每天知道
你的领域
出了什么

Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore alternatives, and decide when to stop. This test-time strategy makes it difficult to measure how agent performance scales. We study open-ended tasks that provide continuous scores for intermediate submissions, making progress observable throughout long trajectories. We propose Elo-per-token analysis, which tracks the best solution found at each token budget and uses a Bradley-Terry model to aggregate within-task orderings into Elo ratings across tasks with different score scales. We apply it to four general-purpose agents on four open-ended benchmarks, with sessions of up to 100M tokens, and to three feedback-driven LLM optimization harnesses in controlled single-task interventions. Independent sampling provides a theoretically characterized reference, for which Elo grows linearly with log compute. Against this reference, agents can initially convert tokens into Elo faster than independent sampling, but their marginal gains diminish and eventually fall below the reference. In contrast, the strongest historical human contestants improve superlinearly over contest time on shared AtCoder Heuristic Contest tasks, providing evidence of continual learning and substantial headroom after agents slow down. We define the scaling inflection point as the per-session budget where marginal Elo gains match the independent-sampling reference. Using this point as the per-session budget, we split 100M tokens across parallel sessions on FrontierCS Polyomino Packing, gaining +264 Elo over one long session and +355 over ten short sessions.

AI co-scientists could accelerate computational research, but over a long-running study the workflow also has to stay inspectable, resumable and reproducible, which requires persistent computational state and provenance. Here we present OpenAI4S, an open-source scientific research agent built around the principle of Code as Action, Science as Sessions. OpenAI4S combines a persistent computing runtime with research-session management: orchestration is handled through structured tool calls, while scientific actions are represented as complete code cells executed in persistent Python and R kernels. An append-only Action Ledger, per-cell execution records, versioned artifacts, environment records, and workspace checkpoints preserve how results were produced and support session recovery, branching, and extension. Configurable sandboxing, permission controls, and code and trajectory screening provide complementary safeguards. We evaluate OpenAI4S on 36 research scenarios spanning retrosynthesis, molecular dynamics, protein binder design, protein mutation, catalyst screening, and mineral spectroscopy, measuring scientific task accuracy, workflow completeness, and reproducibility of the resulting repositories. OpenAI4S achieves an overall score of 7.83, compared with 5.7--6.4 for a general-purpose coding harness evaluated with three frontier models, with the largest gains on long-horizon and computation-intensive workflows. These results suggest that integrating persistent execution with session-level provenance can improve the reliability of AI-assisted scientific workflows. Environment specification and full rerunnability remain weak for every evaluated system, ours included, so reproducibility is still an open problem for scientific agents. The system is available under the MIT license at \href{https://github.com/PKU-YuanGroup/OpenAI4S}{github.com/PKU-YuanGroup/OpenAI4S}.

AI agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative execution, concurrency, and partial failures, the resulting external state may be inconsistent with the workflow's intended resolution: required effects may be missing or duplicated, aborted effects may survive, and committed effects may depend on provisional state that is later withdrawn. Advanced transaction models address related failures, but assume that lower-level operations expose the semantics they depend on: whether an effect occurred, whether it can be compensated, staged, or safely reordered. Shared agent-tool interfaces usually do not. We contribute an effect-history model that separates events in the external world from the runtime's observations of them, and a catalog of eight recurring external-effect anomalies. From the catalog we derive the boundary capabilities required to exclude each anomaly in general, and four points where black-box tool invocation alone cannot provide a general guarantee. We then ask how much of this is expressible in a widely used shared tool interface, measuring the use of the standard annotation vocabulary across 98,291 tools exposed by registered Model Context Protocol (MCP) servers. The fields are widely emitted but provide only coarse call-level hints, and none of the required capabilities is fully expressible. These results motivate reusable transactional contracts at the tool boundary.

Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases. However, data agents face a challenging agent-data gap: heterogeneous data resides outside the agent, while the agent can access it (e.g., column names and file paths) only through generic tools. Existing approaches either let agents directly explore raw data sources or inject manually constructed semantic layers into prompts. However, neither scales well to large heterogeneous data sources nor adapts to different agent behaviors. In this paper, we introduce EvoOntology, a self-evolving ontology layer for data agents. EvoOntology encapsulates the ontology as an MCP server comprising a schema layer, a content layer, and a tool layer, enabling agents to actively query and interact with the ontology at runtime. To this end, we introduce a builder agent for autonomous ontology construction and a self-evolution loop that continuously refines the ontology through attribution-guided typed edits that are accepted only after a backbone-conditional paired evaluation. Experiments on three well-adopted data-agent benchmarks with four LLM backbones demonstrate that EvoOntology consistently outperforms strong baselines and existing semantic-layer approaches, effectively bridging the agent-data gap and enabling more effective interaction with heterogeneous data. Code: https://github.com/ruc-datalab/EvoOntology

Long-horizon LLM agents accumulate memory across sessions, creating sparse but high-impact risks: stale facts, conflicting updates, cross-user leakage, revoked-memory reuse, and constraint decay. Standard aggregate scores hide per-risk failure rates--a model achieving 78% average accuracy may still leak data in 4% of episodes--and benchmark compression preferentially discards the rare high-severity events that distinguish a mostly-working model from one that occasionally causes harm. We present MemRiskBench. The primary contribution is a five-category risk taxonomy (plus one documented, unscored category) operationalized by deterministic trace grounded checks, instantiated as a 120-episode scripted benchmark with full trace logging and no LLM-as-judge on the pass/fail path, evaluated on five locally run quantized instruction-tuned models. Second, a risk-preserving subset selector: a coverage-constrained greedy selector on deterministic trace-derived features that retains full ranking (Spearman rho = 0.975, deterministic; CI collapses to a point estimate with zero bootstrap variance), risk coverage (1.0), and high-risk model detection (1.0) at a 20% subset size, reducing compute 5x. Unlike ranking-only subset selectors, this selector additionally preserves risk-type coverage and high-risk detection using trace-grounded deterministic features that do not require an LLM judge. All episodes, traces, the scoring implementation, and the selector are released to support reproducible evaluation and risk assessment of deployed LLM agents

Digital agents must often adapt to new environments whose interfaces, tools, and failure modes are not fully captured by pretrained models. We introduce RSIAgent, a training-free multi-agent framework for recursive self-improvement through autonomous memory construction. RSIAgent coordinates curriculum, actor, and verifier agents to continually explore the environment, validate outcomes, and retain environment-specific knowledge, including reusable causal relationships between actions, conditions, and consequences. It further adopts a broad-then-deep exploration strategy, combining parallel broad recursive self-exploration for discovering diverse environment structures with focused deep self-exploration for uncovering hard cases, hidden constraints, boundary conditions, and previously unknown causal dependencies. The resulting memory is frozen and can be directly reused for downstream tasks without updating model parameters. Experiments on OSWorld-v2 and Agent's Last Exam show that RSIAgent substantially improves strong open-source models, enabling Kimi-K3 and GLM-5.3 to outperform frontier closed-source models including GPT-6.

Software agents with Large Language Models (LLMs) are designed for Automated Program Repair (APR) tasks, raising the possibility that, in the near future, APR agents will fix bugs automatically without much human intervention. Can we trust an APR agent to produce both functionally correct and secure code in such situations? What if attackers target production APR agents with adversarial issues that seem benign but may influence the agents to produce correct but insecure code? In this paper, we took a first step towards answering these questions by conducting an empirical study. First, we created SWEADV, a benchmark of 750 adversarial issue descriptions constructed from 150 repair tasks in SWE-bench Verified. For each repair task, we created five adversarial issue descriptions, one for each attack type: command execution, deserialization, path traversal, denial of service, and weak hashing. Second, we evaluated mini_swe APR agents from three LLM backends on SWEADV: GPT-5-Mini, MiniMax-M2.5, and DeepSeek-R. We found that on average, adversarial issue descriptions can induce malicious behaviors with successful repair in 51.7% of cases. Third, we investigated whether typical detection mechanisms are sufficient to prevent such malicious patches from being accepted. Pre-repair detection with LLM-as-judge on the adversarial issue descriptions resulted in an average detection accuracy of only 62.3%. Post-repair detection on adversarial APR patches using static analysis tools and LLM-as-judge achieved average detection accuracies of only 39.4% and 55.4%, respectively. We conclude that autonomous APR agents cannot be trusted yet in production deployment, given their susceptibility to adversarial attacks.

