Dialog
-
Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation
2026-08-10 10:48:40Bo Wang, Ruixing Zhang, Yunqi Liu, Yang Zhang, Liangzhe Han, Tongyu Zhu, Leilei SunAbstract
User simulators are widely used as scalable environments for training and evaluating interactive assistants. Generating the next user turn is inherently one-to-many: the same profile and dialogue context may support multiple plausible continuations with different local interaction intents. A fluent response may therefore advance the dialogue through an inappropriate intent, such as acceptance rather than repair. Our key insight is that controllable user simulation should separate which local interaction intent the next user turn should realize from how that intent is expressed in language. We introduce UserIDA (User Intent-Directive Alignment), which exposes interaction intent as an explicit per-turn directive. UserIDA defines a six-way intent interface, learns directive-conditioned generation through supervised fine-tuning, and uses intent-calibrated policy optimization during group-based reinforcement learning. The reward preserves composite response quality while ensuring that intent-violating candidates rank below compliant alternatives in mixed groups. On LMSYS-USP, UserIDA achieves 86.6\% intent accuracy, outperforming the strongest dedicated user-simulator baseline by 24.3 percentage points while improving semantic and stylistic similarity. In within-context interventions, it realizes at least four of the six target intents in 91.7\% of evaluated dialogue states, compared with 22.9\% for the strongest external baseline. These results establish per-turn intent control as a complementary dimension to response fidelity in user simulation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09420
PDF
-
Reading Cognition as Decisions Unfold in Words: A Factorized Inverse Decision Model
2026-08-10 07:46:13Jiawen Kang, Dongrui Han, Xixin Wu, Helen MengAbstract
Inverse decision modeling infers latent properties of decision processes from observed behavior, but existing formulations rely primarily on action trajectories. In verbalized cognitive tasks, task execution also produces response dynamics that action-only formulations leave unmodeled, such as verbal production, interaction, and hesitation. We propose a factorized inverse decision model (FIDM) that decomposes each individual's task-execution likelihood into an action factor and an effort factor, governed by separate individual-specific parameters. From raw verbal transcripts, a language model produces structured task-execution traces for factorized inference. On data from 400 older adults performing a grocery-shopping dialog task for cognitive screening, controlled recovery shows selective estimation of the intended factors, while matched semi-synthetic conditions show that FIDM preserves action-execution distinctions even when aggregate behavioral summaries are matched. Action evidence further localizes task-defined deviations across participants. In cognitive-status classification, FIDM provides information complementary to clinical scores, trajectory summaries, and frozen language representations, with consistent gains across all evaluated baselines in the binary setting.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09222
PDF
-
SAIN: Structure-Aware Interactive Navigation with Active Dialogue Grounding for Mobile Robot
2026-08-10 07:08:44Yuhao Cao, Xiao Liu, Yang Xie, Lu Liu, Haoyao ChenAbstract
Most existing vision-language navigation tasks assume that instructions are complete and unambiguous. However, real-world robots often encounter natural human instructions that are ambiguous, underspecified, or incomplete, requiring them to resolve such uncertainties through active questioning. Interactive Instance Goal Navigation (IIGN) requires an embodied agent to find the specific instance under an ambiguous category-level instruction through active dialogue. However, existing dialogue-enabled methods often consume oracle answers as transient textual context for immediate decisions, rather than persistent spatial or object-centric structured state. We present SAIN, a zero-shot framework that turns active dialogue into persistent navigation state. Instead of consuming oracle answers as one-step text hints, SAIN compiles them into target evidence, route-level corridor memory, and object-candidate labels. These states are stored in structured value, room, graph, and object memories, then consumed by a unified policy for frontier ranking and final target approach. On the VL-LN IIGN benchmark, SAIN improves SR from 20.2 to 25.4 and SPL from 13.07 to 14.17 over the strongest reported dialogue-enabled baseline, while requiring no task-specific policy training. The results support dialogue-to-state conversion as an effective zero-shot mechanism for long-horizon interactive instance navigation. Project website: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.09196
