MeetBench-XL: Calibrated Multi-Dimensional Evaluation and Learned Dual-Policy Agents for Real-Time Meetings

Enterprise meeting environments require AI assistants that handle diverse operational tasks, from rapid fact checking during live discussions to cross meeting analysis for strategic planning, under strict latency, cost, and privacy constraints. Existing meeting benchmarks mainly focus on simplified question answering and fail to reflect real world enterprise workflows, where queries arise organically from multi stakeholder collaboration, span long temporal contexts, and require tool augmented reasoning. We address this gap through a grounded dataset and a learned agent framework. First, we introduce MeetAll, a bilingual and multimodal corpus derived from 231 enterprise meetings totaling 140 hours. Questions are injected using an enterprise informed protocol validated by domain expert review and human discriminability studies. Unlike purely synthetic benchmarks, this protocol is grounded in four enterprise critical dimensions: cognitive load, temporal context span, domain expertise, and actionable task execution, calibrated through interviews with stakeholders across finance, healthcare, and technology sectors. Second, we propose MeetBench XL, a multi dimensional evaluation protocol aligned with human judgment that measures factual fidelity, intent alignment, response efficiency, structural clarity, and completeness. Third, we present MeetMaster XL, a learned dual policy agent that jointly optimizes query routing between fast and slow reasoning paths and tool invocation, including retrieval, cross meeting aggregation, and web search. A lightweight classifier enables accurate routing with minimal overhead, achieving a superior quality latency tradeoff over single model baselines. Experiments against commercial systems show consistent gains, supported by ablations, robustness tests, and a real world deployment case study.Resources: https://github.com/huyuelin/MeetBench.

State Rank Dynamics in Linear Attention LLMs

Linear Attention Large Language Models (LLMs) offer a compelling recurrent formulation that compresses context into a fixed-size state matrix, enabling constant-time inference. However, the internal dynamics of this compressed state remain largely opaque. In this work, we present a comprehensive study on the runtime state dynamics of state-of-the-art Linear Attention models. We uncover a fundamental phenomenon termed State Rank Stratification, characterized by a distinct spectral bifurcation among linear attention heads: while one group maintains an effective rank oscillating near zero, the other exhibits rapid growth that converges to an upper bound. Extensive experiments across diverse inference contexts reveal that these dynamics remain strikingly consistent, indicating that the identity of a head,whether low-rank or high-rank,is an intrinsic structural property acquired during pre-training, rather than a transient state dependent on the input data. Furthermore, our diagnostic probes reveal a surprising functional divergence: low-rank heads are indispensable for model reasoning, whereas high-rank heads exhibit significant redundancy. Leveraging this insight, we propose Joint Rank-Norm Pruning, a zero-shot strategy that achieves a 38.9\% reduction in KV-cache overhead while largely maintaining model accuracy.

Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience

Deep search agents powered by large language models have demonstrated strong capabilities in multi-step retrieval, reasoning, and long-horizon task execution. However, their practical failures often stem from the lack of mechanisms to monitor and regulate reasoning and retrieval states as tasks evolve under uncertainty. Insights from cognitive neuroscience suggest that human metacognition is hierarchically organized, integrating fast anomaly detection with selectively triggered, experience-driven reflection. In this work, we propose Deep Search with Meta-Cognitive Monitoring (DS-MCM), a deep search framework augmented with an explicit hierarchical metacognitive monitoring mechanism. DS-MCM integrates a Fast Consistency Monitor, which performs lightweight checks on the alignment between external evidence and internal reasoning confidence, and a Slow Experience-Driven Monitor, which is selectively activated to guide corrective intervention based on experience memory from historical agent trajectories. By embedding monitoring directly into the reasoning-retrieval loop, DS-MCM determines both when intervention is warranted and how corrective actions should be informed by prior experience. Experiments across multiple deep search benchmarks and backbone models demonstrate that DS-MCM consistently improves performance and robustness.