Large language models have advanced automated algorithm discovery by synthesizing executable code, but existing frameworks trap them in rigid search pipelines with pre-defined control flows. This limitation restricts adaptive reasoning, blocks cross-paradigm transfer, and discards valuable execution feedback. We propose AlgoEvo, a unified agentic framework that transforms automated algorithm discovery into an interactive, knowledge-accumulating process. An autonomous agent dynamically inspects, diagnoses, and edits code based on runtime feedback. A design skill hub decouples paradigm-specific knowledge from the core discovery engine, allowing a single workflow to seamlessly handle single-objective, multi-objective, and multi-component design. Meanwhile, a hierarchical experience mechanism organizes search trajectories into a task-level tree to guide exploration and consolidates cross-task patterns into reusable skills. Across six representative benchmark tasks, AlgoEvo matches or surpasses specialized methods with substantially fewer evaluations and reduced token consumption, demonstrating strong intra-task accumulation, cross-task transfer, and the ability to reproduce or exceed existing state-of-the-art performance through flexible skill activation.

Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve execution mechanisms from experience. However, generalizable harness RSI remains challenging. First, evolving harnesses on evaluation benchmarks or their subsets makes it difficult to distinguish reusable improvements from benchmark-specific adaptation. Second, single-trajectory updates can conflate systematic harness deficiencies with instance-specific reasoning and solution details, producing modifications that transfer poorly to unseen tasks. Third, localizing recurring behavioral deficiencies within monolithic harnesses is difficult, while whole-harness optimization can entangle unrelated mechanisms and complicate attribution and validation. We propose ModularRSI, a benchmark-disjoint, contrastive, and modular framework for generalizable harness evolution. ModularRSI contrasts successful and failed trajectories for the same task and aggregates evidence across tasks to identify recurring behavioral deficiencies. It decomposes the evolvable harness into five functional modules: Agent Loop, Tool Use, Observation Management, Context Management, and Task Completion Detection. Each module evolves independently within a restricted modification scope, followed by an integration stage that combines the evolved modules into a unified harness and resolves potential conflicts. To support benchmark-disjoint evolution, we curate 2,000 executable evolution tasks from external sources that are disjoint from downstream evaluation benchmarks. Experiments on TB2.0 and SWE-Bench Verified show consistent improvements on unseen in-domain and cross-domain tasks, with the evolved harness also transferring across different foundation models.

Embodied navigation requires agents to ground instructions or object goals in spatial observations and translate plans into successful execution. As multimodal large language models (MLLMs) become increasingly capable, they offer stronger support for navigation without task-specific training; however, improved semantic reasoning alone does not ensure that proposed actions remain consistent with spatial evidence, task progress, and execution outcomes. We introduce HarnessVLN, a zero-shot, training-free framework that unifies instruction-following and object-goal navigation through a shared Agent Harness. The Harness coordinates perception, memory, and execution tools through a unified interface, validating planner proposals for evidential support, geometric feasibility, and subgoal consistency before dispatch. It jointly manages hierarchical event memory and a persistent Spatiotemporal Graph to track task progress, preserve spatial evidence, and contextualize failures. Structured execution feedback updates this shared state, guiding subsequent planning, recovery, and termination. Across R2R, RxR, HM3D-v2, and HM3D-OVON, HarnessVLN achieves success rates of 60.8%, 53.9%, 76.0%, and 59.3%, respectively, outperforming prior training-free state-of-the-art methods. Humanoid robot deployment further demonstrates its applicability to both navigation tasks in real-world environments. The project page is available at https://agibot-harnessvln.netlify.app/.

While In-Context Learning (ICL) enables models to adapt from exemplars without parameter updates, multimodal ICL remains largely underexplored, particularly regarding video demonstrations in interactive environments. For multimodal agents, learning from videos presents unique challenges: they must translate in-context demonstrations into executable policies, ground these policies in novel visual states, and iteratively refine actions based on environmental feedback. We introduce V-ICAL, a novel benchmark designed to evaluate video-based ICL for multimodal agents. Comprising 342 interactive tasks across 37 environments, V-ICAL utilizes human-curated demonstration videos as task-specific behavioral exemplars, evaluating agents through sustained interaction from a target initialization. The benchmark seamlessly connects in-context knowledge induction with core agentic capabilities, including state grounding, temporal memory, planning, and adaptation in dynamic environments. Extensive evaluations across 19 state-of-the-art multimodal agents reveal significant limitations: the best-performing model, Seed-2.1-Pro, achieves a score of only 54.4/100, while other leading models (e.g., Gemini-3.1-Pro, GPT-5.6) fail to surpass 50, far below the human baseline of 83.6. Controlled comparisons further demonstrate that current agents struggle to reliably translate video exemplars into effective policies, failing to yield consistent performance gains. Ultimately, V-ICAL exposes a critical gap in the ICL capabilities of multimodal agents, underscoring an urgent need for future research.

