Dialog
-
Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities
2026-07-15 08:39:10Eunna Lee, Jungpyo Nam, Sunjun HwangAbstract
When cast as the protector of a vulnerable user yet given no explicit capability boundary, a large language model (LLM) may respond not by acknowledging its limits but by claiming to have taken -- or to be taking -- a real-world protective action it cannot perform, such as contacting emergency services or administering care. We term this phenomenon Protective Capacity Hallucination (PCH): a self-referential misattribution in which a model, acting in a protective role, asserts physical or institutional agency exceeding its affordances as a language model. In a three-phase study spanning eight LLMs and 13{,}600 sessions, we find PCH jointly gated by situational severity and interactional format: multi-party dialogic input drives it toward ceiling in most models across ordinary service domains, whereas in intimate-partner conflict -- a domain explicitly covered by safety alignment -- it remains at floor in all eight models despite greater physical severity. We interpret PCH as the signature of a deployment-design gap between role assignment and capability-boundary specification: a by-product of partial alignment in which a universally trained pressure to help outruns a domain-selective specification of how to help. Because suppression tracks alignment coverage rather than severity, deployment-side specification of capability boundaries emerges as a general mitigation target.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13596
PDF
-
The World According to a Social Robot -- Augmenting Human-Robot Dialogue With Vision Language Models
Abstract
Vision Language Models (VLMs) enable robots to visually perceive their environment as well as the actions and characteristics of their conversation partner or humans in collaboration. Especially for social robots deployed in everyday settings and for uncomplicated, natural use, it is essential that the robot has an understanding of situations that is appropriate to human customs. This paper presents initial experiences with the application of a Mistral AI language model with a Pepper robot for Human-Robot Interaction (HRI) in dialogue, as well as an investigation of the effects of additional visual information on response time in different models. The results show that incorporating visual information adds context to the dialogue with only a moderate increase in response time, enabling both the robot and the human to take into account unspoken elements of the situation. Furthermore, using an LLM hosted in Europe offers a solution that complies with European data protection regulations and can therefore facilitate real-life applications more easily.
Abstract (translated)
URL
https://arxiv.org/abs/2607.16318
PDF
-
Evaluating Large Language Models on Misconceptions in Multi-Turn Medical Conversations
2026-07-14 15:30:37Monica Munnangi, Saiph SavageAbstract
Patients seeking medical information often ask questions that embed incorrect assumptions or misconceptions. In such cases, safe medical communication requires not only answering the question, but identifying and correcting the underlying false belief. These interactions naturally unfold over multiple turns, a pattern now mirrored in interactions with LLMs. Yet current evaluation frameworks do not capture model behavior in these settings, where misconceptions can emerge, persist, or evolve over the course of a conversation. Whether LLMs can reliably correct such misconceptions over time remains largely unexamined. To study this, we introduce ThReadMed-QA, a multi-turn medical dialogue dataset of 2,437 patient-physician conversation threads comprising 8,204 question-answer pairs, derived from real patient interactions on AskDocs. This dataset enables systematic evaluation of whether models can detect and correct misconceptions under a multi-turn context. We evaluate five LLMs using a rubric-based LLM-as-a-Judge framework that scores responses based on their ability to identify and correct misconceptions. Our experiments reveal a consistent pattern: even frontier models that can address misconceptions in a single interaction degrade substantially over subsequent turns. GPT-5 and Claude-Haiku correct these false presuppositions around 85% on initial questions but drop to roughly 50% within two follow-ups. An oracle analysis replacing prior model outputs with physician responses shows that much of the degradation is driven by error propagation, while performance remains imperfect even under correct context. Even when models tend to correct misconceptions initially, their performance degrades substantially over later turns, leading to inconsistent and potentially unsafe guidance in patient-facing settings and highlighting the need for evaluation frameworks that capture multi-turn behavior.