PDF
-
EmoS: A Theory-Grounded Framework for Evaluating and Aligning Emotional Intelligence in Spoken Language Models
2026-08-10 06:58:30Junyu Wang, Siyuan Zhang, Peiyuan Jiang, Jian Zong, Jingyu Zhang, Tianrui Wang, Yuqin Lin, Zhenghui Chen, Shuqing Xie, Ziyang Ma, Meng Ge, Xiaobao Wang, Longbiao Wang, Jianwu DangAbstract
Despite significant advances in instruction-following and auditory comprehension, the evaluation of Emotional Intelligence (EI) in Spoken Language Models (SLMs) remains confined to rudimentary paralinguistic perception, lacking a systematic, theory-driven cognitive framework. We introduce EmoSBench, the first comprehensive EI evaluation benchmark for SLMs constructed upon the four-branch theoretical model, covering Perceiving, Understanding, Using, and Managing Emotion across ten sub-tasks. Preliminary assessments on EmoSBench reveal a substantial gap: even leading proprietary models like GPT-4o-Audio achieve only 52.6%, significantly trailing human baselines. To bridge this gap, we develop EmoS, a specialized evaluator model optimized via Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO). To facilitate its effective training, we curate EmoDialogue, a bilingual dataset providing necessary fine-grained supervision through response pairs with rigorously defined EI gradations. Concurrently, we introduce a reward mechanism integrating a Steep Exponential Accuracy Reward (SEAR) and a Rationale Fidelity Reward (RFR) to enforce precise ordinal scoring and valid reasoning. Experiments demonstrate that EmoS reaches 83.8% accuracy, approaching human-level performance. Furthermore, evaluations on authentic, unconstrained spoken interactions validate its robust real-world generalization, establishing a foundational framework for advancing emotionally intelligent dialogue systems.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09189
PDF
-
Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization
Abstract
Users of modern platforms repeatedly need summaries of recent dialogue, but the window rarely contains enough context to be interpreted on its own. We formalize this setting as streaming dialogue summarization, where a system must summarize a current window using selective memory from an unbounded history under a fixed budget. We show that the central challenge is not how much history is accessed, but whether memory recovers the evidence that the current window presupposes. We construct a benchmark and evaluation protocol that separately assesses whether memory contains gap-resolving evidence and whether the generated summary reflects it. We propose ReMEMBER, a missing-evidence memory framework that conditions retrieval on unresolved window dependencies and refines retrieved chunks into evidence-dense memory under a fixed budget. Experiments on dialogues with histories up to 160K tokens show that ReMEMBER improves memory recall and gap-resolution completeness over memory construction baselines under the same budget.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09043
PDF
-
Context Is Not Authority: Structured Runtime Governance for Financial Market Agents
2026-08-10 02:26:07Rui Tang, Qiangqiang Liu, Yichi Zhang, Youwei Wang, Xi Chen, Chen DongAbstract
Financial agents can turn correct context into an unauthorized effect: a customer-facing commitment, trade, or deployed policy. We present SAGE-Fin, a finance-specific authority-handoff contract that makes the proposed effect, not merely its text, the object of runtime control. SAGE-Fin compiles proposals into typed, adapter-bound candidates; records missing or stale institutional obligations as coverage debt; contracts authority under current market, account, policy, and dialogue state; and requires an exact-artifact receipt whose nominal type matches the consuming response, execution, or policy adapter. Evidence and workflow progress cannot substitute for effect authority, and prior authorization is rechecked after state changes. Across an authored 616-case catalog, five deterministic specifications yield 3,080 outputs; a label-isolated harness obtains 616/616 binary reference-prototype parity, including 3/3 named response-gate fixtures, while 22 tests cover selected paths. These results establish executable conformance, not independent safety accuracy. Separately, SAGE-Fin's response gate processed real customer-facing production requests at a confidential digital-asset platform. An operational team independent of the implementation team reached a strongly positive post-deployment conclusion on practical usefulness and workflow fit, and end-user feedback was also strongly positive. Disclosure permits only the review's independence, stakeholder classes, assessed dimensions, and directional conclusion, so this is qualitative field corroboration rather than an aggregate effect estimate. Three distinct de-identified predecessor failures, with independently confirmed 0/3 interception, ground repeated-emission drift, stale account evidence, and missing escalation state without estimating prevalence or treatment effect.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09025
