2026
A Review on Test-Time Scaling for Agentic Large Language Models
IJCAI 2026
A Review on Test-Time Reasoning for Agentic Large Language Models
73 accepted papers
A Review on Test-Time Reasoning for Agentic Large Language Models
In semi-decentralized federated learning, devices primarily rely on device-to-device communication but occasionally interact with a central server. Periodically, a sampled subset of devices uploads their local models to the server, which computes an aggregate model. The server can then either (i) sh
Low-bit model quantization for image super-resolution (SR) is a longstanding task that is renowned for its surprising compression and acceleration ability. However, accuracy degradation is inevitable when compressing the full-precision (FP) model to ultra-low bit widths ($2\sim4$ bits). Experimental…
Recent advancements in image motion deblurring, driven by CNNs and transformers, have made significant progress. Large-scale pre-trained diffusion models, which are rich in real-world modeling, have shown great promise for high-quality image restoration tasks such as deblurring, demonstrating strong…
The development of multimodal large language models (MLLMs) enables the evaluation of image quality through natural language descriptions. This advancement allows for more detailed assessments. However, these MLLM-based IQA methods primarily rely on general contextual descriptions, sometimes limitin…
Real-world videos often extend over thousands of frames. Existing generative video super-resolution (VSR) approaches, however, face two persistent challenges when processing long sequences: (1) inefficiency due to the heavy cost of multi-step denoising for full-length sequences; and (2) poor consist…
Electroencephalogram (EEG) signals are vital for automated seizure detection, but their inherent noise makes robust representation learning challenging. Existing graph construction methods, whether correlation-based or learning-based, often generate redundant or irrelevant edges due to the noisy nat
One-Step Diffusion Models have demonstrated promising capability and fast inference in real-world Video Super-Resolution (VSR). However, the substantial model size and high computational cost of Diffusion Transformers (DiTs) hinder their practical deployment. While low-bit quantization is a common a…
Logical consistency, the requirement that statements remain non-contradictory under logical rules, is fundamental for trustworthy reasoning, yet current LLMs often fail to maintain it even on simple inference tasks. Existing benchmarks for LLM logical consistency are not scalable, not diverse, and n…
Modeling neural population dynamics is crucial for foundational neuroscientific research and various clinical applications. Conventional latent variable methods typically model continuous brain dynamics through discretizing time with recurrent architecture, which necessarily results in compounded cu…
Diffusion models have shown superior performance in real-world video super-resolution (VSR). However, the slow processing speeds and heavy resource consumption of diffusion models hinder their practical application and deployment. Quantization offers a potential solution for compressing the VSR mode
Sparse Mixture-of-Experts (MoE) language models enable conditional computation but face deployment challenges due to the "memory wall": while few experts are activated per token, the entire model must reside in memory. Existing expert pruning methods primarily rely on independent ranking, failing to…
Diffusion-based image compression has demonstrated impressive perceptual performance. However, it suffers from two critical drawbacks: (1) excessive decoding latency due to multi-step sampling, and (2) poor fidelity resulting from over-reliance on generative priors. To address these issues, we propo
Retrieving targeted pathways in biological knowledge bases, particularly when incorporating wet-lab experimental data, remains a challenging task and often requires downstream analyses and specialized expertise. In this paper, we frame this challenge as a solvable graph learning and explaining task
Foundation models are reshaping EEG analysis, yet an important problem of EEG tokenization remains a challenge. This paper presents TFM-Tokenizer, a novel tokenization framework that learns a vocabulary of time-frequency motifs from *single-channel* EEG signals and encodes them into discrete tokens…
Mixture-of-Experts(MoE) Vision-Language Models(VLMs) offer remarkable performance but incur prohibitive memory and computational costs, making compression essential. Post-Training Quantization (PTQ) is an effective training-free technique to address the massive memory and computation overhead. Exist…
While super-resolution (SR) methods based on diffusion models (DM) have demonstrated inspiring performance, their deployment is impeded due to the heavy request of memory and computation. Recent researchers apply two kinds of methods to compress or fasten the DM. One is to compress the DM into 1-bit…
Diffusion models have demonstrated remarkable success in image restoration tasks. However, their multi-step denoising process introduces significant computational overhead, limiting their practical deployment. Furthermore, existing methods struggle to effectively remove severe JPEG artifact, especia…
