Science & Mathematics

Retrieval-augmented generation (RAG) grounds language models in retrieved evidence, but its outputs often contain claims unsupported by that evidence. Recent multi-agent RAG systems decompose the pipeline into cooperative decisions, yet they typically optimize all agents under a shared task reward such as EM or F1, which measures answer overlap rather than faithfulness to evidence. We propose a hallucination-aware multi-agent RAG framework that combines the task reward with an internal hallucination-risk signal computed from the generator's attention-head norms. Three role-specific LoRA adapters, a query planner, an evidence selector, and an answer generator, share a frozen backbone. A lightweight critic is trained once on TruthfulQA truthful/false pairs and then kept frozen, providing a complementary risk score that is added to the shared reward during cooperative PPO training. Across three backbones (Qwen3-8B, Llama3-8B, Llama2-13B) and three benchmarks (RAGTruth, HotpotQA, 2WikiMultiHopQA), our method improves task performance and reduces hallucination rates over the strongest multi-agent baseline. Ablations and critic diagnostics show that the TruthfulQA-calibrated signal provides useful reward shaping that transfers across RAG tasks.

Estimating forces acting on Deformable Linear Objects (DLOs) is challenging due to their underactuated nature. However, reliable contact estimation is crucial to precisely control them and enable safe manipulation tasks. Differently from the various approaches presented in the literature, this work adopts a probabilistic formulation where the DLO state and sensor data are related through conditional distributions. In particular, factor graphs are used to determine the magnitude, direction, and location of a 3D force acting on a DLO, while simultaneously reconstructing its shape. Since DLOs are not actuated and are typically thin, like cables and wires, strain gauges and actuation readings are usually impractical. Therefore, to overcome this issue, this work is tested using one type of sensing information only, thus developing a generic technique suited for a wider variety of tasks. Realistic tests are performed by introducing noise into the measurements while the DLO follows a prescribed path in the presence of external forces that are accurately estimated.

Large language models (LLMs) can produce plausible but incorrect answers when they are uncertain, which can mislead users and undermine model reliability. Training models to abstain with reinforcement learning is a natural approach, but most existing methods use a fixed error penalty and therefore cannot adapt their behavior to different confidence requirements at inference time. We study \emph{explicit confidence targets}, where a user specifies a target \(p\) in the prompt and the model directly chooses whether to answer or abstain, with the goal of achieving an accuracy of at least \(p\) among answered questions. However, learning to respond to different confidence targets with a single model has proven difficult, and prior attempts have failed to distinguish different targets. We show that this failure comes from two problems: the reward signal that distinguishes different values of $p$ is often lost during optimization, while the original error penalty grows without bound as $p$ approaches one. We propose RLEC (\textbf{R}einforcement \textbf{L}earning with \textbf{E}xplicit \textbf{C}onfidence Targets), which preserves the learning signal needed to distinguish confidence targets, introduces a stable reward family that keeps the desired answer condition unchanged, and uses reward scheduling to balance effective learning and training stability. Together, these designs enable the first successful training of a single LLM for explicit confidence target control. Extensive experiments across diverse benchmarks and model scales show that RLEC largely preserves general capabilities and achieves competitive calibration performance. RLEC also supports fine-grained target control without an external decision system or threshold calibration after training. By making explicit confidence targets part of the trained policy, RLEC opens a new and more direct path toward behavioral calibration.

Large vehicles in cluttered environments are often blocked by movable obstacles, motivating mobile robot teams to clear traversable corridors. Navigation Among Movable Obstacles (NAMO) approaches often abstract obstacle displacements while neglecting robot dimensions, obstacle mass, contact geometry and forces, yielding physically infeasible plans. PushAround is a physics-informed hybrid search that couples geometric connectivity reasoning with short-horizon simulation to construct executable clearing plans. Repeated W-clearance connectivity graph (WCCG) queries expose frontier gaps requiring widening and rank them by estimated downstream costs. The search generates direct or recursive pushing candidates, selecting obstacles, directions, contacts and forces, and admits physics-evaluated candidates. Numerical experiments validate WCCG against standard connectivity checks and demonstrate scaling to denser clutter and teams of up to four robots, with robustness to simulated execution-side physical-parameter mismatch.

