Research

• Spiking neural networks11+175.0%
• Quantum machine learning34+25.9%
• Character recognition OCR44+25.7%
• Speech emotion23+21.1%
• Voice AI76+13.4%
• Forecasting time133−2.9%
• Robotics195−3.0%
• Channel state information18−5.3%

• Comprehensive and reliable benchmarking for AI capabilities3 papers raise it · 3 address it

  Current benchmarks often lack the depth to fully characterize model capabilities, especially for complex, real-world, or long-horizon tasks.

  • SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Modelsraises · addresses
  • Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimizationraises · addresses
  • One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Predictionraises · addresses
• Effective AI agents in complex, dynamic real-world environments3 papers raise it · 3 address it

  AI agents struggle with real-world tasks requiring adaptation, learning from limited data, or debugging live systems, limiting practical deployment.

  • Where LLM Agents Get Stuck Debugging Databases: Access More Than Reasoningraises
  • World In-Context Learning for Agentic Robot Manipulationraises · addresses
  • Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimizationraises · addresses
  • Sage-Taiyi: A Metacognitive Architecture for Scientific Discoveryaddresses
• Efficient and scalable generation of complex data2 papers raise it · 2 address it

  Generating high-quality, complex data like streaming video or diverse tabular data efficiently and with fewer computational resources is crucial.

  • Few-Step Streaming Video Generation via Condition Shiftingraises · addresses
  • One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Predictionraises · addresses
• Unified models for diverse data modalities and tasks2 papers raise it · 2 address it

  Creating single models that handle diverse tasks or data variations within a complex domain reduces complexity and improves generalization.

  • Prompt2Echo (P2Echo): Text-Prompted Multi-View Echocardiography Segmentation with One Modelraises · addresses
  • One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Predictionraises · addresses
• Reducing computational cost of language model attribution1 paper raises it · 1 addresses it

  Understanding how prompt parts influence language model output is crucial for interpretability, but direct methods are computationally expensive.

  • Sketching Language Models for Context Attributionraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.SDSep 19

  EquiSELD: Efficient training of equivariant sound event localization and detection networks

  Goksenin Yuksel, Marcel van Gerven, Kiki van der Heijden

  First-order Ambisonics (FOA) signals exhibit exact O(3) symmetry: The rotation or reflection of the FOA signal modifies the direction of arrival of the sound sources, while preserving the sound sources themselves. Prior attempts to utilize this spatial symmetry of FOA to improve the efficiency and robustness of sound event detection and localization (SELD) systems either learned only an approximation of the symmetry through rotation-based augmentation or relied on computationally expensive methods to integrate equivariance. Furthermore, prior work focused exclusively on SO(3) equivariance , leaving the potential of incorporating O(3) equivariance for SELD tasks unclear. To address these limitations, we developed EquiSELD. This equivariant attention network processes first-order Ambisonics as paired streams of O(3)-invariant scalars and equivariant intensity vectors, producing an invariant activity magnitude and an equivariant DOA with a Multi-ACCDOA readout. To compare the impact of O(3) versus SO(3)-equivariance, we designed a matched SO(3)-only variant. EquiSELD outperforms prior equivariant networks on both simulated scenes with measured RIRs and recordings of real-world sound…

  PDF

  Summarize this
• arXiv cs.CVSep 19

  SparkDiffusion: Mitigating the High-Sparsity Trap --- A Unified Framework for up to $265\times$ Single-GPU Acceleration of Visual Generation

  Yuxi Liu, Haoyu Li, Zekun Zhang, Tengxu Sun, Yixiang Cai +10

  Video diffusion transformers are expensive because attention dominates long spatiotemporal token sequences. We identify the \emph{high-sparsity trap}: at extreme attention sparsity, step-local training losses keep decreasing while terminal generation quality stagnates or degrades. The trap is one of supervision: the dominant terminal errors originate in the high-noise structure-generation stage, and terminal-aligned training corrects terminal errors that substantially extended step-local training cannot. This yields a simple staging principle: \emph{first adapt the sparse architecture into a coarse prior, then correct the terminal distribution}. We instantiate the principle as \method, a unified acceleration framework for visual generation that combines a short sparse warm-up, few-step trajectory-mixed distillation, and FP8 quantization with fused kernels. \method sustains $97\%$ attention sparsity with strong visual quality on long-sequence 720P generation across Wan2.1/Wan2.2 backbones and T2V/I2V tasks, and $90\%$ sparsity on Wan2.1-T2V-1.3B-480P. With 3-step CFG-free inference, \method achieves a $265\times$ end-to-end speedup over the 50-step CFG dense baseline for…