Diffusion models have demonstrated promising performance in real-world video super-resolution (VSR). However, the dozens of sampling steps they require, make inference extremely slow. Sampling acceleration techniques, particularly single-step, provide a potential solution. Nonetheless, achieving one…
The domain of non-line-of-sight (NLOS) imaging is advancing rapidly, offering the capability to reveal occluded scenes that are not directly visible. However, contemporary NLOS systems face several significant challenges: (1) The computational and storage requirements are profound due to the inheren…
Dynamic GNNs, which integrate temporal and spatial features in Electroencephalography (EEG) data, have shown great potential in automating seizure detection. However, fully capturing the underlying dynamics necessary to represent brain states, such as seizure and non-seizure, remains a non-trivial t…
Retrieving gene functional networks from knowledge databases presents a challenge due to the mismatch between disease networks and subtype-specific variations. Current solutions, including statistical and deep learning methods, often fail to effectively integrate gene interaction knowledge from data…
Human-centered images often suffer from severe generic degradation during transmission and are prone to human motion blur (HMB), making restoration challenging. Existing research lacks sufficient focus on these issues, as both problems often coexist in practice. To address this, we design a degradat…
We investigate the Combined Target-Assignment and Path-Finding (TAPF) problem that computes both task assignments and collision-free paths for multiple agents, that is, each agent is required to select a target from an underlying set, reaching which leads to a payoff. There is a cost closely related
Human body restoration, as a specific application of image restoration, is widely applied in practice and plays a vital role across diverse fields. However, thorough research remains difficult, particularly due to the lack of benchmark datasets. In this study, we propose a high-quality dataset autom…
The Multi-Agent Combinatorial Path Finding (MCPF) problem is a generalized version of the Multi-Agent Path Finding (MAPF) problem, in which each agent must collectively visit multiple intermediate target locations on the way to its final destination. The state-of-the-art approach for addressing MCPF
Large Language Models (LLMs) have attained human-level fluency in text generation, which complicates the distinguishing between human-written and LLM generated texts. This increases the risk of misuse and highlights the need for reliable detectors. Yet, existing detectors exhibit poor robustness on…
This work explores unifying knowledge enhanced recommendation with multi-domain recommendation systems in a conversational AI assistant application. Multi-domain recommendation leverages users’ interactions in previous domains to improve recommendations in a new one. Knowledge graph enhancement seek…
Deep learning models have recently shown great success in classifying epileptic patients using EEG recordings. Unfortunately, classification-based methods lack a sound mechanism to detect the onset of seizure events. In this work, we propose a two-stage framework, SODor, that explicitly models seizu…
Pretrained latent diffusion models have shown strong potential for lossy image compression, owing to their powerful generative priors. Most existing diffusion-based methods reconstruct images by iteratively denoising from random noise, guided by compressed latent representations. While these approac…
Diffusion models have demonstrated impressive performance in face restoration. Yet, their multi-step inference process remains computationally intensive, limiting their applicability in real-world scenarios. Moreover, existing methods often struggle to generate face images that are harmonious, reali…
Identifying spatially complete planar primitives from visual data is a crucial task in computer vision. Prior methods are largely restricted to either 2D segment recovery or simplifying 3D structures, even with extensive plane annotations. We present PlanarNeRF, a novel framework capable of detectin
Image dehazing is a crucial task that involves the enhancement of degraded images to recover their sharpness and textures. While vision Transformers have exhibited impressive results in diverse dehazing tasks, their quadratic complexity and lack of dehazing priors pose significant drawbacks for real…
Wide-baseline panoramic images are frequently used in applications like VR and simulations to minimize capturing labor costs and storage needs. However, synthesizing novel views from these panoramic images in real time remains a significant challenge, especially due to panoramic imagery's high resol…
Although pre-trained large vision foundation models (VFM) yield superior results on various downstream tasks, full fine-tuning is often impractical due to its high computational cost and storage requirements. Recent advancements in parameter-efficient fine-tuning (PEFT) of VFM for image classificati…
Advanced diffusion models (DMs) perform impressively in image super-resolution (SR), but the high memory and computational costs hinder their deployment. Binarization, an ultra-compression algorithm, offers the potential for effectively accelerating DMs. Nonetheless, due to the model structure and t…
Bounded rational agents often make decisions by evaluating a finite selection of choices, typically derived from a reference point termed the ‘default policy,’ based on previous experience. However, the inherent rigidity of the static default policy presents significant challenges for agents when op…