Tube-wise video completion reconstructs temporal trajectories at spatial locations unobserved in every frame. We propose a two-stage framework combining regularized masked Kronecker product decomposition (KPD) with cross-fitted self-supervised residual learning. First, we estimate a compact structural backbone directly from observed entries using cyclic component-wise least-squares updates, spatial and temporal factor regularization, and regularizer-optimal scale balancing. The exact updates yield a nonincreasing objective. Second, we address the mismatch between in-sample fitting errors and the prediction errors encountered at missing tubes. We partition observed tubes into folds and construct residual targets using backbone models fitted without the corresponding target tubes. A lightweight 3-D convolutional neural network then predicts corrections from the backbone, visible residual context, observation mask, and local detail features. Exact data consistency preserves observed measurements. Experiments include ablations, sensitivity analysis, grayscale and RGB video completion, and structured missing patterns. Our method achieves the highest mean PSNR and SSIM at the higher tested sampling rates on the grayscale benchmark. On eight selected DAVIS RGB sequences, it achieves the highest mean missing-region PSNR and full-frame SSIM and the lowest mean missing-tube temporal-gradient MAE at every evaluated sampling rate.

Vision-language navigation (VLN) requires an embodied agent to follow language instructions through 3D environments. Maintaining persistent episodic memory remains a challenge for VLM-based streaming agents in long-horizon navigation. We present MEMVLN, a streaming episodic memory framework that maintains a bounded bank of compressed perceptual features annotated with timesteps and action-derived relative poses, and produces compact memory tokens via cross-attention. We pair the proposed memory with a frozen pretrained geometry encoder. To learn the memory module, we design a masking-based trajectory summarization task with multi-granularity sub-trajectory decomposition, encouraging route reconstruction exclusively from episodic memory. Under navigation training restricted to the official R2R/RxR trajectories, MEMVLN achieves state-of-the-art performance on most reported metrics on standard VLN-CE benchmarks. Long-horizon analyses further characterize when episodic memory is useful. For physical evaluation, we collect 30 instruction-conditioned episodes in one physical scene, use 24 as demonstrations for post-training, and hold out six for testing. On the held-out episodes, MEMVLN improves success over the VLM baseline from 17% to 40%, and post-training further raises it to 47%.

Large language models (LLMs) are increasingly evaluated for fairness, yet most existing benchmarks audit one sensitive attribute at a time. This single-attribute paradigm can miss intersectional harms, where multiple attributes interact non-additively and produce failures that are invisible under marginal evaluation. We introduce ComFair, a configurable benchmark that converts existing fairness data into 479,066 controlled Dual- and Multi-attribute instances and pairs every augmented instance with its task-equivalent source. Across Recognition, Selection, Continuation, and Conversation, this pairing supports a unified audit of performance or bias-score shifts, how often added attributes introduce new errors or mask existing ones, and model-ranking stability. Experiments on ten LLMs show task- and subgroup-dependent sensitivity: discriminative tasks expose both transition directions even when aggregate changes are modest, generative tasks exhibit larger and directionally asymmetric shifts, and rankings vary with attribute composition. ComFair therefore provides a scalable controlled sensitivity audit---rather than a model of the natural joint distribution of identities---for testing the robustness of fairness-benchmark conclusions beyond single-attribute settings.

Connected and automated vehicles could allow reassigning lane directions and speed limits on every road frequently, but the benefit hinges on how traffic reroutes, and one-way roads can isolate junctions. We formulate network-wide dynamic lane allocation and directional speed limit control with one-way roads, lane clearing before each reversal, and a navigable graph kept strongly connected at all times. An action-resolution algorithm grounded in graph orientation theory admits a proposal closing a direction only if the network stays strongly connected and otherwise relaxes or reverts it, keeping all junctions mutually reachable within the model, even during clearing. All road controllers share one transformer whose attention, Global Endpoint Relation-Aware Spatio-Temporal Self-Attention (GERASTSA), spans all road-time tokens, biased by the endpoint relations between roads. It is pretrained on action-conditioned traffic forecasting and fine-tuned with per-road proximal policy optimization under a mixed reward that also credits neighboring roads and the network. On a 6 x 6 grid with commuter rush hours, the learned policy makes about two thirds of roads one-way in the peak direction and cuts daily delay by 90% against the initial configuration held fixed and by 85% against a tuned two-way load balancer. Restricted to two-way roads at test time, it gains only about as much as this balancer, whereas its learned speed limits add delay. Pretraining roughly halves the updates needed to surpass the fixed configuration. Of the ablations, only removing the relational bias or the spatial embedding clearly matters, multiplying delay about fivefold.