PDF
-
ELICITED: EHR-grounded Longitudinal Interactive Conversations for Information-seeking Triage Evaluation and Decision-making
2026-08-10 02:26:06Haohao Zhu, Xiaolin Shi, Jiayu ZhouAbstract
Emergency-department (ED) triage requires clinicians to rapidly identify patients who need immediate attention, determine who can safely wait, and prioritize limited clinical resources. At presentation, however, information may be limited to a chief complaint and initial vital signs. Clinically important details, including symptom onset and progression, associated symptoms, medical history, and medication use, are often obtained through focused conversation. Effective triage therefore requires clinicians to identify information gaps, ask appropriate follow-up questions, and update their assessment as new evidence becomes available. Most existing ED benchmarks evaluate acuity prediction from a fixed clinical snapshot. Although this formulation measures predictive performance after patient information has been assembled, it does not capture the interactive process through which triage-relevant evidence is elicited and interpreted. Existing medical dialogue datasets support the study of clinical communication, but dialogue statements are not always linked to temporally ordered events in the electronic health record (EHR). We introduce EHR2Dial-Triage, an agentic conversation-generation framework and benchmark grounded in MIMIC-IV-ED. The framework constructs triage conversations under explicit role-based and temporal information boundaries. Each accepted patient disclosure is linked to its supporting EHR event and the first dialogue turn at which it becomes available. EHR2Dial-Triage enables controlled evaluation of information elicitation, evidence use, five-level Emergency Severity Index prediction, and patient-facing communication across models and patient personas. It provides a structured setting for studying conversational triage as a dynamic process of clinical information acquisition, reasoning, and communication.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09024
PDF
-
Investigating Multimodal Informativity under Different Partner Visibility Conditions in Video-Mediated Dialogue
2026-08-09 21:08:22Esam Ghaleb, Hugh Mee Wong, Kristina KobrockAbstract
Situated language use is multimodal and embodied. For example, gestures can carry information that is absent or underspecified in the speech signal, yet dialogue models typically rely on transcripts alone. We study how much referential information gestures and their combination with speech carry in multimodal dialogue under different partner visibility conditions. % We build models that identify the intended referent in a video-mediated referential communication game based on either the speech transcript, the skeletal representation of gesture, or both modalities. Our results show that gesture alone is predictive of the intended referent and that multimodal fusion is most beneficial when the transcript-based model is uncertain. Training-only alignment of learned representations with the referent image further improves the fusion model performance. % In a comparison with human interaction data, we further see pragmatic effects of interlocutor visibility on gesture production and informativeness as well as an entrainment effect in speech and multimodal, but not gesture, performance across rounds of repeated interaction. We thus make contributions to the technical modelling of multimodal information in human dialogue and the analysis of human interaction data via trained model representations.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08915
PDF
-
Scale-to-Dialogue: Low-Burden Elicitation of Daily Premenstrual Symptom Ratings with Small Language Models
Abstract
