CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance

Large Language Models (LLMs) deployed in dynamic financial environments face a critical challenge: maintaining factual accuracy as market conditions, regulations, and corporate facts change continuously. While 4-bit quantization enables efficient deployment, it severely limits the viability of sequential memory editing: existing methods undergo catastrophic performance degradation under this "quantization stability crisis." We introduce CACHE-UK (Contextual Adaptive Continual Hybrid Editor for UK Finance), a stability-aware memory editing framework specifically designed for domain-specific, quantized LLMs. CACHE-UK integrates three components: a rank-1 LoRA perturbation mechanism that confines edits to the low-rank adapter subspace, a financial domain prioritization module for content-adaptive edit strength, and a closed-loop Stability Controller that tracks "degradation debt" to prevent catastrophic forgetting across sequential updates. Evaluated on a 4-bit quantized OpenLLaMA-3B model with a curated UK financial corpus of 88,021 documents, CACHE-UK reduces knowledge degradation by 11-17% relative to adapted baselines under identical 4-bit constraints -- its most robust effect -- while attaining the highest test success (generalization) rate observed in our setting (28%, a 6 percentage point improvement over the strongest adapted baseline). These results indicate that stability-aware editing can improve factual maintenance in resource-constrained financial LLM deployments, though absolute generalization rates remain low.

RouteRec: Strict Evaluation of Recommender-Agent Selection and Aggregation

Recommender systems increasingly face a choice among heterogeneous agents -- collaborative filters, sequential models, content-based retrievers, and LLM-based rerankers -- yet no single agent is uniformly best. We study this choice as task-aware agent ranking under cost constraints using RouteRec, a framework that compares request-level hard selection with item-level learned aggregation over four traditional recommender agents and one LLM reranker agent. On MovieLens-1M, the full quality oracle has substantial headroom (HR@10 = 0.584), confirming that useful cross-agent signal exists. Under a leakage-free 5-fold out-of-fold protocol, however, hard selection remains below BM25 (0.223 vs. 0.254), and selective LLM escalation does not improve it. The same protocol yields a different outcome for learned aggregation: its cheap-only variant matches BM25 in HR and has a higher NDCG point estimate (0.123 vs. 0.114), while gated all-agent aggregation reaches HR@10 = 0.295 with 70.2\% LLM calls. The resulting lesson is not that routing is solved, but that request-level selection of one complete agent list is too coarse for this sparse fixed-candidate setting; item-level aggregation is the more promising action space.

Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation

Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. However, existing frameworks typically call APIs based on coarse-grained matching between tasks and the functions of expert models or tools, while overlooking critical factors such as performance variability and cost efficiency among functionally similar alternatives. To address this, we propose Agora, a framework that introduces an incentive-compatible auction mechanism for dynamically allocating tasks to expert models and tools. By treating reasoning steps as tradeable items, Agora enables agents to bid based on their rectified competence-ensuring that critical logic is routed to the most capable solver rather than the most overconfident one. Evaluations across five benchmarks show that Agora improves over matched single-model, routing, and cascade baselines under comparable candidate pools, while exposing a controllable cost-quality trade-off through a single auction parameter.

From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent

Large language models (LLMs) have shown promise in automating scientific peer review. However, existing approaches often struggle to generate in-depth reviews supported by concrete evidence. We argue that a key limitation is the lack of flexibility to proactively investigate suspicious parts of a paper based on accumulated evidence, as human reviewers do. In this paper, we explore how to enable an LLM-based review agent to perform such proactive investigation. We find that this can be naturally formulated as a Markov Decision Process (MDP), and propose ProReviewer, a scientific peer review agent that proactively reviews a paper guided by a maintained, structured review log. The structured review log serves as a workspace for the agent to track evidence and intermediate findings collected during review. Experiments show that ProReviewer with an 8B backbone, trained by supervised fine-tuning and optimized by reinforcement learning, achieves the highest average score across five quality dimensions, outperforming prompt-based methods with much larger frontier LLMs by up to 39% and the strongest fine-tuned baseline by 16% relatively. It also attains the highest win rates against baselines in human evaluation.

When to Think Deeply: Inhibitory Deliberation for LLM Reasoning

Reasoning Large Language Models can improve problem-solving performance through deliberative inference, but invoking slow reasoning for every input is computationally expensive and often unnecessary. We propose IDPR, a framework for response-conditioned inhibitory deliberation. IDPR first generates a concise intuitive answer and then uses an inhibition controller to decide whether that specific response should be released or suppressed in favor of slow reasoning. Unlike input-only routers, the inhibition controller conditions on the fast answer and fast-side evidence, including confidence, logit margin, parseability, and generation cost. We train the controller from paired fast-slow outcomes and select the inhibition threshold on a held-out validation set under an accuracy-first slow-call budget. On a held-out 5,000-example mathematical reasoning test set, IDPR invokes slow reasoning on only 8.20% of examples and improves accuracy from 47.90% to 48.92%. Under the same slow-call budget, random routing decreases accuracy to 46.76%, while the strongest confidence-based baseline reaches 48.22%. IDPR also achieves the highest corrective precision, showing that response-conditioned inhibition better identifies fast answers that benefit from slow reasoning.