  PDF

  Summarize this
• arXiv cs.SDVoice AISep 19

  Bearings: Self-Supervised Soundfield Embeddings from First-Order Ambisonics

  Goksenin Yuksel, Marcel van Gerven, Kiki van der Heijden

  Recently proposed self-supervised audio encoders learn powerful general-purpose representations of sound scenes, yet they are spatially blind. To supply the missing spatial representation of sound scenes, we introduce Bearings. Bearings is a self-supervised framework that learns soundfield embeddings from unlabeled first-order Ambisonics. We pre-train a masked auto-encoder paired with a decoder conditioned on frozen acoustic embeddings from an off-the-shelf single-channel audio encoder. Our results show that the resulting soundfield embeddings form a reusable stream that can be attached to frozen acoustic encoders with a lightweight trainable fusion head. On sound event localization and detection, concatenating our soundfield embeddings with acoustic representations provides the missing spatial information and enables joint detection and localization, raising the location-dependent F-score from below 4 to 50 on TAU-NIGENS 2021 and 39 on STARSS23. To our knowledge, Bearings is the first self-supervised soundfield encoder whose embeddings plug into frozen acoustic encoders without retraining either model.

  AI60PDF

  Summarize this
• arXiv cs.LGMultimodalSep 19

  Ask for Any Appliance: A Prompt-Programmable Foundation Model for Non-Intrusive Load Monitoring

  Xudong Wang, Jiacheng Cui, Junyu Xue, Tongxin Li, Guoming Tang

  Non-intrusive load monitoring (NILM) estimates appliance-level consumption from a whole-home meter, but appliance-specific models and fixed output inventories make coverage costly to extend. We present FM4NILM (Foundation Model for NILM), a single prompt-programmable model that estimates a requested appliance's power trajectory from aggregate measurements, a natural-language description, and optional activation exemplars. A lightweight cadence-aware transformer is pretrained by masked reconstruction on 645k sequences from seven public corpora spanning 1-60 s sampling intervals, then aligned with appliance requests using observation-masked losses for partially labeled households. A Bernoulli-lognormal decoder separates activity detection from conditional power estimation. On held-out households and time periods from REDD, UK-DALE, and REFIT, one frozen text-prompted model serves twelve appliance-corpus requests, achieving 0.556 event F1, 0.625 AUPRC, and the lowest active-window MAE (251.8 W) among seven appliance-specific baselines. Streaming score aggregation raises event F1 to 0.582 with a 60 s aggregation delay. In a separate category-held-out evaluation, adding ten activation…

  AI70PDF

  Summarize this
• arXiv cs.AISep 19

  CraftBench-UE: Deterministic Evaluation for Coding Agents in Unreal Engine

  Shutong Wu, Kevin Calderone, Andy Tsen

  Building gameplay features in a game engine requires more than code, as code that compiles and runs does not necessarily implement the requested gameplay. We introduce CraftBenchUE, an evaluation harness that runs agents in an isolated Unreal Engine environment, reconstructs their saved submissions in fresh projects, and applies deterministic build, asset, and runtime checks without an LLM judge. Based on the harness, we built a benchmark consisting of 70 tasks spanning C++ source, Blueprint assets, and editor scripting. We evaluate seven models under two editor-tool configurations, with a file-and-shell baseline on C++ tasks. We further pair tasks that specify the same gameplay and use the same runtime tests, but require C++ and Blueprint as the deliverables. Across the 10 paired tasks, C++ completion rates exceed Blueprint by 30.0 and 42.9 percentage points in the two tool configurations. Among on-time Blueprint submissions in this paired set that pass asset checks, 42.2% and 50.0% fail explicit runtime assertions. These submissions satisfy asset requirements but fail the required gameplay tests. We will release the harness, task benchmark, and our trajectory findings with the…