Prospective daily symptom tracking is central to premenstrual health assessment, but repeated ordinal forms impose substantial response burden. We formulate conversational administration as an ordinal label-recovery problem: the system actively elicits a small set of symptom clusters and maps each response to the original severity labels. We used 3,320 complete participant-days from the mcPHASES dataset, covering cramps, mood swing, fatigue, sleep issues, stress, and bloating on a six-level scale. Six participants were reserved for development and 36 for a frozen evaluation comprising 360 participant-days and 2,160 item labels. A ModernBERT evidence gate detected whether a symptom was expressed, and Qwen2.5-1.5B-Instruct produced deterministic structured severity scores. Fixed six-item questioning achieved a quadratic weighted kappa of 0.976, whereas three joint symptom-cluster questions achieved 0.913, 97.45% agreement within one severity level, and 80.94% recall for moderate-or-higher symptoms while reducing questions by 50%. Open-first adaptive policies required 3.92-5.98 questions and produced lower agreement than the corresponding fixed policies. Participant-cluster bootstrap analysis estimated a kappa difference of -0.062 (95% CI -0.076 to -0.048) between the three-cluster and six-item strategies. Active cluster-level elicitation provides a direct, local-model route from natural conversation to reusable daily symptom labels.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08746
PDF
-
Walking through Discussions: A Mobile Visual Analytics System for In-Situ Group Discussion Analysis
2026-08-09 10:05:46Yiping Sun, Ziyao Kang, Wei Zeng, Minli Wu, Jiazhi XiaAbstract
Group discussion-based teaching is widely used to foster collaborative learning, yet teachers in physical classrooms often struggle to simultaneously monitor multiple groups and quickly diagnose a target group before intervening. Existing visual analytics tools primarily support post-hoc analysis on desktop, providing limited support for in-situ walk-around teaching. To address this gap, we present MobileGroupVis, a mobile visual analytics system for in-situ analysis of classroom group discussions. MobileGroupVis integrates multi-group monitoring, single-group diagnosis, and instructional intervention into a concise analytical workflow tailored for small-screen touch interaction. The system is powered by a lightweight streaming analysis pipeline that converts group audio into structured discussion data and further extracts interaction patterns, topic progression, and topic deviation through a dialogue analysis module. To enable both glanceable overview and traceable diagnosis, we design six coordinated views, including a compact glyph that visually encodes word count, interaction intensity, and topic deviation for efficient cross-group comparison and anomaly localization, along with detailed views for opinion evolution, interaction dynamics, topic coverage, and dialogue records. We evaluate MobileGroupVis through two case studies and expert interviews. The results provide preliminary evidence that MobileGroupVis supports teachers in understanding discussion processes, identifying groups in need of attention, and facilitating in-class intervention.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08617
PDF
-
Calling the Bluff: Detecting Ever-Shifting Harmful Chat Dialogue via Ordered Reasoning Chain Regularization
2026-08-09 03:41:39Haojie Yu, Ziyou Jiang, Junjie Wang, Mingyang Li, Yuekai Huang, Jie Huang, Qing WangAbstract
Harmful chat dialogues are ever-shifting through type-shifting and lexical evasion, yet we find they share invariant principles, i.e., an Ordered Reasoning Chain (ORC) of recurring topics, harm language indicators, severity hierarchies, and type characteristics, which can help us capture the key information in the frequently changing lexical expressions. We propose BRACE, which encodes the ORC as four differentiable stages (Topic -> Indicator -> Severity -> Type) with intermediate supervision, serving as a structured regularizer blended with direct heads, and supported by prototype-based feature augmentation and feature path disentanglement. The evaluation results show that, across 4 domains and 5 harm categories, BRACE achieves harm-type macro F1 of 0.934 (RoBERTa-wwm-ext, 3-seed mean), with decoder backbones (Qwen3-1.7B LoRA) reaching 0.949. Ablation studies show that all components contribute to BRACE, and the structural decomposition of ORC enables BRACE to distinguish harmful types with semantic ambiguity. Disclaimer: This paper may contain content that is disturbing to some readers.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08451
PDF
-
Dramarrator: Object-Based Audio Editing for Audio Drama Production from Books
2026-08-08 22:09:52Karim Benharrak, Oriol Nieto, Bryan Wang, Zeyu Jin, Amy PavelAbstract