Diffusion-based methods have achieved remarkable achievements in 2D image or 3D object generation, however, the generation of 3D scenes and even $360^{\circ}$ images remains constrained, due to the limited number of scene datasets, the complexity of 3D scenes themselves, and the difficulty of genera…
Training high-accuracy 3D detectors necessitates massive labeled 3D annotations with 7 degree-of-freedom, which is laborious and time-consuming. Therefore, the form of point annotations is proposed to offer significant prospects for practical applications in 3D detection, which is not only more acce…
We present NARUTO a neural active reconstruction system that combines a hybrid neural representation with uncertainty learning enabling high-fidelity surface reconstruction. Our approach leverages a multi-resolution hash-grid as the mapping backbone chosen for its exceptional convergence speed and c…
While the recommendation system (RS) has advanced significantly through deep learning, current RS approaches usually train and fine-tune models on task-specific datasets, limiting their generalizability to new recommendation tasks and their ability to leverage external knowledge due to model scale a…
Transformer architectures have exhibited remarkable performance in image super-resolution (SR). Since the quadratic computational complexity of the self-attention (SA) in Transformer, existing methods tend to adopt SA in a local region to reduce overheads. However, the local design restricts the glo…
Prediction beyond partial observations is crucial for robots to navigate in unknown environments because it can provide extra information regarding the surroundings beyond the current sensing range or resolution. In this work, we consider the inpainting of semantic Bird’s-Eye-View maps. We propose S…
Fine-tuning has been demonstrated to be an effective method to improve the domain performance of large language models (LLMs). However, LLMs might fit the dataset bias and shortcuts for prediction, leading to poor generation performance. Previous works have proven that LLMs are prone to exhibit posi…
We propose an accurate and robust initialization approach for stereo visual-inertial SLAM systems. Unlike the current state-of-the-art method, which heavily relies on the accuracy of a pure visual SLAM system to estimate inertial variables without updating camera poses, potentially compromising accu…
Autonomous navigation in unknown environments is challenging and requires the consideration of both geometric and semantic information to assess the navigability of the environment. In this work, we propose a novel space modeling framework, Visual-Geometry Sparse Gaussian Process (VG-SGP), that simu…
Transformer has recently gained considerable popularity in low-level vision tasks, including image super-resolution (SR). These networks utilize self-attention along different dimensions, spatial or channel, and achieve impressive performance. This inspires us to combine the two dimensions in Transf…
Many policy optimization approaches in reinforcement learning incorporate a Kullback-Leilbler (KL) divergence to the previous policy, to prevent the policy from changing too quickly. This idea was initially proposed in a seminal paper on Conservative Policy Iteration, with approximations given by al…
Deep metric learning is crucial for finding an embedding function that can generalize to training and testing data, including unknown test classes. However, limited training samples restrict the model's generalization to downstream tasks. While adding new training samples is a promising solution, de…
Diffusion models (DMs) have recently been introduced in image deblurring and exhibited promising performance, particularly in terms of details reconstruction. However, the diffusion model requires a large number of inference iterations to recover the clean image from pure Gaussian noise, which consu…
Mixup-based data augmentation has been validated to be a critical stage in the self-training framework for unsupervised domain adaptive semantic segmentation (UDASS), which aims to transfer knowledge from a well-annotated (source) domain to an unlabeled (target) domain. Existing self-training method…
Query Rewriting (QR) plays a critical role in large-scale dialogue systems for reducing frictions. When there is an entity error, it imposes extra challenges for a dialogue system to produce satisfactory responses. In this work, we propose KG-ECO: Knowledge Graph enhanced Entity COrrection for query…
As a new paradigm in information retrieval, generative retrieval directly generates a ranked list of document identifiers (docids) for a given query using generative language models (LMs). How to assign each document a unique docid (denoted as document tokenization) is a critical problem, because it…
Achieving an immersive experience enabling users to explore virtual environments with six degrees of freedom (6DoF) is essential for various applications such as virtual reality (VR). Wide-baseline panoramas are commonly used in these applications to reduce network bandwidth and storage requirements…
Detecting navigable space is a fundamental capability for mobile robots navigating in unknown or unmapped environments. In this work, we treat visual navigable space segmentation as a scene decomposition problem and propose <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www
