83 accepted papers
LLM-based agents already operate in production across many industries, yet we lack a clear understanding of which technical methods make these deployments successful. We present the first systematic study of Characterizing Agents in Production (CAP) using first-hand data from agent developers. We co…
As Computer-Use Agents (CUAs) proliferate and grow increasingly capable, evaluation has become more challenging: static, manually curated benchmarks are narrow in domain, contamination-prone, and environment-heavy, and they diverge substantially from user-driven, real-world evaluation. We present Co…
Large language model (LLM) serving demands low latency and high throughput, but high load variability leads to significant GPU utilization. In this paper, we identify a synergetic but overlooked opportunity to co-serve latency-critical online requests alongside *latency-tolerant offline* tasks, whic…
Video diffusion models have achieved remarkable generative performance, but their substantial computational and memory costs pose significant challenges for deployment, especially on consumer GPUs. As recent advances in attention optimization mitigate previous computational bottlenecks, linear layer
Instructed code editing, where LLMs directly modify a developer's existing code based on a user instruction, is becoming a widely used interaction mode in AI coding assistants. However, few benchmarks directly evaluate this capability and current datasets often rely on artificial sources. We introdu…
We introduce FrontierCS, a benchmark of 240 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs and top-tier competitive programming participants and problem setters. Unlike existing benchmarks that focus on tasks with known optimal solut…
Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language often provides a much ric…
Despite rapid progress in auto-regressive video diffusion, we identify an emerging system–algorithm bottleneck that limits both deployability and generation quality: KV-cache memory. In auto-regressive video generation models, the KV-cache grows with generation history and quickly dominates GPU memo…
In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. Interestingly, we find that attention weights can be decoupled into two matrices: a small fraction of large weights with hig…
Mixture of Experts (MoE) models have emerged as the de-facto architecture for scaling up language models without significantly increasing the computational cost. Existing MoE methods optimize system efficiency or model architecture independently. We show that as MoE models get more granular and spar…
Playing video games requires perception, reasoning, memory, and long-horizon planning—exactly the faculties expected of modern large language and vision–language models (LLMs/VLMs). We introduce LMGame-Bench, a benchmark built on six popular games spanning platformer, puzzle, and narrative games thr…
State-of-the-art sparse attention methods for reducing decoding latency fall into two main categories: approximate top-$k$ (and its extension, top-$p$) and recently introduced sampling-based estimation. However, these approaches are fundamentally limited in their ability to approximate full attentio…
Large language models (LLMs) have transformed natural language processing, with frameworks like Chatbot Arena providing pioneering platforms for evaluating these models. By facilitating millions of pairwise comparisons based on human judgments, Chatbot Arena has become a cornerstone in LLM evaluatio…
Evaluating in-the-wild coding capabilities of large language models (LLMs) is a challenging endeavor with no existing solution. We introduce Copilot Arena, a platform to collect user preferences through native integration into a developer's working environment. Copilot Arena comprises a novel interf…
Test-time reasoning algorithms such as chain-of-thought, self-consistency, and MCTS enhance LLM problem-solving but can wastefully generate many tokens without improving accuracy. At the same time, we observe that these algorithms exhibit answer stabilization: their intermediate solutions often ceas…
Benchmarks are essential for quantitatively tracking progress in AI. As AI agents become increasingly capable, researchers and practitioners have introduced agentic benchmarks to evaluate agents on complex, real-world tasks. These benchmarks typically measure agent capabilities by evaluating task ou…
It is now common to evaluate Large Language Models (LLMs) by having humans manually vote to evaluate model outputs, in contrast to typical benchmarks that evaluate knowledge or skill at some particular task. Chatbot Arena, the most popular benchmark of this type, ranks models by asking users to sele…
Diffusion Transformers (DiTs) with 3D full attention power state-of-the-art video generation, but suffer from prohibitive compute cost -- when generating just a 5-second 720P video, attention alone takes 800 out of 950 seconds of total inference time. This paper introduces sliding tile attention (ST…
Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions. We turn this observation into VSA, a trainable, hardware-efficient sparse attention that replaces full attention at both traini…
The rapid evolution of Large Language Models (LLMs) has outpaced the development of model evaluation, highlighting the need for continuous curation of new, challenging benchmarks. However, manual curation of high-quality, human-aligned benchmarks is expensive and time-consuming. To address this, we…
Developing high-performance software is a complex task that requires specialized expertise. We introduce GSO, a benchmark for evaluating language models' capabilities in developing high-performance software. We develop an automated pipeline that generates and executes performance tests to analyze r…
Evaluating the reasoning abilities of large language models (LLMs) is challenging. Existing benchmarks often depend on static datasets, which are vulnerable to data contamination and may get saturated over time, or on binary live human feedback that conflates reasoning with other abilities. As the m…