Retrieval-Augmented Generation (RAG) enhances the factual grounding of Large Language Models (LLMs) by incorporating external evidence, but also exposes them to corpus poisoning attacks. In particular, coordinated attacks can introduce multiple mutually reinforcing poisoned documents into retrieved contexts, making reliable evidence filtering challenging. To address this problem, we propose GuardRAG, a training-free and plug-and-play post-retrieval defense that exploits the semantic structure of retrieved evidence to identify suspicious document groups. Specifically, GuardRAG first expands the retrieval range and removes near-duplicate candidates, then partitions the retained documents using Hierarchical Agglomerative Clustering (HAC) with a query-adaptive threshold. Finally, it scores and prunes suspicious clusters based on query relevance, cluster size, and semantic compactness. Experiments across three question-answering datasets, multiple poisoning attacks, and six LLMs demonstrate that GuardRAG substantially reduces attack success rates while maintaining answer utility under clean retrieval.

Serverless computing has emerged as a pivotal cloud deployment paradigm due to its efficient utilization of on-demand resources. However, the persistent cold start problem continues to hinder system performance. Current strategies often employ oversimplified preloading/unloading mechanisms that inadequately exploit invocation patterns, failing to optimize the critical trade-off between startup latency and resource efficiency. Furthermore, existing approaches disregard practical constraints of memory-limited multi-worker environments, exacerbating function eviction and load imbalance issues. To address these limitations, we present SPES-Ext, a rule-based priority-aware scheduler designed for memory-constrained distributed worker nodes. Our methodology stems from two key observations: (1) serverless systems exhibit concentrated invocation patterns enabling behavioral predictability, and (2) these patterns permit function categorization for granular instance management. This insight posits that characteristic-driven prioritization enables optimal scheduling rules, leading to our system design, which integrates three coordinated components: predictive function provisioning, eviction optimization, and dynamic load balancing. Experimental validation demonstrates the superiority of SPES-Ext over state-of-the-art solutions: 80% reduction in $75^{th}$-percentile cold starts, 83.92% decrease in memory waste, and 52.49% improvement in worker load variance.

A graph neural network (GNN) forecasting a collection of load series combines two mechanisms, sharing parameters across series and reading neighboring series, and a gain over a non-graph model may come from either; telling them apart decides whether a graph is worth maintaining. We propose a model diagnostic protocol that compares the GNN with three reference models: a per-node network, a network shared across nodes without neighbors, and the same GNN without edges. Degree-preserving rewiring tests whether neighbor identity matters. After a tuned benchmark on regional load in France and on low-voltage feeders in the UK, we apply the protocol to deliberately short node histories, as when non-stationary demand leaves only recent observations relevant: the feeders, within one week, and a public dataset of client consumption series. On the feeders, sharing parameters recovers most of the error gap between node-specific models and GNNs, about two thirds against a regularized one. Adding the edges to an otherwise identical backbone brings a smaller gain, half or more of which disappears under rewiring. On the client series, the neighbor mean degrades the per-node model on the shorter window and the edges' gain is not consistently distinguishable from zero; on the regions of France, where each node's own history is already informative, the ranking between per-node models and GNNs changes with tuning. A synthetic study points to noisy local measurements as one regime where neighbors help. In an exploratory online aggregation, graph and non-graph forecasters appear complementary, and the weight assigned to GNNs is not proportional to their contribution. In none of the three datasets do the edges account for most of a GNN's advantage over node-specific models, so a forecasting gain should be credited to the graph only after comparison with per-node and shared references.

