker applies categorical filters and numeric loss functions over 3,638 product specifications. Meanwhile, a constrained LLM generates grounded descriptions constrained to catalog evidence, thus mitigating the risk of hallucinated or persuasive content. Third, we provide decision support in the form of natural-language comparisons and a highlights feature. These
arXiv:2608.06013v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in emotional intelligence. However, prevailing research predominantly focuses on task-specific specialization, often neglecting inter-task synergy and leaving latent reasoning potential underexplored. To bridge this gap, we introduce OneEmo, a unified affective generalist capable of mastering emotion perception, comprehension, and interaction. For this purpose, we first construct EmoWorld-130K, a comprehensive dataset that distills specialized affective knowledge into explicit reasoning trajectories via a human-in-the-loop workflow. Supervised fine-tuning on this corpus reveals significant mutual benefits derived from multi-task learning. Second, to fully unlock the latent reasoning potential, we propose Emo-Chord, a novel reinforcement learning strategy that stabilizes optimization through unified multi-task reward allocation. Extensive experiments demonst
arXiv:2608.05971v1 Announce Type: new Abstract: Athletic coaching increasingly relies on video analysis, yet raw footage lacks tools to quantify motion or simulate valid technique corrections. Drawing on formative interviews with eleven cricket experts (coaches, performance analysts, captains, and players), we introduce PoseForge, a visual analytics system that extracts 3D skeletal poses from single-camera sports videos for interactive movement analysis. In a cricket batting case study, PoseForge computes interpretable kinematic metrics such as feet gap and elbow angle, compares them against scientifically derived norms, and uses an AI coach to suggest targeted adjustments, presented visually and through natural-language feedback (e.g., "increase feet gap by 10 cm"). Users can directly modify poses via mouse interaction or natural-language instructions, with inverse kinematics maintaining anatomical plausibility and real-time updates of metrics and comparisons. An evaluation with the s
arXiv:2608.05966v1 Announce Type: new Abstract: We introduce a web-based modular workflow for real-time multimodal experiments in naturalistic online reading. The workflow integrates eye tracking, EEG, and interaction data from mouse and keyboard, synchronizes them via Lab Streaming Layer, and links gaze to browser-based text at the word, sentence, and AOI levels. It is designed as a reusable experimental procedure that can be adapted to different sensors, tasks, and analysis goals. As a use case, we apply the workflow to a study of selective exposure in online news search and reading. During the experiment, gaze-derived measures are computed online, while EEG and other synchronized streams are processed immediately after task sessions based on fixation-triggered segmentation. The resulting behavioral, neural, and linguistic metrics support selecting text passages for targeted post-task rating or labelling within the same lab session. The workflow thus provides a general basis for mult
arXiv:2608.05942v1 Announce Type: new Abstract: Research on selective exposure frequently relies on eye tracking to study reading behaviour, often assuming that texts across different controversial topics are comparable once basic controls are applied. This assumption is problematic if topic-dependent linguistic properties systematically shape how users read and allocate attention. We therefore examine whether such properties relate to differences in reading behaviour in selective exposure contexts. We analyse linguistic features and eye-tracking data from a laboratory study in which 68 participants searched for and read news articles on climate change and migration policy. Our results reveal systematic differences in both textual characteristics and reading behaviour across topics. These findings identify an important methodological confound in selective exposure research and highlight the need to account for topic-specific linguistic properties when interpreting eye-tracking measures
arXiv:2608.05837v1 Announce Type: new Abstract: Time-varying bivariate fields arise in many scientific applications, where the relationship between two scalar quantities evolves over time. While topological methods such as merge trees provide an effective framework for identifying and tracking features in univariate data, analogous approaches for bivariate fields remain comparatively underexplored. Reeb spaces extend topological analysis to multivariate data by representing fiber connectivity through a collection of interconnected sheets, making these sheets natural candidates for describing bivariate structures. However, establishing temporal correspondences between sheets is challenging due to the structural complexity of Reeb spaces, sensitivity to noise, and the difficulty of defining meaningful similarity measures across timesteps. We present a framework for tracking Reeb space sheets in time-varying bivariate fields. The method establishes correspondences between sheets in consec
arXiv:2608.05730v1 Announce Type: new Abstract: Vision-language-action (VLA) models follow language commands but often lack explicit spatial intent for manipulation. We present Visual Intent Anchors, an XR pipeline that lets users specify grasp and placement regions and renders them as image-space overlays for VLA control. We collect 200 Unity pick-and-place demonstrations and fine-tune OpenVLA-7B with LoRA on temporally subsampled annotated observations. The policy predicts tokenized 7-DoF incremental actions from marked RGB observations and language. We evaluate the policy in closed-loop Unity trials, achieving a grasp success rate of 91.25% and mean grasp and placement errors of 0.5 cm and 0.7 cm, respectively.
arXiv:2608.05690v1 Announce Type: new Abstract: When people argue over text, they share a record of what was said but may hold different accounts of what it meant. Existing AI reflection tools typically work from one person's account, while dyadic tools support co-expression without making interpretation gaps inspectable. We present ASIDE, a system for Dyadic Spectator Reflection (DSR). DSR follows the sequence externalize independently, then encounter together. From a past chat conflict, ASIDE creates a pixel-art theatrical replay with revisable AI-generated inner-state hypotheses. Partners first confirm hypotheses about themselves and separately edit their interpretations of the other. After both finish, they view the co-annotated scene together and review Divergence Cards that pair a confirmed account with the partner's reading at a specific conversational beat. In an exploratory study with 10 couples who revisited real text-based conflicts, participants described the theatrical rep