Leveraging long contexts is crucial for advanced AI systems, but attention computation poses a scalability challenge. While scaled dot-product attention (SDPA) exhibits token sparsity, i.e. only a few pivotal tokens significantly contribute to output, exploiting this sparsity remains challenging. Ex…
We introduce a new benchmark for reward models that quantifies their ability to produce strong language models through RLHF (Reinforcement Learning from Human Feedback). The gold-standard approach is to run a full RLHF training pipeline and directly probe downstream LLM performance. However, this pr…
LLM-based judges have emerged as a scalable alternative to human evaluation and are increasingly used to assess, compare, and improve models. However, the reliability of LLM-based judges themselves is rarely scrutinized. As LLMs become more advanced, their responses grow more sophisticated, requirin…
Large reasoning models (LRMs) tackle complex problems by following long chain-of-thoughts (Long CoT) that incorporate reflection, backtracking, and self-validation. However, the training techniques and data requirements to elicit Long CoT remain poorly understood. In this work, we find that language
Large Language Models (LLMs) applied to code-related applications have emerged as a prominent field, attracting significant interest from academia and industry. However, as new and improved LLMs are developed, existing evaluation benchmarks (e.g., HumanEvla, MBPP) are no longer sufficient for assess…
Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs. While significant research focuses on mitigating harmful content generation, the enhanced safety often come with the side effect of over-refusal, where LLMs may reject innocuous prompts and become less helpf…
Large language model (LLM) evaluations typically rely on aggregated metrics like accuracy or human preference, averaging across users and prompts. This averaging obscures user- and prompt-specific variations in model performance. To address this, we propose Prompt-to-Leaderboard (P2L), a method that…
Recent advances in diffusion models have enabled high-quality video generation, but the additional temporal dimension significantly increases computational costs, making training and inference on long videos prohibitively expensive. In this paper, we identify a phenomenon we term Spatiotemporal Ener…
Vision-Language-Action (VLA) models, pre-trained on large-scale imitation learning datasets, have demonstrated remarkable capabilities in visuomotor control. However, these models exhibit diverse failure modes in unstructured real-world environments, limiting the widespread adoption of VLAs in robot…
Large language models (LLMs) excel at a wide range of tasks, but choosing the right model often involves balancing performance and cost. Powerful models offer better results but are expensive, while smaller models are more cost-effective but less capable. To address this trade-off, we introduce a tr…
Increasing test-time compute for LLMs shows promise across domains but remains underexplored in code generation, despite extensive study in math. In this paper, we propose S*, the first hybrid test-time scaling framework that substantially improves the coverage and selection accuracy of generated co
Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability, usually requiring tens of minutes to generate a few seconds of video even on high-performance GPUs. This inefficiency primarily arises from the quadratic computational…
Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention. By computing only critical tokens, sparse attention reduces computational costs and offers a promising acceleration approach. However, we identify that…
Function calling, also called tool use, refers to an LLM's ability to invoke external functions, APIs, or user-defined tools in response to user queries—an essential capability for agentic LLM applications. Despite its prominence, there did not exist a standard benchmark to evaluate function calling…
Leveraging attention sparsity to accelerate long-context large language models (LLMs) has been of great importance recently. However, most existing sparse attention algorithms use a fixed budget of how many tokens to use in their computations. This simple static decision raises critical issues in re…
The growing adoption and capabilities of vision-language models (VLMs) demand benchmarks that reflect real-world user interactions. We introduce VisionArena, the largest existing dataset of crowdsourced real-world conversations between users and VLMs. While most visual question-answering datasets fo…
Despite enthusiasm for Multi-Agent LLM Systems (MAS), their performance gains on popular benchmarks are often minimal. This gap highlights a critical need for a principled understanding of why MAS fail. Addressing this question requires systematic identification and analysis of failure patterns. We…
Video generation models have rapidly progressed, positioning themselves as video world models capable of supporting decision-making applications like robotics and autonomous driving. However, current benchmarks fail to rigorously evaluate these claims, focusing only on general video quality, ignorin…
Many recent state-of-the-art results in language tasks were achieved using compound systems that perform multiple Language Model (LM) calls and aggregate their responses. However, there is little understanding of how the number of LM calls -- e.g., when asking the LM to answer each question multiple…
Autoregressive decoding of large language models (LLMs) is memory bandwidth bounded, resulting in high latency and significant wastes of the parallel processing power of modern accelerators. Existing methods for accelerating LLM decoding often require a draft model (e.g., speculative decoding), whic…