  PDF

  Summarize this
• arXiv physics.plasm-phSep 19

  Real-Time Plasma State Prediction via FPGA-Accelerated Quantized Recurrent Probabilistic Neural Networks

  Daniel Gaytan-Villarreal, Aiken Xie, Tu Pham, Rohit Sonker, Chiara Amendola +3

  Real time plasma state estimation for control of Tokamak devices are challenging due to the stringent latency requirements of the plasma control system (PCS). We present an end-to-end workflow for deploying a recurrent probabilistic neural network (RPNN) on FPGA hardware. We combine architecture size reduction with quantization-aware training via QKeras. The model is then synthesized using hls4ml, targeting a Xilinx Alveo U50 device. We report a design that fits comfortably within all four resource budgets (DSP, LUT, FF, BRAM) at deterministic sub-10~$μ$s single-timestep latency, meeting the requirements for real-time inference inside a model-predictive-control-style plasma control loop.

  PDF

  Summarize this
• arXiv cs.CVSep 19

  QwenVLConnector: A Fast, Unified Medical VLM Chatbot for Fine-Grained Clinical Perception and Text Generation

  Le Thien Phuc Nguyen, Thien Nguyen, Thanh-Huy Nguyen, Gia Minh Hoang, Anh Mai Vu +1

  Most medical vision-language models (VLMs) excel at open-ended report generation and VQA but provide limited support for structured, fine-grained clinical perception within a unified interface. We present QwenVLConnector, a Qwen2.5-VL-based medical chatbot that unifies classification, multi-label classification, textualized detection, counting, regression, and free-form report generation under a single next-token objective. Our key component is a lightweight dense multi-layer Connector that aggregates low- and high-level visual features, aligns them through the pretrained vision Merger, and fuses them with the final visual representation without increasing sequence length. This design enriches visual tokens with complementary spatial and semantic cues while preserving efficiency. On FLARE-2D, QwenVLConnector improves detection F1 from 0.55 to 0.85, raises single-label classification from 0.37 to 0.51, and boosts report-generation GREEN by up to 18.3 points over the Qwen2.5-VL baseline. We further explore multimodal in-context learning for report generation, showing additional improvements without updating model parameters. Overall, QwenVLConnector offers a unified and efficient…

  PDF

  Summarize this
• arXiv cs.AISep 19

  From Inference Engine to Inference Control Plane: Connecting vLLM, llm-d, and the Evolution of Efficient Distributed LLM Serving

  Twinkll Sisodia

  Large language model (LLM) inference is evolving from an engine-local optimization problem into a distributed control problem involving reusable state, phase placement, heterogeneous accelerators, networking, autoscaling, reliability, and service-level objectives. This paper connects that transition across peer-reviewed systems research, open-source implementations, and documented production studies. It treats vLLM and llm-d as complementary layers: model-serving engines optimize execution through mechanisms such as PagedAttention, continuous batching, kernels, quantization, and parallelism, while an inference control plane can optimize where, when, and under what policy execution occurs across a fleet. The contribution is synthesis rather than a new benchmark; all reported performance and deployment results remain attributed to their original sources. The combined evidence suggests that the scarce resource in modern inference is shifting from raw FLOPs alone toward managed state, placement, network movement, reliability, and decision quality. We propose an Inference Execution Planner that selects feasible execution plans rather than only endpoints, including aggregated versus…

  PDF

  Summarize this
• arXiv cs.LGSep 19

  Provably Efficient Reinforcement Learning in Continuous-Time Episodic MDPs with Poisson Decision Epochs