Lightweight High-Fidelity Low-Bitrate Talking Face Compression for 3D Video Conference

The demand for immersive and interactive communication has driven advancements in 3D video conferencing, yet achieving high-fidelity 3D talking face representation at low bitrates remains a challenge. Traditional 2D video compression techniques fail to preserve fine-grained geometric and appearance details, while implicit neural rendering methods like NeRF suffer from prohibitive computational costs. To address these challenges, we propose a lightweight, high-fidelity, low-bitrate 3D talking face compression framework that integrates FLAME-based parametric modeling with 3DGS neural rendering. Our approach transmits only essential facial metadata in real time, enabling efficient reconstruction with a Gaussian-based head model. Additionally, we introduce a compact representation and compression scheme, including Gaussian attribute compression and MLP optimization, to enhance transmission efficiency. Experimental results demonstrate that our method achieves superior rate-distortion performance, delivering high-quality facial rendering at extremely low bitrates, making it well-suited for real-time 3D video conferencing applications.

LTS-VoiceAgent: A Listen-Think-Speak Framework for Efficient Streaming Voice Interaction via Semantic Triggering and Incremental Reasoning

Real-time voice agents face a dilemma: end-to-end models often lack deep reasoning, while cascaded pipelines incur high latency by executing ASR, LLM reasoning, and TTS strictly in sequence, unlike human conversation where listeners often start thinking before the speaker finishes. Since cascaded architectures remain the dominant choice for complex tasks, existing cascaded streaming strategies attempt to reduce this latency via mechanical segmentation (e.g., fixed chunks, VAD-based splitting) or speculative generation, but they frequently either break semantic units or waste computation on predictions that must be rolled back. To address these challenges, we propose LTS-VoiceAgent, a Listen-Think-Speak framework that explicitly separates when to think from how to reason incrementally. It features a Dynamic Semantic Trigger to detect meaningful prefixes, and a Dual-Role Stream Orchestrator that coordinates a background Thinker (for state maintenance) and a foreground Speaker (for speculative solving). This parallel design enables "thinking while speaking" without blocking responses. We also introduce a Pause-and-Repair benchmark containing natural disfluencies to stress-test streaming robustness. Experiments across VERA, Spoken-MQA, BigBenchAudio, and our benchmark show that LTS-VoiceAgent achieves a stronger accuracy-latency-efficiency trade-off than serial cascaded baselines and existing streaming strategies.

Unveiling and Simulating Short-Video Addiction Behaviors via Economic Addiction Theory

Short-video applications have attracted substantial user traffic. However, these platforms also foster problematic usage patterns, commonly referred to as short-video addiction, which pose risks to both user health and the sustainable development of platforms. Prior studies on this issue have primarily relied on questionnaires or volunteer-based data collection, which are often limited by small sample sizes and population biases. In contrast, short-video platforms have large-scale behavioral data, offering a valuable foundation for analyzing addictive behaviors. To examine addiction-aware behavior patterns, we combine economic addiction theory with users' implicit behavior captured by recommendation systems. Our analysis shows that short-video addiction follows functional patterns similar to traditional forms of addictive behavior (e.g., substance abuse) and that its intensity is consistent with findings from previous social science studies. To develop a simulator that can learn and model these patterns, we introduce a novel training framework, AddictSim. To consider the personalized addiction patterns, AddictSim uses a mean-to-adapted strategy with group relative policy optimization training. Experiments on two large-scale datasets show that AddictSim consistently outperforms existing training strategies. Our simulation results show that integrating diversity-aware algorithms can mitigate addictive behaviors well.