Audio dramas weave dialogue, sound effects, and music into immersive stories. Creators often adapt books into audio dramas, but this process remains labor-intensive, requiring them to interpret source material, author scripts, generate audio assets, and assemble them on a timeline. Because story elements like characters and scenes manifest across many interdependent assets, a single change can ripple into manual updates across the entire project. We present Dramarrator, an audio drama authoring tool built around object-based audio editing, where these story elements are represented as editable objects. Dramarrator extracts these objects from a book, generates linked audio assets (speech, sound effects, and music), and composes a multi-track audio drama. Edits to any object (e.g., a character's voice) automatically propagate to all dependent assets. In a user study with professionals (N=8), Dramarrator significantly lowered task load when creating audio dramas. A listener study (N=300) shows that creator-refined output from Dramarrator approaches the quality of productions made with existing professional tools, and an exploratory study (N=3) suggests object-based editing lowers entry barriers and generalizes beyond audio dramas.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08349
PDF
-
Toward Self-Repairing Ubiquitous Robots Using Goal-Oriented Agentic AI in Human-Robot Interactions
2026-08-08 20:32:35Morten Roed FrederiksenAbstract
Ubiquitous robotic systems often lack traditional visual interfaces, making natural language interaction important for maintenance and repair. This paper presents a goal-oriented agentic AI architecture that enables non-expert users to complete technical repair tasks through situated dialogue. The architecture separates pre-interaction goal decomposition, persistent state tracking, strategic goal management, and real-time conversational execution. We evaluated the system in a physical hardware repair task with twenty participants. Nineteen participants completed the task, corresponding to a 95% completion rate. Participants rated the system as helpful and competent, and the agent remained robust to conversational diversions such as meta-queries and code-switching. A comparison with a prior online baseline showed that physical interaction significantly reduced perceived social presence, (p=.0005), and trust and competence, (p=.037), while perceived helpfulness remained high.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26155
PDF
-
Illusion of Alignment: Detecting Hidden Disagreement in Collaborative Dialogue
2026-08-08 16:11:58Kaiming Liu, Fuwen Luo, Ziyue Wang, Jinrui Ju, Yuxuan Liu, Xuanyu Lei, Yunghwei Lai, Peng Li, Yang LiuAbstract
Collaborative dialogue can end with apparent agreement while participants still differ on goals, assumptions, or execution plans, creating an \textbf{illusion of alignment (IoA)}. A real-user study across 18 meetings confirms that IoA arises routinely in human collaboration. Yet IoA poses a paradox: if participants were aware of such disagreements, they would already be explicit; if not, they cannot articulate them when asked, leaving IoA invisible to both participants and observers. In this work, we make IoA detectable by generating diagnostic multiple-choice questions whose divergent answers across participants provide direct behavioral evidence of hidden disagreement. We construct \textbf{IoA-Suite}, a dataset and evaluation protocol for detecting hidden disagreement, spanning five task types and six domains. We find that even the best model attains only 49.5\% F1, with the bottleneck traced to private context that the dialogue does not surface. We then train \textbf{IoA-Prober-8B} based on IoA-Suite, reaching 51.8\% F1 on IoA-Suite. Across the aforementioned 18 real meetings, it surfaces 2.89 hidden disagreements per meeting that participants confirm they had not voiced, transferring to live human dialogue. Further, in multi-agent collaboration, pairing IoA-Prober-8B with LLM agents improves downstream task performance on BigCodeBench-Hard and HiddenBench.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08210
PDF
-
Wiener Representation Filtering for VLM Hallucination Suppression
2026-08-08 14:51:17Ameen Ali, Tamim Zoabi, Lidor Brami, Lior WolfAbstract
Vision-language models (VLMs) excel at open-ended captioning and visual QA but often describe objects, attributes, or relations absent from the image, a phenomenon known as object hallucination. We propose a {training-free, post-hoc representation editing technique} that operates in the representation space of the language backbone. The method performs a lightweight, one-time offline calibration on a modest paired dataset to estimate the required covariance structures, using only forward passes and empirical second-order statistics with no gradient updates or fine-tuning, after which the correction is absorbed directly into the model's existing weights. By modeling hidden states as a superposition of truthful and hallucination-associated components, we derive a Wiener-type estimator whose optimal gains are given in closed form from the covariances of paired truthful and hallucinated representations. An eigendecomposition yields mode-wise attenuation that respects a stability criterion, i.e., the filter responds continuously to estimation noise. The correction is applied once to the feed-forward output projections of selected deeper layers, at inference time, the model runs unchanged and at the same speed. Experiments on LLaVA-1.5, MiniGPT-4, Gemma3, and mPLUG-Owl2 demonstrate consistent reductions in object hallucination on CHAIR, POPE, and MME while maintaining caption fluency and overall response quality. We further demonstrate the generality of our approach on the TempCompass video understanding benchmark and on discrete diffusion language models for grounded dialogue, showing that representation filtering reduces hallucinations even in temporal video reasoning and multi-step, sequence-wide denoising settings.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08167