Explainable Forensics of Manipulated Segments in Untrimmed Long Videos

The rapid advancement of AI-driven video generation has transformed content creation, while simultaneously increasing the risk of misinformation through localized manipulations in long-form videos. Existing video forensic methods predominantly operate on short, independent clips, and thus fail to capture realistic scenarios where AI-generated content is sparsely embedded within otherwise authentic footage. To bridge this gap, we formulate the task of Temporal AI-Generated Segment Localization and Explanation, which targets authenticity detection, temporal localization, and interpretable analysis of manipulated segments in untrimmed long videos. We further introduce TASLE, a large-scale benchmark comprising 12,472 untrimmed videos with diverse manipulation patterns and rich annotation signals, including temporal boundaries, authenticity labels, and segment-level rationales. In addition, we propose MSLoc, a coarse-to-fine forensic baseline that combines a boundary-sensitive proposal generation module for efficient long-video scanning with an MLLM-based refinement module for precise boundary localization and interpretable reasoning. Experiments validate the effectiveness of the proposed baseline, highlighting the importance of segment-level explainable forensics for long-form AI-generated video analysis. Our dataset and code are publicly available at https://debby-0527.github.io/TASLE.

Bilateral Teleoperation with Compliant 6-DOF Pose-and-Force Sensing

Existing bilateral teleoperation platforms still rely on costly rigid six-axis force/torque sensors, tightly coupled leader-follower hardware, and kilohertz control loops. We present a Cartesian bilateral framework built on the hardware-agnostic WinGs Operating Studio (WOS) middleware, in which a low-cost compliant 6-DOF pose-and-force sensing end-effector, Delta6, is mounted on both sides so that each manipulator behaves as an end-effector 6-DOF series elastic actuator (SEA). The leader runs a damping-only admittance loop with a 6-D biquad notch filter; the follower realizes a stiffness-damping impedance through a position-based outer loop with a PID wrench-to-pose mapping. Three time scales (hardware I/O, mid-rate impedance/admittance, low-rate teleoperation messages) are explicitly decoupled, enabling the same application to drive heterogeneous arms. On a Lite6/FR3 testbed at 150 Hz, the system tracks stably under delays up to $120\pm40$ ms and 1% packet loss, matches the prescribed virtual stiffness in contact, and shows a favorable cumulative energy signature in passivity-style tests.

Spacetime Optimal-Transport Attention for Visuo-Haptic Imitation Learning of Contact-Rich Manipulation

Contact-rich manipulation tasks such as tight-clearance insertion, connector mating, polishing, and surface-conforming wiping remain difficult for data-driven controllers because they couple discontinuous contact dynamics, partial observability, and strict safety constraints. No single sensing modality suffices: vision supplies global context before contact, force/torque (F/T) feedback governs interaction after contact, and proprioceptive pose provides a consistent kinematic backbone. Most prior imitation-learning policies for contact-rich tasks operate on uni- or bi-modal signals, and the few that fuse three modalities typically adopt off-the-shelf attention modules with no explicit prior on how attention mass should be distributed across task-relevant regions. We present Spacetime Optimal-Transport Attention (SO-TA), a tri-modal fusion backbone that replaces softmax-normalized patch attention by an entropy-regularized Optimal Transport (OT) alignment between force-pose-derived sub-queries and visual patches. Explicit marginal constraints act as a structured inductive bias for contact-rich tasks, encouraging conditioning-aware spatial selection that is stable across illumination, distractors, and partial occlusion. SO-TA is paired with a diffusion-based sequence policy mapping observation windows to pose-action chunks. We evaluate SO-TA on three real-robot tasks: tight peg-in-hole assembly, BCM wiring-connector insertion, and curved-surface mark erasing. With ~200 rollouts per condition, SO-TA reaches 100% success on tight peg-in-hole versus 93% for cross-attention at matched capacity, and retains 82.5% success under illumination, distractor, and partial-occlusion perturbations where a concatenation baseline drops to 43.5%. OT-derived patch heatmaps and leave-one-out modality-influence ratios provide interpretable, phase-dependent diagnostics.

From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation

Legal consultation question answering (Legal CQA) presents unique challenges compared to traditional legal QA tasks, including the scarcity of high-quality training data, complex task composition, and strong contextual dependencies. To address these, we construct JurisCQAD, a large-scale dataset of over 43,000 real-world Chinese legal queries annotated with expert-validated positive and negative responses, and design a structured task decomposition that converts each query into a legal element graph integrating entities, events, intents, and legal issues. We further propose JurisMA, a modular multi-agent framework supporting dynamic routing, statutory grounding, and stylistic optimization. Combined with the element graph, the framework enables strong context-aware reasoning, effectively capturing dependencies across legal facts, norms, and procedural logic. Trained on JurisCQAD and evaluated on a refined LawBench, our system significantly outperforms both general-purpose and legal-domain LLMs across multiple lexical and semantic metrics, demonstrating the benefits of interpretable decomposition and modular collaboration in Legal CQA.

One Interface, Many Robots: Unified Real-Time Low-Level Motion Planning for Collaborative Arms

This paper proposes a common interface for real-time low-level motion planning of collaborative robotic arms, aimed at enabling broader applicability and improved portability across heterogeneous hardware platforms. In previous work, we introduced WinGs Operating Studio (WOS), a middleware solution that abstracts diverse robotic components into uniform software resources and provides a broad suite of language-agnostic APIs. This paper specifically focuses on its minimal yet flexible interface for real-time end-effector trajectory control. By employing an n-degree polynomial interpolator in conjunction with a quadratic programming solver, the proposed method generates smooth, continuously differentiable trajectories with precise position, velocity, and acceleration profiles. We validate our approach in three distinct scenarios. First, in an offline demonstration, a collaborative arm accurately draws various geometric shapes on paper. Second, in an interruptible, low-frequency re-planning setting, a robotic manipulator grasps a dynamic object placed on a moving mobile robot. Finally, we conducted a teleoperation experiment in which one robotic arm controlled another to perform a series of dexterous manipulations, confirming the proposed method's reliability, versatility, and ease of use.