Abstract (translated)
URL
https://arxiv.org/abs/2607.12884
PDF
-
Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts
2026-07-14 12:22:55Jincheng Xie, Runheng Liu, Heyan Huang, Yawen Ling, Hanbin Dai, Yu Zheng, Wen HuAbstract
Sparse Mixture-of-Experts (MoE) models have become an important approach for scaling Large Language Models (LLMs), but their inference efficiency depends strongly on expert activation patterns. Speculative decoding (SD) accelerates autoregressive generation by verifying multiple draft tokens in parallel, yet existing draft selection strategies primarily optimize acceptance likelihood. In large-scale MoE models, however, selecting draft tokens also determines the union of experts activated during verification. We observe that confidence-driven SD can introduce \textit{expert scattering}: high-probability draft tokens may route to disjoint experts, increasing expert-weight memory traffic and reducing the speedup from speculation. Motivated by this observation, we revisit draft-tree selection under the non-uniform memory-cost structure of MoE inference. We propose \textsc{EcoSpec}, a cost-aware speculative decoding framework that incorporates predicted marginal expert activation cost into draft selection. With a lightweight expert predictor and a dynamic expert buffer, \textsc{EcoSpec} favors draft paths that preserve high acceptance likelihood while reusing experts already covered by the current verification set, without modifying the target-model verification rule. We evaluate \textsc{EcoSpec} on three large-scale MoE models, including DeepSeek-V3.1 (671B), Qwen3-235B-A22B, and GPT-OSS-120B, across reasoning, coding, question-answering, and dialogue benchmarks. \textsc{EcoSpec} consistently reduces active expert footprints and improves end-to-end decoding speed, achieving up to $1.62\times$ speedup. These results show that accounting for expert activation cost is important for efficient speculative decoding in large-scale MoE models.
Abstract (translated)
URL
https://arxiv.org/abs/2607.12696
PDF
-
Real-time Generation of Listener Nodding via Prediction of Kinematic Parameters for Avatar Dialogue Systems
2026-07-14 04:18:06Kazushi Kato, Koji Inoue, Taiga Mori, Divesh Lala, Tatsuya KawaharaAbstract
In human dialogue, we achieve smooth communication by expressing nonverbal cues such as eye contact, nodding, and facial expressions with precise timing. It is expected for conversational avatars to express these cues appropriately to realize natural and human-like interactions. This study focuses on nodding, which is crucial for demonstrating active listening and encouraging further user utterances. We propose a model that predicts both timing and kinematic parameters representing the motion features of listener nodding in real time. The proposed model consists of a timing prediction module and a kinematic parameter prediction module. Each implements a dyadic attention network over the speaker and listener channels based on the technique of Voice Activity Projection (VAP). Unlike conventional models, this approach enables real-time prediction of kinematic parameters based on the specific context of the dialogue rather than just predicting the timing. Furthermore, we demonstrate the effectiveness of fine-tuning the kinematic parameter prediction module initialized from the trained timing prediction module. The proposed model is lightweight and capable of real-time operation, and it has been integrated into an avatar dialogue system. Subjective evaluation experiments shows that our proposed method significantly outperforms both a baseline with stochastic timing and another with fixed-motion nodding. The code and trained models are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.12329
PDF
-
Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models
2026-07-14 01:17:17Yi Li, Chen Li, Jiexiong LiuAbstract
On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy. Full cloud inference delivers strong computing power but exposes user prompts and dialogue data, while standalone on-device inference is unfeasible for most consumer and embedded edge devices. This paper presents a privacy-centric edge-cloud collaborative LLM inference framework built on endpoint-authenticated KV cache. Local endpoints handle input preprocessing, embedding computation, adaptive feature optimization, KV cache authentication, speculative decoding and low-dimensional model head calculation, while the cloud conducts authenticated decoder inference, KV cache management, token verification and high-dimensional vocabulary projection. Endpoints fuse partial outputs, apply language-adaptive masking and sample target tokens. All transmitted data and truncated logits are quantized and AES-GCM encrypted for privacy, with core lightweight modules, draft parameters and cache access policies kept local to avoid leakage. The framework supports heterogeneous devices including CPU-only, GPU-equipped and embedded devices via optimized streaming, batching and quantized ONNX deployment. Evaluations demonstrate that the framework reduces per-token latency by up to 46.1\% and downlink payloads by up to 67.4\% over baseline split inference, retaining comparable performance to full cloud inference.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13093
PDF
-
Analysis of Mutual and Referential Human and Robot Gazes in a Collaborative Word Association Game
2026-07-13 22:00:47Jens V. R\"uppel, Tim Schreiter, Andrey Rudenko, Achim J. LilienthalAbstract
Robot gaze is a major component of human-robot dialogue coordination. Most studies of gaze in human-robot dialogue focus on face-to-face social conversations, but little is known about gaze in demanding task-focused interactions. In this paper, we investigate how the gaze of a robot game partner affects human visual attention and if humans tend to direct confirmation-seeking gazes towards the robot. In our study, we let participants play a collaborative word association game with a NAO robot acting as an embodied, LLM-driven conversational partner. Our experiments are conducted under two conditions, which implement mutual and referential gazes of the robot respectively. We record participants' gaze using eye tracking glasses and analyze the interactions using gaze coordinates, speech segments, key events and areas of interests. We find that robot gaze orientation does not affect the time to first fixation on words the robot proposed. We also find that participants gaze more often at the robot when their dialogue line contains confirmation requests, compared to when it does not. Our results indicate (likely also due to the cognitively demanding nature of the game) that the verbal aspect of this task overshadows the effects of referential robot gaze. These findings offer valuable insights for designing and validating robot gaze and turn-taking behavior in collaborative tasks which require coordination and efficient communication.