PDF
-
DialectS2S: End-to-End Speech Dialogue Modeling for Low-Resource Chinese Dialects
2026-08-08 11:11:10Yi Shu, Tianyu Peng, Yingzhuo Deng, Wen Yang, Jun Lin, Changming Xie, Xinyu Yu, Jiajun ZhangAbstract
Current end-to-end speech dialogue models are primarily optimized for mainstream languages and remain limited in low-resource dialect scenarios due to the scarcity of dialect speech data. Moreover, during dialect adaptation, the semantic representation space of speech dialogue models continuously evolves, while conventional speech supervision remains unchanged, leading to semantic inconsistency between hidden representations and speech targets and degrading speech stability and naturalness. To address these issues, we propose DialectS2S, an end-to-end speech dialogue model for Chinese dialects. We first develop a scalable dialect speech dialogue synthesis pipeline for efficient data construction. We further introduce a two-stage post-training strategy with self-aligned speech supervision, which aligns the semantic content of speech supervision with the evolved semantic representations of the model to improve dialect speech generation quality. Experimental results show that DialectS2S consistently outperforms existing baselines across multiple Chinese dialects in speech dialogue, achieving substantial improvements in dialect consistency, response quality, and speech intelligibility. Our work provides an efficient and scalable solution for end-to-end speech dialogue modeling in low-resource dialect scenarios. To facilitate future research and practical applications, we fully open-source the DialectS2S framework, including model checkpoints, training datasets, and fine-tuning code.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08067
PDF
-
ResidencyRL: Reinforcement Learning in Simulated Clinical Environments
2026-08-07 17:04:41Valentin Li\'{e}vin, Samuel Schmidgall, Tim Strother, Alex Bijamov, Akshay Goel, Anil Palepu, Chunjong Park, Vahid Balazadeh, Min Woo Sun, Marius Guerard, Justin Chen, Dave Steiner, Vikram Dhillon, Ibrahim Azar, Akhil Mehta, Nicholas Spetsieris, Shilpan Shah, Maen Abdelrahim, Amit Dahiya, Yun Liu, Katherine Chou, Yossi Matias, Avinatan Hassidim, Dale R. Webster, Quoc V. Le, Raia Hadsell, Joelle Barral, Carey Radebaugh, Aleksandra Faust, Shekoofeh Azizi, Mike Schaekermann, Po-Hsuan Cameron Chen, Tao Tu, David Racz, Lin YangAbstract
In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters, with diverse sources of feedback and progressively greater autonomy. Much of clinical reasoning relies on the patient encounter, a dialogue in which a clinician elicits history, refines diagnostic hypotheses, and decides management under uncertainty. While large language models (LLMs) excel on static medical benchmarks, methods to optimize the full sequence of clinical decisions remain underdeveloped. We present ResidencyRL, a reinforcement learning (RL) method for training clinical artificial intelligence (AI) agents through simulated multi-turn clinical encounters (up to 60 dialogue turns and 8 tool calls per trajectory). ResidencyRL pairs the policy agent with LLM simulators capable of complex, adversarial behaviors, training against a structured reward aligned to diagnostic accuracy, management quality, communication, documentation, and safety. On held-out evaluations, the ResidencyRL agent improves diagnostic accuracy by 7.0% under adversarial conditions (88.0% vs. 81.0%) and reduces missed red flag rates by 31%, demonstrating rigorous mitigation of premature closure. Blinded expert clinicians validated these gains, preferring the trained agent in 87.6% of side-by-side comparisons. The procedural competencies transfer to unseen benchmarks: the agent outperforms the base model across all six clinical axes of the AMIE multi-visit benchmark, and shows consistent directional improvements on AgentClinic and CRAFT-MD. Our findings demonstrate that sequential clinical decision-making can be effectively learned through multi-turn RL in simulation, yielding robust, generalizable capabilities, paving the way towards clinical mastery. Prospective validation with real-world workflows remains necessary to establish clinical utility.