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

Personalized large language models (LLMs) adapt model behavior to individual users to enhance user satisfaction, yet personalization can inadvertently distort factual reasoning. We show that when personalized LLMs face factual queries, there exists a phenomenon where the model generates answers aligned with a user's prior history rather than the objective truth, resulting in personalization-induced hallucinations that degrade factual reliability and may propagate incorrect beliefs, due to representational entanglement between personalization and factual representations. To address this issue, we propose Factuality-Preserving Personalized Steering (FPPS), a lightweight inference-time approach that mitigates personalization-induced factual distortions while preserving personalized behavior. We further introduce PFQABench, the first benchmark designed to jointly evaluate factual and personalized question answering under personalization. Experiments across multiple LLM backbones and personalization methods show that FPPS substantially improves factual accuracy while maintaining personalized performance.

MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching

Tool-Integrated Reasoning (TIR) empowers large language models (LLMs) to tackle complex tasks by interleaving reasoning steps with external tool interactions. However, existing reinforcement learning methods typically rely on outcome- or trajectory-level rewards, assigning uniform advantages to all steps within a trajectory. This coarse-grained credit assignment fails to distinguish effective tool calls from redundant or erroneous ones, particularly in long-horizon multi-turn scenarios. To address this, we propose MatchTIR, a framework that introduces fine-grained supervision via bipartite matching-based turn-level reward assignment and dual-level advantage estimation. Specifically, we formulate credit assignment as a bipartite matching problem between predicted and ground-truth traces, utilizing two assignment strategies to derive dense turn-level rewards. Furthermore, to balance local step precision with global task success, we introduce a dual-level advantage estimation scheme that integrates turn-level and trajectory-level signals, assigning distinct advantage values to individual interaction turns. Extensive experiments on three benchmarks demonstrate the superiority of MatchTIR. Notably, our 4B model surpasses the majority of 8B competitors, particularly in long-horizon and multi-turn tasks. Our codes are available at https://github.com/quchangle1/MatchTIR.

UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning

User simulators serve as the critical interactive environment for agent post-training, and an ideal user simulator generalizes across domains and proactively engages in negotiation by challenging or bargaining. However, current methods exhibit two issues. They rely on static and context-unaware profiles, necessitating extensive manual redesign for new scenarios, thus limiting generalizability. Moreover, they neglect human strategic thinking, leading to vulnerability to agent manipulation. To address these issues, we propose UserLM-R1, a novel user language model with reasoning capability. Specifically, we first construct comprehensive user profiles with both static roles and dynamic scenario-specific goals for adaptation to diverse scenarios. Then, we propose a goal-driven decision-making policy to generate high-quality rationales before producing responses, and further refine the reasoning and improve strategic capabilities with supervised fine-tuning and multi-reward reinforcement learning. Extensive experimental results demonstrate that UserLM-R1 outperforms competitive baselines, particularly on the more challenging adversarial set.

GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR

Reinforcement Learning with Verifiable Rewards (RLVR) is crucial for advancing large-scale reasoning models. However, existing parameter-efficient methods, such as PiSSA and MiLoRA, are designed for Supervised Fine-Tuning (SFT) and do not account for the distinct optimization dynamics and geometric structures of RLVR. Applying these methods directly leads to spectral collapse and optimization instability, which severely limit model performance. Meanwhile, alternative approaches that leverage update sparsity encounter significant efficiency bottlenecks on modern hardware due to unstructured computations. To address these challenges, we propose GeoRA (Geometry-Aware Low-Rank Adaptation), which exploits the anisotropic and compressible nature of RL update subspaces. GeoRA initializes adapters by extracting principal directions via Singular Value Decomposition (SVD) within a geometrically constrained subspace while freezing the residual components. This method preserves the pre-trained geometric structure and enables efficient GPU computation through dense operators. Experiments on Qwen and Llama demonstrate that GeoRA mitigates optimization bottlenecks caused by geometric misalignment. It consistently outperforms established low-rank baselines on key mathematical benchmarks, achieving state-of-the-art (SOTA) results. Moreover, GeoRA shows superior generalization and resilience to catastrophic forgetting in out-of-domain tasks.