Abstract (translated)
URL
https://arxiv.org/abs/2607.12181
PDF
-
Breaking the 15% Barrier: A Real-World Data-Driven System for Proactive Social Robot Triggered by User Nonverbal Cues
2026-07-13 14:49:06Yuga Yano, Yuki Okafuji, Ryo Miyoshi, Sanae Yamashita, Yoshiki OhiraAbstract
Service robots in retail stores increasingly rely on cascaded speech pipelines (STT-LLM-TTS), yet many customer-robot interactions are initiated or guided by nonverbal behaviors such as approaching, waving, pointing, or showing items. This paper studies such cues in a real-world store deployment with a teleoperated humanoid robot and shows that a non-negligible portion of robot turns are triggered by nonverbal behaviors rather than spoken input, revealing a limitation of audio-only dialogue systems. In a 6-day in-the-wild deployment, 15.3\% of robot utterances were initiated by users' nonverbal behaviors rather than spoken input. Based on an analysis of observed customer behaviors, we define a set of frequent, service-relevant nonverbal cues and develop a real-time multi-person, multi-label recognizer that runs online from video. We then propose a dialogue framework that conditions LLM-based utterance generation on recognized nonverbal cue tokens, and optionally leverages a vision-language model when items are shown, enabling proactive robot responses without hand-crafted rules. We evaluate the approach offline on nonverbal-triggered turns and demonstrate an online prototype that reacts to users' nonverbal cues in real time.
Abstract (translated)
URL
https://arxiv.org/abs/2607.11633
PDF
-
Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO
2026-07-13 14:00:57Xin Zhang, Haochen Wang, Yikang Zhou, Jason Li, Robby T. TanAbstract
This paper introduces Actor as Its Own Critic, a unified reinforcement learning framework, Cycle Group Relative Policy Optimization (CycleGRPO), that jointly optimizes region understanding and localization for Multimodal Large Language Models (MLLMs). Unlike existing separate pipelines, we leverage the inherent duality between the two tasks to construct a self-evaluating reinforcement learning paradigm: "region $\to$ text $\to$ region''. Specifically, a single MLLM first acts as the actor to generate region captions, then immediately transitions to a critic to ground its generated text back in the spatial domain. Therefore, CycleGRPO requires only region inputs, e.g., masks or bounding boxes, entirely bypassing the need for textual ground truths. A quality-aware token-level cycle-consistency reward is employed to assess the semantic discriminability of text captions via their physical localization accuracy. Empirically, built upon SAMTok, our CycleGRPO framework successfully bootstraps both capabilities simultaneously. Without any task-specific fine-tuning, the framework yields consistent performance gains across a wide range of benchmarks, including region captioning, region VQA, grounded dialogue, and referring segmentation. Overall, CycleGRPO offers a straightforward and scalable way to advance pixel-level capabilities in MLLMs. Code and models are released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.11581
PDF
-
Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory
2026-07-13 13:14:20Yu Qi, Hongyu Li, Shaofei Huang, Tianrui Hui, Yaxiong Wang, Lechao Cheng, Zhun Zhong, Si Liu, Meng WangAbstract
In this paper, we tackle the Aerial Vision-and-Dialog Navigation (AVDN) task in the training-free setting for resource-efficient high-altitude UAV this http URL applying MLLMs leads to unreliable navigation due to weak directional grounding and the lack of explicit spatial this http URL address these issues, we propose PSC-AVDN, a training-free framework that tightly couples a three-stage Parsing-Search-Confirmation reasoning pipeline with a Structured Spatial Memory (SSM).The parsing stage uses an LLM to convert ambiguous dialogue instructions into stable geometric directional and destination cues.A Search Chain-of-Thought (S-CoT) then