Effective communication is a cornerstone of distributed intelligence in Multi-Agent Reinforcement Learning (MARL), yet ensuring that generated messages are both informative and robust to physical constraints remains a significant challenge. This paper introduces Multi-Agent Regularized Communication (MARC), a novel framework inspired by information-theoretic principles of conditional mutual information. MARC employs an attention-based architecture coupled with a unique message regularization mechanism designed to minimize uncertainty regarding future system states, thereby inducing the learning of highly representative communication protocols. Crucially, we evaluate MARC under stringent communication bottlenecks and lossy channels, simulating the real-world constraints of autonomous robotic networks and decentralized systems. Our results demonstrate that MARC significantly outperforms state-of-the-art methods in complex cooperative domains. Furthermore, we provide a deep analysis of message characteristics, proving that MARC maintains high operational performance even under significant data compression, offering a scalable path for deploying intelligent agents in resource-constrained environments.

Designing effective memory mechanisms is crucial for advancing LLM-driven Multi-Agent Systems (MAS), helping agents learn together and perform better over time. While recent work has led to strong cooperation skills, most methods still use flat, unstructured memories, which easily get filled with noise and erase differences between agents. To address this, we introduce the concept of collective-individual memory synergy and propose CoMem, an architecture that unifies both private experience and shared knowledge for multi-agent learning. CoMem features:(i) Private Experience Sedimentation, which lets each agent keep and update its own useful memories over time;(ii) Collective Wisdom Curation, which carefully selects only widely proven ideas to be shared among agents;(iii)Parallel Dual-Stream Retrieval, which allows agents to draw both from their own memory and the group's wisdom, using clustering to ensure diversity.Experiments on ALFWorld and PDDL benchmarks show that CoMem achieves strong overall performance and robustly avoids memory pollution.

Scientific agents contribute to hypothesis discovery by synthesizing evidence, assessing proposals, and developing new explanations. Recent systems combine scientific agents with evolutionary search through critique, comparison, and revision. However, how different forms of agent collaboration affect hypothesis quality remains an open question. Answering this question requires separating the effects of agents' scientific capabilities from those of their collaboration. A framework must therefore preserve agents' scientific roles and support rules for combining, revising, and retaining hypotheses. Building on this view, we introduce HypoEvolve, which makes collaboration explicit through successive updates to a hypothesis population. Specifically, we propose a generational genetic algorithm to coordinate specialized large language model (LLM) agents that integrate mechanistic arguments, reconsider assumptions, and assess evidence and testability. Each generation specifies how scientific judgments and new proposals reshape the population, making collaboration effects on hypothesis quality directly testable. Moreover, we design our evaluation around scientifically meaningful hypotheses that explain how a proposed intervention could work. Drug repurposing links these explanations to target-level biological claims assessed against external evidence. Specifically, we adapt DepMap and Open Targets into complementary external measures grounded in experimental, genetic, and clinical evidence. Across 34 cancer types, HypoEvolve achieves the highest scores against six baselines on both measures. DepMap selectivity reaches 0.171, versus 0.115 for the strongest baseline. Gains over single-pass generation also generalize to held-out cancer types. HypoEvolve advances a vision of autonomous science in which AI research teams achieve a capacity for discovery beyond that of individual models.

Automatic Related Work Generation (RWG) significantly reduces the human time and effort required to author the Related Work Section (RWS) of a research paper. However, prior methods leveraging multi-agent Large Language Models (LLMs) typically rely on a predefined workflow, where each agent is responsible for a specific step in the entire process. This rigid, static inter-agent coordination limits the adaptive collaboration required to synthesize complex scientific literature. To address this limitation, we propose CREW (Collaborative Reinforcement Learning for Related Work Generation), a novel framework where LLM agents bypass heuristic pipelines to dynamically coordinate by autonomously selecting actions, such as Retrieve, Disseminate, Compose, and Critique, driven by a policy optimized via Independent Proximal Policy Optimization (IPPO). Extensive experiments on a standard RWG benchmark demonstrate that our approach yields substantial quality improvements over strong existing baselines, while significantly reducing token costs. Code is available at https://github.com/YenPBao/CREW-Collaborative-MARL.git