Learning generalizable humanoid loco-manipulation remains bottlenecked by costly real-world demonstrations. Simulation provides a scalable alternative, but requires visually faithful, physics-ready scenes and executable whole-body motions. We present Zero-HLM, a real-to-sim-to-real framework that transforms smartphone captures and simulated source demonstrations into scalable training data for humanoid loco-manipulation. Gaussian-guided agentic real-to-sim reconstruction aligns visual and physical scenes; motion-environment co-adaptation uses rollout feedback to correct whole-body references and interaction geometry. We generate 4,800 physically validated demonstrations for zero-shot transfer across three Unitree G1 tasks. Simulation-trained GR00T N1.7 achieves 66.7% mean full-task success, versus 46.7% with real-data training. On generalized configurations, expanded simulation training raises pooled success from 23% for base-trained real-data policies to 69%, without additional real demonstrations. Project page: https://young-bit.github.io/zero-hlm/

Blendshape generation for 3D models has been extensively researched, but very few works address generating blendshapes for models with multiple disconnected parts. We present a case study of generating fixed facial expression blendshapes for commercial anime-style 3D character models with up to 11 parts per face. To make sure that our system can handle models in a way that is agnostic to topology, we train neural networks to generate deformation fields around the input meshes. We employ at least one network to independently process each part, and the relative positions of their outputs are coordinated by having each network also process the geometry of an anchor part. We use two mechanisms to improve accuracy: having the networks predict whether the output displacement is zero or not, and classifying blendshapes into different size groups and dedicating a network to each group. We also introduce a method to improve blendshape quality by enhancing bilateral symmetry. Our method is simpler than recent neural-network-based works and solves a real problem of the user community of these models.

Understanding and operating with scientific charts is a standard approach in data analysis, and while humans are good at interpreting such charts, open vision-language models (VLMs) are known to perform poorly when it comes to question answering based on such data types. Motivated by an initial observation that many of their errors are due to inexact answering, we raise the following natural question: how much accuracy can we recover without changing the model at all? In this paper, we study this question by searching over inference programs and the code around a "frozen" version of the model. Using ideas from autonomous evolution (famously used in AlphaEvolve), we first start from a baseline inference program, and in each round we show an LLM judge the code together with a few failures on training questions, and ask for an improving evolutionary move. As usual in autonomous evolution approaches, the candidate programs are kept in a small pool ranked by training accuracy, and the next edit is performed on top-scorers from this pool. We run this approach on three VLMs and four popular benchmarks on scientific charts, and we measure the fraction of descriptive questions whose answer exactly matches the ground truth. The accuracy improves in all experimental settings. On average, it rises from 16.6% with the starting program to 41.3% with the evolved one, and the largest single increase is 55.2 percentage points. As a side benefit, our evolved program is 3.8x faster than the starting program, because short answers are easier to grade and faster to generate. Our results demonstrate that a large part of the observed errors arise due to the inference pipeline, and that optimizing it can improve the "frozen" VLM without the need to retrain it.

We investigate whether limbic-like signatures of rapid, salience-driven behavior can be identified in high-resolution Counter-Strike 2 telemetry. This exploratory study introduces Ego-Knowledge, a leak-reduced reconstruction of each player's plausible perceptual state, supported by a millisecond-precision visibility engine and a reaction-centered extraction pipeline. Using a neuroscience-motivated 60--120 ms window, we derive coarse fight-or-flight labels from visibility- and damage-triggered events, with back-damage cases enabling constrained reaction-time analysis and manual label checks. We train two telemetry-native models using only information available by the trigger: EMBER (gradient boosting) and ORBIT (a custom transformer). On the full validation set, EMBER achieves 73.5% accuracy and ORBIT 71.2%, versus a 51.5% majority-class baseline, and both generalize to held-out players. The strongest LLM baseline achieves 62.7% on 1,000 validation cases; on these same cases, EMBER (73.6%) and ORBIT (70.9%) perform better (McNemar p=1.3e-9 and 1.5e-6, respectively), with orders-of-magnitude lower inference time and cost, though the comparison is not compute-matched. Including a short post-trigger window changes forecasting into early response recognition, raising accuracy monotonically to 85.15%. We propose this curve as a candidate probe of the transition from rapid to deliberative control, but roughly uniform per-tick gains do not establish that interpretation. The neuroscience framing is hypothesis-generating, not mechanistic: physiological ground truth, suitable control distributions, and reverse-inference limitations remain open. We outline extensions to auditory reconstruction, larger datasets, and telemetry-native foundation models.