Traversability prediction is a fundamental perception capability for autonomous navigation. The diversity of data in different domains imposes significant gaps to the prediction performance of the perception model. In this work, we make efforts to reduce the gaps by proposing a novel coarse-to-fine…
Recently, Transformer architecture has been introduced into image restoration to replace convolution neural network (CNN) with surprising results. Considering the high computational complexity of Transformer with global attention, some methods use the local square window to limit the scope of self-a…
Underwater robots often need to communicate with external localization sensors. The low bandwidth in such communications is one of the bottlenecks in achieving accurate tracking control. Toward this end, we adopt a novel periodic event-triggered control (PETC) which allows a robotic fish to reduce i
An end-to-end platform assembling multiple tiers is built for precisely cognizing brain activities. Being fed massive electroencephalogram (EEG) data, the time-frequency spectrograms are conventionally projected into the episode-wise feature matrices (seen as tier-1). A spiking neural network (SNN)…
Seq2seq language generation models that are trained offline with multiple domains in a sequential fashion often suffer from catastrophic forgetting. Lifelong learning has been proposed to handle this problem. However, existing work such as experience replay or elastic weighted consolidation requires…
Nowadays, higher requirements are placed on the design of the controller when robots enter the factory and co-operate with human. In this letter, we propose a unified task space control method combined with the contact reaction strategy in null space of redundant manipulator, which can not only conv
Recent offshore drilling activities have dramatically bloomed oil and gas production. Due to extreme weather, such as hurricanes and tsunamis, offshore oil platforms may need to be constantly monitored in case of unexpected dangers. Using robots to monitor and prevent these dangerous situations is a…
Autonomous underwater vehicles (AUVs) outfitted with manipulators are useful for performing various tasks. As the AUVs manipulate tools, they deviate from neutral buoyancy, and must constantly actuate to maintain depth and orientation. This results in large energy consumption. Furthermore, AUVs cont
In this letter, a collision avoidance control strategy is developed for a robotic fish that is propelled by a two-joint fishtail, comprising a servo motor and an ionic polymer-metal composite (IPMC), which are used as solid and soft actuators, respectively. In this dual-actuator system, the forward
In many autonomous mapping tasks, the maps cannot be accurately constructed due to various reasons such as sparse, noisy, and partial sensor measurements. We propose a novel map prediction method built upon recent success of Low-Rank Matrix Completion. The proposed map prediction is able to achieve…
Robot navigation with noisy perception is a fundamental but challenging task. We present a framework for creating navigable space from cluttered point clouds generated by low-end sensors with high sparsity and noise. Our method incrementally seeds and creates local convex regions free of obstacle po
Traditional methods for RGB hand mesh recovery usually need to train a separate model for each dataset with the corresponding ground truth and are hardly adapted to new scenarios without the ground truth for supervision. To address the problem, we propose a self-supervised framework for hand mesh es…
The release of BERT revolutionized the development of NLP. Various BERT-based reading comprehension models have been proposed, thus updating the performance ranking of reading comprehension tasks. However, the above BERT-based models inherently employ BERT’s combined input method, representing the i…
Three-dimensionally (3D) maneuverable robotic fish are highly desirable due to their ability to explore and survey the underwater environment. Existing depth control mechanisms are typically focused on using either compressed air or a piston to generate changes in volume. However, this often makes t
Query rewriting (QR) is an increasingly important technique to reduce customer friction caused by errors in a spoken language understanding pipeline, where the errors originate from various sources such as speech recognition errors, language understanding errors or entity resolution errors. In this…
Interaction is fundamental in autonomous driving (AD). Despite more than a decade of intensive R&D in AD, how to dynamically interact with diverse road users in various contexts still remains unsolved. Multi-agent learning has recently seen big breakthroughs and has much to offer towards solving rea
Three-dimensionally (3D) maneuverable robotic fish are highly desirable due to their abilities to explore and survey the underwater environment. Existing depth control mechanism is focused on using compressed air or piston to generate volume change, which makes the system bulky and impractical in a…
This paper presents modeling of robotic fish propelled by a hybrid tail with Servo and IPMC actuated two joints. The first joint is driven by a servo motor, which generates flapping motion for main propulsion. The second joint is actuated by a soft actuator, or ionic polymer-metal composite (IPMC) a…