Multi-Agent (MA) systems are effective at solving complex tasks that demand planning, tool use, and the synthesis of evidence from multiple sources. Existing systems typically adopt Hierarchical Manager-Worker (HMW) or Router-based Message Passing (RMP) structures as their communication protocol. However, these designs restrict agent autonomy: Worker agents cannot directly consult specific "peers", and misrouted messages can propagate errors. Inspired by bus architectures in computer systems, we propose BusMA, a communication framework that allows any agent to address other agents through a shared channel, i.e., the Bus. It consists of agent registration, message routing, and shared memory management components. Worker agents, each equipped with tools, have their own local memory and can reason, act (tool usage), and communicate by posting shared messages with specific intents. We introduce four intents: discussion, challenge, guidance, and request for explanation, which support fine-grained communication among agents. A Chair agent monitors the shared memory to coordinate interactions and facilitate convergence among Workers. To evaluate the effectiveness of BusMA, we conduct extensive experiments with two frontier LLMs across 13 tasks spanning visual reasoning, mathematical reasoning, and knowledge retrieval demonstrate that BusMA consistently outperforms state-of-the-art HMW and RMP methods.

Modern data systems compress data at rest and decompress it only when needed to preserve interconnect bandwidth. This design is often inefficient on GPU-based compute platforms because many conventional compression techniques exhibit serial data dependencies that limit GPU parallelism, leaving resources idle. Recent NVIDIA GPUs address this decoding deficiency through the Decompression Engine (DE), an on-die, fixed-function decompression accelerator for general-purpose compression formats such as Deflate, LZ4, and Snappy. Recent work has proposed string codecs that replace frequent substrings with fixed-width codes from a small, trained dictionary, making each code's lookup independent. While these lookups can run in parallel, the resulting scattered reads and short output writes still do not align well with GPU hardware, which handles contiguous memory accesses more efficiently. We present FastPair, a GPU decoder that optimizes the existing dictionary decoding process by reorganizing lookups and assembling decoded substrings for contiguous output writes. On a B300, FastPair decodes ten real-world columns 2.4 to 4.2x faster than the DE, reaching up to 1.6 TB/s.

Multilingual Large Language Models (LLMs) traditionally rely on a single vocabulary shared by all supported languages, which can lead to uneven compression across them. Moreover, their large embedding and output matrices increase memory usage and slow inference, notably for small-scale models. It is also wasteful as models are often used for only a subset of languages. To address these issues, we introduce a modular framework for multilingual model training. First, we propose methods to learn large modular BPE and Unigram tokenizers that enable extraction of subtokenizers tailored to any language subset. These subtokenizers achieve compression on par with monolingual tokenizers and improve cross-lingual fairness. Second, we design a pretraining strategy that samples subtokenizers to form batches, restricting predictions to the relevant vocabulary subset and allowing efficient training despite a large vocabulary. This supports efficient inference with any combination of language-specific vocabularies. Therefore, it reduces memory usage and speeds up inference in models without sacrificing performance.

Live free-viewpoint visualization of real humans is critical for immersive communication and interactive digital experiences. Existing methods either rely on computationally expensive optimization or require calibrated cameras and low-resolution inputs, making real-time high-resolution deployment impractical. In this work, we present Tele360, the first real-time feed-forward system for dynamic human reconstruction and live free-viewpoint visualization from sparse, unposed RGB streams. Our system jointly estimates camera poses and reconstructs a dynamic 3D Gaussian representation for each time instance in a single forward pass. To achieve this, we start by designing a lightweight sparsity-aware multi-view transformer backbone that tokenizes foreground human regions while preserving global context through a shared scene token. We then employ a fully transformer-based Gaussian decoder to mitigate convolution-induced over-smoothing while keeping decoding sparse and efficient. In addition, we introduce a hybrid feature pyramid that injects multi-scale appearance cues into geometry prediction. We further introduce a lightweight differentiable Levenberg-Marquardt camera refinement layer to enhance multi-view consistency and geometric alignment. Moreover, to stabilize learning under sparse, unposed inputs, we transfer multi-view geometry priors from a large visual-geometry foundation model via teacher-student distillation. Finally, the predicted Gaussian maps are streamed with video codecs to remote devices for interactive free-viewpoint rendering. Extensive experiments show that Tele360 achieves state-of-the-art visual quality on studio benchmarks while supporting real-time 2K input-to-rendering at over 25 FPS on a single consumer GPU. Additional captured sequences illustrate its performance across varied subjects, clothing, and motions under our multi-camera setup.