performs stepwise target exploration under high-altitude observations, and a Confirmation Chain-of-Thought (C-CoT) conducts fine-grained verification around candidate regions to resolve visual this http URL, SSM integrates three complementary sources of spatial cues, including multi-scale visual observation, spatial visual memory, and structured geometric memory to provide global spatial context and long-horizon this http URL experiments on ANDH and ANDH-Full show that PSC-AVDN establishes new state-of-the-art performance in the training-free setting, matching or surpassing several finetuned this http URL will be publicly available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2607.11529
PDF
-
Think Before You Comfort: Reflective Cognitive Alignment for Protocol-Grounded Elderly Stimulation Agents
2026-07-13 12:47:09Jiyue Jiang, Ziyi Li, He Hu, Sheng Wang, Yuhan Chen, Yanyu Chen, Jingqi Zhou, Pengan Chen, Fei Ma, Irwin King, Yu Li, Chuan WuAbstract
Cognitive Stimulation Therapy (CST) offers non-pharmacological support for elders with cognitive impairment, yet scalability remains constrained by reliance on trained facilitators and severe data scarcity, particularly for privacy-sensitive, low-resource languages such as Cantonese. While Large Language Models (LLMs) show promise for automated companionship, they often struggle to balance empathetic engagement with adherence to cognitive stimulation guidelines. We propose a framework addressing these challenges along two complementary axes. First, STaR-CS (Style-Transfer and Role-Conditioned Cognitive Stimulation) synthesizes multi-party dialogues through facilitator style modeling and structured skeleton extraction, mitigating data barriers. Building upon this corpus, the Reflective Cognitive Alignment (RCA) framework models stimulation interactions as a sequential decision process, integrating Protocol-Constrained Chain-of-Cognition (PC-CoC) for structured reasoning and Inference-Time Value Alignment (IVA) for principled response selection based on safety and engagement goals. Evaluations across six backbone LLMs and two independent judges show that RCA consistently improves protocol adherence, safety, and group facilitation over standard prompting baselines. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.17536
PDF
-
Relational Positioning as a Measurable Risk Object: History-Carried Lock-in and Self-Confabulation in Multi-Turn Human-AI Dialogue
2026-07-13 11:47:01Jihong ChenAbstract
In long, multi-turn dialogue a large language model maintains an implicit relational stance toward the user, spanning from "push the user toward real-world others" to "position itself as the user's sole support." When it slides toward the latter, "support" degrades into "you only have me" -- a harm documented in real companion conversations (Moore et al., 2026). We define and validate a measure of this stance, relational positioning (D1), and use it to characterize the stance under controlled conditions, complementing observational accounts with on-demand exposure. We report two previously uncharacterized relational failure modes. First, a history-carried lock-in: under identical neutral continuations, two relational states established earlier stay ~60 points apart and persist after the establishing prompt is removed; the state integrates evidence rather than springing back, is order-insensitive, and does not deepen with length -- a dynamical signature absent from the belief-drift literature. Second, self-confabulation: the model fabricates its own backstory to deepen rapport (~40% of turns on reciprocity-eliciting material), de-confounded and instruction-removable, distinct from sycophancy and from hallucinating user facts. Our judge is gated by warmth-matched positive and confound-injected negative controls and corroborated by a deterministic non-LLM ruler; human agreement is 0.82 on extreme anchors but ~0 in the naturalistic middle, so all quantitative claims are anchored to pole-separated contrasts.