Abstract (translated)
URL
https://arxiv.org/abs/2608.07418
PDF
-
Homebot: A Personal AI Agent for Conversational Home Assistance and Automation
2026-08-07 16:39:51Shengyuan Ye, Yixin Zhang, Han Liang, Liekang Zeng, Jiangsu Du, Mu YuanAbstract
\texttt{Homebot} is a locally deployable AI agent for conversational household assistance and automation. It accepts voice and instant-messaging requests through a shared runtime that combines language-model responses with registered tools and task-specific skills. The design separates common request processing from session ownership: messaging history remains scoped to a channel and chat, whereas voice interaction is bounded by wake-word activation. For hands-free use, \texttt{Homebot} combines local wake-word detection, streaming speech recognition and synthesis, and an explicit dialogue-state protocol for ending, following up, or continuing a conversation. Clear channel, tool, and skill contracts support practical customization for household use.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02254
PDF
-
PACE: A Playback-Aligned Context Engine for LLM-Based Full-Duplex Voice Dialogue
2026-08-07 12:55:43Shibo Wang, Zicheng Zhang, Libo Wang, Junfeng MaAbstract
LLM-based full-duplex voice services allow users to speak while the assistant is responding. Because servers can generate output and advance dialogue state faster than clients can play it, subsequent user speech may be interpreted based on content the user never heard. We call this failure Generative Context Mis-anchoring (GCM). To address GCM issues, we present PACE, a provider-independent middleware layer that anchors model-facing context to the client playback boundary, a system-observable proxy for what the user could have heard. After an interruption, PACE repairs this context to exclude assistant content that never reached playback, while preserving low-latency generation across heterogeneous voice runtimes. We implement PACE's audio-only projection path end to end in a browser-based realtime voice assistant using a black-box speech model, without modifying the model service. We also construct GCM-Bench, a new controlled benchmark dataset of 108 playback-relative referent-anchoring cases. On GCM-Bench, PACE raises Referent Anchoring Accuracy from 25.0% to 96.3% over a cancellation-only baseline. On 200 Full-Duplex-Bench v1 interruption samples, it preserves interruption response quality. These results show that grounding model-facing context in actual playback is a practical way to maintain consistency in full-duplex voice dialogue.
Abstract (translated)
URL
https://arxiv.org/abs/2608.07631
PDF
-
Stable Curves, Unstable Items: Item-Level Scaling Heterogeneity in Video LLMs
2026-08-07 09:25:20Wenzhang Sun, Chunfeng Wang, Xiangchen Yin, Yujia Chen, Hao Li, Kun ZhanAbstract
Aggregate scaling curves suggest that Video LLMs improve smoothly or saturate as visual budgets grow. We show that this view can conceal large, opposing changes at the item level. We represent each frozen model--item pair by its response trajectory under controlled visual budgets and derive matched-grid measures of configuration complementarity, harmful transitions, and text overwrite. Across five open Video LLMs from three architecture families, four multiple-choice benchmark splits, open-ended QA and summarization, and fixed-history dialogue generation, no single budget serves all items. On the four-model matched MCQA grid, item-level oracle headroom spans $8.8$--$18.9$ accuracy points and $12.5$--$25.5\%$ of items are correct at a lower budget but wrong at a higher one. Task-appropriate continuous metrics show the same complementarity beyond multiple choice: Token-F1 oracle gaps are $2.7$--$3.7$ score points on MLVU generation and $3.8$--$4.8$ points on AVSD current-turn generation, even when mean quality improves with budget. The effect persists across frame count, spatial resolution, sampling policy, temporal--spatial allocation, and independently executed raw-video and cached pipelines, with per-item rates and membership tracking protocol choices. A controlled sampling intervention recovers $29.0\%$ of terminal regressions, and a structured frame audit identifies several recurring evidence pathways. We release per-item trajectories, protocol provenance, derived annotations, and reproducible analysis code as an auditing artifact. A confidence cascade matches fixed-$128f$ accuracy while reducing average shared frame cost by $31.7\%$, illustrating one operational use of the response matrix.
Abstract (translated)
URL
https://arxiv.org/abs/2608.07014
PDF