Large Language Models (LLMs) have unlocked new capabilities and applications; however, evaluating the alignment with human preferences still poses significant challenges. To address this issue, we introduce Chatbot Arena, an open platform for evaluating LLMs based on human preferences. Our methodolo…
Large language models (LLMs) have rapidly improved text embeddings for a growing array of natural-language processing tasks. However, their opaqueness and proliferation into scientific domains such as neuroscience have created a growing need for interpretability. Here, we ask whether we can obtain i…
In Large Language Model (LLM) inference, the output length of an LLM request is typically regarded as not known a priori. Consequently, most LLM serving systems employ a simple First-come-first-serve (FCFS) scheduling strategy, leading to Head-Of-Line (HOL) blocking and reduced throughput and servic…
Cloud robotics enables robots to offload complex computational tasks to cloud servers for performance and ease of management. However, cloud compute can be costly, cloud services can suffer occasional downtime, and connectivity between the robot and cloud can be prone to variations in network Qualit…
Natural language to code generation is an important application area of LLMs and has received wide attention from the community. The majority of relevant studies have exclusively concentrated on increasing the quantity and functional correctness of training sets while disregarding other stylistic e…
Studying how people interact with large language models (LLMs) in real-world scenarios is increasingly important due to their widespread use in various applications. In this paper, we introduce LMSYS-Chat-1M, a large-scale dataset containing one million real-world conversations with 25 state-of-the-…
Large language models (LLMs) have demonstrated remarkable performance, and organizations are racing to serve LLMs of varying sizes as endpoints for use-cases like chat, programming and search. However, efficiently serving multiple LLMs poses significant challenges for existing approaches due to vary…
Speculative decoding is a pivotal technique to accelerate the inference of large language models (LLMs) by employing a smaller draft model to predict the target model's outputs. However, its efficacy can be limited due to the low predictive accuracy of the draft model, particularly when faced with d…
While Large Language Models’ (LLMs) coding capabilities have advanced rapidly, corresponding evaluation benchmarks on real-world programming setups are yet to catch up. Building a scalable and interactive testbed for evaluating general-purpose AI coding agents for real-world code has been challengin…
Large language models (LLMs) are increasingly used for complex tasks that require multiple generation calls, advanced prompting techniques, control flow, and structured inputs/outputs. However, efficient systems are lacking for programming and executing these applications. We introduce SGLang, a sys…
Beyond scaling base models with more data or parameters, fine-tuned adapters provide an alternative way to generate high fidelity, custom images at reduced costs. As such, adapters have been widely adopted by open-source communities, accumulating a database of over 100K adapters—most of which are hi…
There is an increasing conflict between business incentives to hide models and data as trade secrets, and the societal need for algorithmic transparency. For example, a rightsholder who currently wishes to know whether their copyrighted works have been used during training must convince the model pr…
Reinforcement Learning (RL) algorithms are often known for sample inefficiency and difficult generalization. Recently, Unsupervised Environment Design (UED) emerged as a new paradigm for zero-shot generalization by simultaneously learning a task distribution and agent policies on the generated tasks…
The high computational and memory requirements of large language model (LLM) inference make it feasible only with multiple high-end accelerators. Motivated by the emerging demand for latency-insensitive tasks with batched processing, this paper initiates the study of high-throughput LLM inference us…
Mobility, power, and price points often dictate that robots do not have sufficient computing power on board to run contemporary robot algorithms at desired rates. Cloud computing providers such as AWS, GCP, and Azure offer immense computing power and increasingly low latency on demand, but tapping i…
Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences. To address this, we explore using strong LLMs as judges to evaluate these models on more open-ended questions. We exami…
The safety of autonomous vehicles (AVs) depends on their ability to perform complex computations on high-volume sensor data in a timely manner. Their ability to run these computations with state-of-the-art models is limited by the processing power and slow update cycles of their onboard hardware. In…
"Efficient vision works maximize accuracy under a latency budget. These works evaluate accuracy offline, one image at a time. However, real-time vision applications like autonomous driving operate in streaming settings, where ground truth changes between inference start and finish. This results in a…
The sharing of scarce resources among multiple rational agents is one of the classical problems in economics. In exchange economies, which are used to model such situations, agents begin with an initial endowment of resources and exchange them in a way that is mutually beneficial until they reach a…
Fine-tuning models on edge devices like mobile phones would enable privacy-preserving personalization over sensitive data. However, edge training has historically been limited to relatively small models with simple architectures because training is both memory and energy intensive. We present POET,…
The capability of a reinforcement learning (RL) agent heavily depends on the diversity of the learning scenarios generated by the environment. Generation of diverse realistic scenarios is challenging for real-time strategy (RTS) environments. The RTS environments are characterized by intelligent ent…