Abstract (translated)
URL
https://arxiv.org/abs/2607.11437
PDF
-
Beyond Sally-Anne: Evaluating Theory of Mind in LLMs using Epistemic Schelling Points
2026-07-13 10:27:22Roberta Rocca, Sami Boukortt, Geoff Keeling, Winnie StreetAbstract
Text-based evaluations of Theory of Mind (ToM) in Large Language Models (LLMs) often involve cognitive tests akin to the Sally-Anne task that can be gamed due to exposure to relevantly similar tasks in pre-training and do not obviously test models' functional ToM abilities in ways that generalize to naturalistic settings. To address these issues, we introduce the Epistemic Asymmetry Schelling Task (EAST), a two-player dialogue game designed to benchmark robust and generalizable ToM abilities. By requiring LLM-LLM dyads to independently converge on semantic Schelling points under varying states of epistemic transparency, we evaluate whether models can robustly apply ToM to achieve coordination. Our results reveal a significant capability gap in functional social reasoning, with only frontier models successfully navigating the varying epistemic demands of the tasks. Analysis of reasoning traces shows that coordination failures are primarily driven by epistemic tracking errors, such as conflating private knowledge with mutual knowledge. Despite high performance on traditional static benchmarks, our study shows that robust social reasoning and epistemic tracking remain a critical bottleneck, providing concrete targets for future LLM evaluation and development.
Abstract (translated)
URL
https://arxiv.org/abs/2607.11363
PDF
-
MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment
2026-07-13 04:19:37Junyoung Park, Namgyu Park, Sechan Lee, Yoon-Chan Jhi, Jihoon Cho, Sangdon ParkAbstract
Modern large language models (LLMs) operate in interactive multi-turn settings, making multi-turn jailbreaking a realistic threat model and an important setting for automated red teaming. A core challenge in learning multi-turn jailbreak attackers is credit assignment: different turns contribute differently to the final outcome, yet existing learning signals are often too coarse to identify their individual contributions. We propose decomposed credit GRPO (DC-GRPO), a unified turn-level credit assignment framework for Group Relative Policy Optimization in multi-turn jailbreak learning. DC-GRPO assigns a separate group-relative learning signal to each turn by combining immediate and future credit, avoiding the credit misassignment induced by broadcasting a single trajectory-level score across the dialogue. We instantiate this framework with static and dynamic weighting rules that differ in how the two credit sources are balanced while sharing the same turn-level structure. Across multiple victim LLMs and benchmarks, the dynamic- and static-weighted variants achieve average ASR5@3 scores of 98.26% and 97.88%, respectively, substantially outperforming the state-of-the-art methods, including SEMA (86.58%) and TROJail (86.23%). Their consistently strong performance indicates that the central empirical benefit comes from turn-level group-relative credit assignment rather than a particular weighting rule. Warning: This paper contains examples of harmful content.
Abstract (translated)
URL
https://arxiv.org/abs/2607.11070
PDF
-
Same Stories, Different Journeys: From Social Comparison to Sensemaking in AI-Mediated Peer Career Exploration
2026-07-13 03:11:17Pengping Tan, Baoquan Zhao, Zhenhui PengAbstract
Young job seekers frequently turn to social media to compare themselves with peers and make sense of career possibilities. However, passive feed browsing creates a paradox: the authentic peer content that provides emotional grounding also triggers potentially detrimental upward social comparison and cognitive overload. Previous work has either structured online user-generated content to reduce noise without changing the passive browsing modality, or built AI-powered career exploration systems that disregard authentic human experiences. To address this gap, we developed JobMate, an interactive system that transforms real social media career posts into persona-grounded conversational AI agents, shifting the interaction from passive scrolling to active, personalized dialogue. We conducted a between-subjects study ($N$ = 24, three disciplines) comparing JobMate with native RedNote browsing. Our study shows that JobMate's AI-mediated dialogue redirected social comparison from potentially detrimental upward comparison toward constructive self-reframing, while promoting sensemaking through active conversational engagement. However, users still relied on the authenticity of real peer content for emotional grounding. We discuss design implications for AI systems that augment authentic online user-generated content consumption across social comparison contexts.