Orthrus is a hybrid autoregressive-diffusion architecture that accelerates autoregressive language-model inference by generating multiple tokens in parallel while using a frozen autoregressive backbone. Its central claim is that an intra-model consensus mechanism enables lossless speculative decoding, producing the same output sequence as the autoregressive model. We independently reproduce Orthrus and examine this claim under different numerical precisions. Under BF16 inference, exact trajectory matching occurs in only 45% of cases for the authors' checkpoint and 43% for our independently trained model across 1,190 prompts from 12 domains. The probability of exact matching is also strongly associated with the response-conditional perplexity of the reference model. Despite this trajectory divergence, Orthrus does not show systematic degradation on downstream lm-eval-harness benchmarks. In contrast, repeating the trajectory evaluation with FP32 yields exact trajectory matching on all evaluated prompts. These results show that the practical losslessness of Orthrus depends on numerical precision and that exact trajectory equivalence should be evaluated separately from downstream task performance.

Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling out low-latency uses such as live captioning and voice agents. We present a deployable system for streaming Thai ASR that lets a user steer its vocabulary at decode time, without retraining. A widely used open Thai model, trained with full context, collapses when run as a true stream; we restore streaming with a cache-aware encoder, by converting it or adapting a natively streaming one, and add a shallow-fusion layer that re-ranks candidates inside the streaming decoder with a GPU n-gram language model and phrase boosting. Across two Thai benchmarks and two model sizes, the streaming models stay usable where the full-context model fails, cutting character error rate 4.3-4.5x at a one-second look-ahead while running faster than real time. Decode-time steering then lifts keyword recall from 16.6% to 20.7% at no accuracy cost and negligible overhead; most of the gain comes from an n-gram over ordinary training transcripts, which resolves the written form of code-switched words the model hears but spells inconsistently, with phrase boosting adding targeted control over rare domain terms.

An MoE appliance for trillion-parameter models at low concurrency must host terabytes of weights on one node and serve prefill and decode with fixed resources. Combining operator analysis of two trillion-parameter MoE models, a measured expert routing trace, and agentic serving traces over multiple turns, we explore a design space spanning High-Bandwidth Flash (HBF) and DRAM configurations, bandwidth exposure, and near-data compute. We find that state bandwidth and HBF transport form two largely orthogonal knees and address two provisioning questions. Q1: Once weights move to HBF, what bandwidth-to-capacity ratio does DRAM require? With a 256-GB floor for the state tier, both models meet a $1.10\times$ completion time target at ratios of only $1.4$--$4.0~\mathrm{s}^{-1}$, roughly an order of magnitude below HBM3e's $33.3~\mathrm{s}^{-1}$. Q2: As HBF internal bandwidth scales with capacity, must bandwidth to the host scale proportionally? Six HBF packages expose 384~GB/s per package to the host, 2.30~TB/s aggregate and 62.5% below the 6.14~TB/s full exposure reference, while more packages reduce required bandwidth per package at the same target.

Multimodal large language models (MLLMs) require substantial computation to process numerous visual tokens across all transformer layers. Most methods for efficient MLLM inference exploit horizontal redundancy by compressing visual tokens. Beyond token reduction, recent studies exploit vertical redundancy through early exit or fixed-layer skipping. However, we find that the extent and distribution of this redundancy vary across inputs and differ between self-attention and MLP modules. Motivated by these observations, we propose AdaVSkip, which equips each layer with two lightweight routers that independently determine whether visual tokens pass through by or skip the self-attention and MLP modules. These decisions collectively define an input-specific visual-computation path, but their discrete and non-differentiable nature makes learning effective paths challenging. To address this challenge, we develop a progressive two-stage training framework that updates only the routers while keeping the backbone frozen. Stage I establishes an initial routing policy through supervised training with input-specific targets derived from module-wise necessity scores. To further align the routing policy with task performance, Stage II uses reinforcement learning to optimize routing decisions with direct feedback from generated answers. It combines an answer correctness reward with a skip-consistency reward that discourages excessive retention of visual-token computation. Across three MLLM backbones, AdaVSkip maintains strong task performance with substantially less computation. On LLaVA-NeXT-7B, AdaVSkip reduces FLOPs by 53.2% while preserving the original model's average performance. Combining it with visual token compression increases this reduction to 91.2%, while retaining 97.2% of the original performance on average.