First-order methods for quadratic optimization such as OSQP are widely used for large-scale machine learning and embedded optimal control, where many related problems must be rapidly solved. These methods face two persistent challenges: manual hyperparameter tuning and convergence time to high-accur…
The increasing size of neural network models has been critical for improvements in their accuracy, but device memory is not growing at the same rate. This creates fundamental challenges for training neural networks within limited memory environments. In this work, we propose ActNN, a memory-efficien…
Recent work learns contextual representations of source code by reconstructing tokens from their context. For downstream semantic understanding tasks like code clone detection, these representations should ideally capture program functionality. However, we show that the popular reconstruction-based…
Question answering models struggle to generalize to novel compositions of training patterns. Current end-to-end models learn a flat input embedding which can lose input syntax context. Prior approaches improve generalization by learning permutation invariant models, but these methods do not scale to…
We present Pylot, a platform for autonomous vehicle (AV) research and development, built with the goal to allow researchers to study the effects of the latency and accuracy of their models and algorithms on the end-to-end driving behavior of an AV. This is achieved through a modular structure enable…
Researchers and practitioners in the field of reinforcement learning (RL) frequently leverage parallel computation, which has led to a plethora of new algorithms and systems in the last few years. In this paper, we re-examine the challenges posed by distributed RL and try to view it through the lens…
Graph neural networks are powerful architectures for structured datasets. However, current methods struggle to represent long-range dependencies. Scaling the depth or width of GNNs is insufficient to broaden receptive fields as larger GNNs encounter optimization instabilities such as vanishing gradi…
We study exploration in stochastic multi-armed bandits when we have access to a divisible resource that can be allocated in varying amounts to arm pulls. We focus in particular on the allocation of distributed computing resources, where we may obtain results faster by allocating more resources per p…
Search-based tensor compilers can greatly accelerate the execution of machine learning models by generating high-performance tensor programs, such as matrix multiplications and convolutions. These compilers take a high-level mathematical expression as input and search for the fastest low-level imple…
Model parallelism has become a necessity for training modern large-scale deep language models. In this work, we identify a new and orthogonal dimension from existing model parallel approaches: it is possible to perform pipeline parallelism within a single training sequence for Transformer-based lang…
Consumer demand for augmented reality (AR) in mobile phone applications, such as the Apple ARKit. Such applications have potential to expand access to robot grasp planning systems such as Dex-Net. AR apps use structure from motion methods to compute a point cloud from a sequence of RGB images taken…
Existing approaches to federated learning suffer from a communication bottleneck as well as convergence issues due to sparse client participation. In this paper we introduce a novel algorithm,called FetchSGD, to overcome these challenges. FetchSGD compresses model updates using a Count Sketch, and t…
For robots using motion planning algorithms such as RRT and RRT*, the computational load can vary by orders of magnitude as the complexity of the local environment changes. To adaptively provide such computation, we propose Fog Robotics algorithms in which cloud-based serverless lambda computing pro…
The practical usage of reinforcement learning agents is often bottlenecked by the duration of training time. To accelerate training, practitioners often turn to distributed reinforcement learning architectures to parallelize and accelerate the training process. However, modern methods for scalable r…
Deep autoregressive models compute point likelihood estimates of individual data points. However, many applications (i.e., database cardinality estimation), require estimating range densities, a capability that is under-explored by current neural density estimation literature. In these applications,…
Large-scale distributed training of neural networks is often limited by network bandwidth, wherein the communication time overwhelms the local computation time. Motivated by the success of sketching methods in sub-linear/streaming algorithms, we introduce Sketched-SGD, an algorithm for carrying out…
A key challenge in leveraging data augmentation for neural network training is choosing an effective augmentation policy from a large search space of candidate operations. Properly chosen augmentation policies can lead to significant generalization improvements; however, state-of-the-art approaches…
Neural programs are highly accurate and structured policies that perform algorithmic tasks by controlling the behavior of a computation mechanism. Despite the potential to increase the interpretability and the compositionality of the behavior of artificial agents, it remains difficult to learn from…
Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular computation patterns, each of which typically exhibits opportunities for distributed computation. We argue for distributing RL components in a composable way by adapting algorithms for top-down hierarchical control,…
An option is a short-term skill consisting of a control policy for a specified region of the state space, and a termination condition recognizing leaving that region. In prior work, we proposed an algorithm called Deep Discovery of Options (DDO) to discover options to accelerate reinforcement learni