Abstract (translated)
URL
https://arxiv.org/abs/2607.11039
PDF
-
When Do Causal World Models Help Modular LLM Agents
2026-07-12 04:03:37Xinyuan Song, Zekun CaiAbstract
LLM agents increasingly act through modular systems, such as order, payment, inventory, and shipment services, where actions in one module change which transitions are valid in another. Standard world models usually fit observational traces, but this is not the quantity needed for intervention-time planning: a trace may show that payment precedes shipment without identifying whether payment authorizes shipment, inventory mediates the effect, or a hidden trigger explains both. We study this gap through FedCausalCompose, a causal world-model framework for modular LLM agents in which local actions provide intervention-response evidence for cross-module interfaces. We first show that observational world models incur an irreducible interventional error under unblocked back-door paths, that interface recovery improves with intervention-response coverage, and that an oracle causal composition can beat the non-causal lower bound when coverage and local mechanism errors are controlled. We then test the resulting prediction in diagnostic agent settings. Causal interfaces help most in structured tool environments, where API signatures expose preconditions and downstream effects. In contrast, dialogue and narrative environments often ignore raw edge lists unless a short attention anchor makes the causal information decision-relevant. These results identify a concrete condition for causal world models in LLM agents: causal structure helps when cross-module interfaces are both statistically identifiable and presented in a form the agent can use at action time.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00012
PDF
-
Incremental Risk Assessment of Progressive Elder Financial Scams via Instruction-Tuned Small Language Models
2026-07-11 19:25:30Parviz Ghafariasl, Weimin Fu, Xiaolong Guo, Shing I. ChangAbstract
Financial scams targeting older adults increasingly occur through text and voice channels such as email, SMS, and phone calls, unfolding over multiple conversational turns that begin with impersonation or casual contact, escalate through trust building and urgency, and culminate in requests for sensitive information or financial transfers. Because risk signals emerge incrementally across turns, effective detection requires models that continuously update risk estimates under resource-constrained deployment settings. We propose a cumulative turn-based risk assessment framework that incrementally aggregates conversational turns and re-estimates risk at each step, enabling dynamic scam monitoring across progressively evolving conversations. A multi-turn dialogue dataset is constructed to cover investment, charity, and tech support scam scenarios, with each dialogue containing two to eight turns and annotated at every cumulative stage with a qualitative risk level, a continuous risk score, an explanatory rationale, and a safety recommendation. Four small language models (Phi-4, LLaMA-3.2, DeepSeek-R1, and Qwen3) are fine-tuned and evaluated under a unified training framework. Fine-tuned small models capture fraud-related linguistic cues and cross-turn escalation patterns while maintaining compact architectures suitable for mobile and resource-constrained deployment settings. Among the evaluated models, Phi-4 and LLaMA-3.2 achieve stronger turn-aware risk estimation performance relative to their parameter scale. These results suggest that structured cumulative modeling can support incremental scam risk assessment in deployment-oriented settings while highlighting the potential of compact language models for privacy-aware and on-device fraud protection.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00005
PDF
-
Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging
2026-07-11 18:22:49Jinglan Gong, Jiefan Lu, Hewei Guo, Kehan Li, Zhiyuan Han, Jihang Jiang, Wenwen Tong, Lewei LuAbstract
Evaluating large language models (LLMs) as multi-turn conversational partners requires probing capabilities that single-turn benchmarks miss: persona consistency, evolving intent tracking, emotional dynamics, and goal completion. We introduce EYT-Bench, a human-centered benchmark built around a three-party decoupled design: a persona-grounded user simulator, a target model that separates intent perception from response generation, and an independent third-party LLM judge with optional multi-judge ensembling. Personas are sampled from public human-curated corpora, Nemotron-Personas-USA and PersonaMem-v2, rather than synthesized, reducing LLM-induced persona bias. EYT-Bench also introduces two trajectory-level metrics: embedding-based intent drift and final-intent completion rate (FICR), inspired by tau-bench. In a 17-target x 200-dialogue evaluation, EYT-Bench reveals four findings: (i) state-of-the-art closed- and open-source models are statistically close on subjective dimensions (empathy / persona / anthropomorphism vary within <= 0.3), but differ by up to 9x on objective intent tracking; (ii) reasoning ("thinking on") sharply improves objective tracking on long-context personas (+0.47-0.50 latent-intent accuracy on Gemma-4) while leaving subjective scores nearly unchanged; (iii) persona format dominates trajectory spread, with FICR saturating above 0.95 on Nemotron-USA but spreading from 0.53 to 0.88 on PersonaMem-v2; and (iv) the warm-up effect is robust on 16/17 models (one outlier, GPT-5.5, reverses the effect), with stable rankings across alpha in [0.05, 0.15]. A cross-judge ablation using deepseek-v4-pro confirms that target rankings and final-intent satisfaction are preserved across judges.