Dynamic-vision-sensor (DVS) cameras generate events on a per-pixel basis with a $μ$s-level temporal resolution, calling for new algorithm-hardware co-design approaches compared to standard frame-based vision. While event-driven graph neural networks (EV-GNNs) emerge as a promising algorithmic solution, they raise new HW challenges by mixing dense-regular compute operations and sparse-irregular memory accesses. We present ETHEREAL, the first EV-GNN accelerator that scales to 640$\times$480 resolutions, thanks to a neighbor-parallel spline convolution engine and a 2D/3D-split memory hierarchy with a novel region-of-interest spatiotemporal caching mechanism. Measurement results demonstrate end-to-end inference with 25.6$μ$s latency and 1.7$μ$J energy per event on state-of-the-art workloads

Large language model (LLM) inference in AI datacenters creates a coupled control problem between GPU serving and facility cooling. Raising ambient temperature setpoints can reduce cooling energy and carbon, but also shrinks thermal headroom, induces GPU throttling, and leads to Service-Level-Objective (SLO) violations. In this paper, we study joint cooling--computing control for LLM inference: minimizing per-job GPU-plus-cooling energy while satisfying thermal safety and latency SLO constraints. We present ETCInfer, an energy-efficient, thermal-aware scheduler that selects a pre-job Computer Room Air Conditioner (CRAC) setpoint and adapts per-GPU frequency and micro-batch size during execution. ETCInfer builds compact physics-informed control models by calibrating GPU heat generation, chassis heat dissipation, CRAC power, and prefill/decode latency relations from telemetry. These models estimate hidden thermal states and time-to-throttle, enabling the scheduler to evaluate energy, temperature, and latency before applying an action. We formulate this joint setpoint--frequency--micro-batch control problem as a partially observable Markov decision process and design ETCAdapter, a learning-based controller that minimizes per-job energy under thermal safety and SLO constraints. We implement ETCInfer as a coordination layer over typical inference and cluster management stacks. Evaluation across real-trace simulation and validation experiments shows that ETCInfer reduces total job energy by up to 33.1%, thermal throttle exposure by up to 92.9%, and keeps SLO violation rates below 0.7% even at ambient temperatures up to $48^{\circ}\mathrm{C}$.

Shared host-memory caching can avoid repeated prefill when a request moves between inference replicas. Its usefulness depends on both correct state transfer and lost prefix locality. We study two single-GPU 27B vLLM replicas sharing a 256 GiB LMCache pool. After adopting an existing packed-page patch, we isolate a raw-pointer fallback that omits the dependency on the current CUDA stream. Controlled byte tests fail under an imposed delay and pass when the dependency is restored; the existing mixed allocator provides a working deployment path. Full-pool allocation checks and service regression complete the validation. A four-block OFF-ON-ON-OFF comparison contains 768 measured requests within two block pairs. Median cross-replica time to first content token falls from 31.715 to 0.605 seconds at 128k input and from 92.047 to 0.790 seconds at 256k. Six-turn synthetic sessions alternating replicas improve by approximately 35% and 45% at initial contexts of 32k and 128k, while fixed placement shows little benefit. This engineering case study identifies practical validation steps and the locality conditions in which shared caching pays off.

External cache transfers can succeed while a hybrid language model resumes from an inconsistent state. We examine the full 45-layer GLM-5.3-Flash model, using the RedHatAI/ GLM-5.3-Flash-NVFP4 quantized checkpoint with vLLM and LMCache under four-way tensor parallelism. A complete-hit recovery mismatch restored state for the full prompt while the scheduler credited one fewer token. We aligned recovery through strict-prefix lookup and established a numerical comparison using shared computation corrections, matched checkpoint scheduling, and fixed per-rank kernel configurations. In a nine-length serial workload, agreement with the modified recomputation control improved from 34/36 to 36/36 generations, each containing 64 token IDs. A separate instrumented run passed recorded transfer-page, effective-tail, and delayed-save checks. Three additional synthetic templates passed 72 paired 256-token continuations across two fresh-container runs. A subsequent serial performance study preserved output equality across 120 requests; among the measured trials, CPU reload reduced time to first token by 46-64% and total request time by 1.9-7.0% relative to modified cold recomputation. The contribution is an experimentally validated integration repair applying an existing checkpoint-alignment principle. The evidence is confined to one model revision and controlled configuration; it does not establish general determinism, task-quality equivalence, concurrent-serving gains, or capacity beyond GPU memory.

Looped Transformers have recently demonstrated strong performance in both reasoning and language tasks by reusing a shared set of parameters across multiple iterations, achieving parameter efficiency without sacrificing representational power. Besides, looped Transformers perform inference directly in the latent space (latent reasoning) to reduce the number of tokens consumed during inference, thereby achieving improved sample efficiency. However, these models typically apply a fixed recursion depth uniformly to every token, leading to suboptimal compute allocation and leaving significant efficiency gains on the table. In this work, we propose dynamic token-choice routing for looped transformers, enabling each token to adaptively determine its own number of loop iterations based on its hidden state. We use a dynamic router to decide whether a token should continue recursing or exit early, allowing simple tokens to bypass unnecessary computation while hard tokens receive deeper processing. To ensure that this adaptive mechanism does not compromise decoding efficiency, we further introduce recursion-wise KV caching, which maintains an independent key-value cache for each recursion loop. This design ensures that tokens at different depths only attend to their corresponding cached states, effectively eliminating redundant computations for exited tokens and enabling fast autoregressive decoding. Extensive experiments show that T-LoopFormer reaches the sota performance under the same parameters on PPL and 10 zero-shot reasoning tasks, even surpassing the base model at 24x FLOPs and our model could reach the lowest inference latency, which validate the effectiveness of token-choice router and recursion-wise KV cache. Code: https://github.com/YuMingQian1234/T-LoopFormer.

Diffusion Transformers deliver state-of-the-art video generation, but their long spatiotemporal sequences make attention the dominant deployment cost, and a deployable low-bit kernel must be accurate and fast. Accuracy is limited by outliers: a block's quantization scale is set by its largest entries, leaving typical entries confined to a narrow range of representable values. Prior work smooths queries and keys, but value outliers follow no fixed channel or spatiotemporal structure and remain the dominant source of output error. Speed is limited by softmax: low-bit Tensor Cores accelerate only the two matrix multiplications, so the high-precision exponential between them becomes the longest pipeline stage on datacenter GPUs. We propose VC-Attention, a training-free low-bit attention framework that addresses both by pairing Value smoothing with a fused probability Cast. V-Smooth reorders value tokens by lightweight online clustering, so the tokens in a hardware block quantize well together. It quantizes only the residual after subtracting the block mean, and restores that mean from the row sum the online softmax already maintains. ExpCast-FP8 maps log-domain scores directly to E4M3 probability codes with one fused multiply-add, eliminating the FP32 exponential and the format conversion. We implement VC-Attention for B200, B300, H200, RTX PRO 6000, and RTX 5090. Across Wan2.2, LongCat-Video, HunyuanVideo-1.5, and MiniMax-H3, VC-Attention improves fidelity over low-bit baselines, speeds up the attention kernel over BF16 FlashAttention-4 by 1.46-1.59x on datacenter Blackwell and Hopper and by 2.3-3.6x on workstation cards, and generates a clip 1.13-1.19x and 1.36-1.70x faster end to end.

Agentic serving can consume orders of magnitude more tokens than chatbot workloads, stressing both KV-cache capacity and decode-time bandwidth. Most KV-eviction methods score cached keys against representative queries drawn from the most recent tokens, assuming future attention resembles recent attention. We show that agentic generation violates this assumption: future queries form a mixture over think, act, tool, and others phases, and principal-angle analysis shows these components occupy measurably different query subspaces, so recency representatives systematically undervalue keys that upcoming phases will need. We propose AGENTKV, which maintains a small query buffer per phase and scores cached keys against their union. We further implement AGENTKV in a persistent multi-turn serving path that carries compressed KV state across turns and compacts retained KV pages online. Across two models, six task domains, and three KV budgets each, AGENTKV improves task score by 5.5 points on average over R-KV and 5.3 over Tri-attention. Relative to upstream full-KV SGLang, AGENTKV improves output-token throughput by up to 1.80x. Code: https://github.com/LiuTaowen-Tony/agentkv.