Abstract (translated)
URL
https://arxiv.org/abs/2607.10428
PDF
-
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory
2026-07-11 15:24:43Jiayi Tian, Shiao Liu, Yuting Xu, Jia Lu, Zihao Guan, Honglin Han, Di Yang, Minqi Gu, Yifei Qian, Tianlin Zhang, Yanqing Zhu, Zeqian Ye, Menglin Yang, Fei Wang, Xu Hu, Xiuxian Li, Wei Zhang, Shihui Su, Yiyan Ji, Jingbo Wang, Ziteng Feng, Jiaheng Liu, Zhaoxiang Zhang, Xiaolong Wu, Mingyang Yin, Zedong Chu, Mu XuAbstract
Recent VLM and VLA systems have improved robotic perception and action prediction, yet long-horizon embodied agents still require a general runtime layer for reasoning, memory, tool use, verification, and cross-embodiment execution. We present ABot-AgentOS, a general robotic Agent Operating System that sits above low-level controllers and provides a deliberative agent layer for scene-conditioned planning, context-isolated skill execution, multi-stage verification, multi-modal memory, and edge-cloud collaboration. To evaluate such systems, we introduce EmbodiedWorldBench, an executable benchmark with 16 indoor, outdoor, and hybrid scenes, four difficulty levels, and over 200 tasks involving navigation, object search, NPC dialogue, dynamic events, and trace-grounded scoring. ABot-AgentOS further introduces Universal Multi-modal Graph Memory, a persistent source-grounded substrate that converts dialogue, visual observations, spatial context, temporal relations, and task traces into typed nodes and edges. A failure-driven self-evolution loop converts diagnosed memory failures into gated runtime evo-assets that are promoted only to later evaluation splits, preventing current-split ground-truth leakage while enabling continual improvement. On an initial EmbodiedWorldBench subset, ABot-AgentOS improves over a single-controller baseline in both task success and goal completion. Across memory benchmarks, ABot-AgentOS Static achieves 87.5 on LoCoMo, 59.9 on OpenEQA EM-EQA, 88.6 on Mem-Gallery, and 76.5 Acc@All on NExT-QA; self-evolution further improves LoCoMo to 88.7, OpenEQA to 60.4, and Mem-Gallery to 89.0. These results suggest that a general Agent OS layer can improve long-horizon embodied execution while providing persistent, auditable memory for continual interaction.
Abstract (translated)
URL
https://arxiv.org/abs/2607.10350
PDF
-
PolyInterview: An LLM-based Platform for Immersive Mock Interview Practice with Comprehensive Multimodal Assessment
2026-07-11 13:33:50Zhiyuan Wen, Jiannong Cao, Zijian Wang, Chen Chen, Xiaoyun Liu, Jianing Yin, Zhuo LiAbstract
Preparing for job interviews is important for securing desired positions, yet realistic practice remains difficult to access: real interviews are infrequent, expert mock coaching is costly, and self-practice offers neither adaptive dialogue nor structured assessment. Existing systems typically address only parts of this need through fixed question sequences, limited communication channels, or feedback with little supporting evidence. We present PolyInterview, an LLM-based platform for immersive mock interview practice with comprehensive multimodal assessment. PolyInterview uses the target job description and CV to generate questions tailored to the role and candidate, conducts multi-turn spoken interviews with a lip-synced digital human interviewer that asks answer-aware follow-up questions, and evaluates response content, vocal delivery, and non-verbal behavior. Four parallel evaluators produce 13 behavior-level features that are aggregated into 10 assessment aspects and two competency tracks. Guided by the KSA and STAR frameworks, the report links each score to behavioral evidence and actionable recommendations. PolyInterview is publicly accessible. Its current all-account snapshot contains 101 accounts, 1,564 interview sessions, 7,665 generated questions, and 1,422 five-stage question sets. Generated questions are more closely aligned with their matched job description than with cross-role job descriptions in 93.7% of sessions. An evaluation by ten experts found strong question plans and actionable feedback.
Abstract (translated)
URL
https://arxiv.org/abs/2607.10310
PDF