  Kenny Guo, Valentio Iverson, Sahan Wijetunga, William Chang

  Many real-world reinforcement learning (RL) problems evolve in continuous time, where decisions occur at irregular, event-driven intervals rather than at fixed discrete steps. We study episodic continuous-time Markov Decision Processes (MDPs) in which decision epochs are governed by a homogeneous Poisson process and the reward and transition dynamics vary smoothly over time. We consider both a fixed number of jumps per episode and a fixed time budget with a random number of Poisson decision epochs. Under a Lipschitz continuity assumption in time, we exploit local smoothness through discretization and extend both UCRL (Auer and Ortner 2006) and Q-learning (Jin et al. 2018) to this setting, proving $\widetilde{O}(T^{2/3})$ regret bounds for both model-based and model-free algorithms. Finally, we establish matching $\widetildeΩ(T^{2/3})$ minimax lower bounds, showing that the rate is optimal up to logarithmic factors. These results provide the first tight regret guarantees for Lipschitz-smooth continuous-time episodic MDPs with Poisson decision epochs.

  PDF

  Summarize this
• arXiv cs.LGInference & servingSep 19

  Perplexity Cost Understates What Activation Quantisation Breaks

  Anish Sathyanarayanan

  Activation quantisation is usually evaluated with an aggregate metric, perplexity, averaged over every token a model predicts. We ask whether that average identifies which computations a quantiser damages. Perplexity turns out to be a reliable aggregate signal: across 12 models from four families and 780 within-model comparisons, the arm perplexity prefers also retains more induction and more retrieval in all but 2.1 and 4.0 percent of cases respectively. But where perplexity has risen by only a factor of 1.2 to 1.5, induction still keeps 0.959 of its intact accuracy while retrieval has already fallen to 0.554, a gap the aggregate number does not surface. This gap has structure, not just size: a matched Gaussian-noise control of the same per-channel magnitude leaves it largely intact, and randomising only the sign of the quantisation error, every magnitude held fixed, is nearly as harmless, so magnitude alone does not explain the damage. Quantising in a rotated basis, which changes coordinate alignment without changing error magnitude, restores induction from 0.001 to 0.980 at three average bits per token in a single-block intervention, though retrieval recovers less completely…

  AIEvals80PDF

  Summarize this
• arXiv cs.CVAgentsSep 19

  MM-ContextFold: Context Folding for Multimodal Agentic Retrieval

  Yang Tian, Fan Liu, Jingyuan Zhang, Zhenyang Li, Yupeng Hu +1

  Multimodal Agentic Retrieval (MAR) requires agents to solve complex information-seeking tasks by iteratively invoking external tools. Typical frameworks such as ReAct maintain raw multimodal inputs and the accumulating interaction history in a single, ever-growing context, leading to the context explosion problem. While existing methods alleviate this issue by compressing redundant text, effective strategies for managing token-intensive visual content remain largely underexplored. To address this gap, we first conduct a systematic empirical study of approximately 10,000 trajectories. The results show that as visual cues are progressively extracted through external tools and textualized into the context, raw images become increasingly redundant. Continued image retention is associated with higher output entropy and can even degrade task accuracy. Motivated by these findings, we propose MM-ContextFold, a training-free framework that loads raw images only when needed. It maintains a persistent, text-only main context for high-level planning and spawns ephemeral branch contexts for image-dependent subtasks. Within each branch, the agent loads the relevant images, completes the…

  AIRAG80PDF

  Summarize this
• arXiv cs.LGSep 19

  Whitening Inverts the Hierarchy: What the Norm of a Whitened Embedding Measures

  Mohammed Ahnouch, Lotfi Elaachak

  Whitening a foundation-model embedding and using its squared norm as a training-free likelihood surrogate is motivated by the observation that whitened coordinates often appear approximately standard normal. We show that this observation follows from the projection central limit theorem and therefore does not imply a Gaussian joint distribution. Across multiple encoders and three training objectives, we find systematic over-dispersion of the whitened radius relative to the Gaussian reference, including against distributional clones with identical mean and covariance. We further show that the commonly reported agreement between empirical and theoretical norm statistics is an algebraic consequence of in-sample whitening and does not constitute evidence for Gaussianity. We identify the mechanism behind this behavior: whitening reverses the encoder's spectral hierarchy, shifting the contribution to the squared norm toward near-degenerate directions that encode predominantly noise. In these directions, the dominant variability is governed by a single input-dependent scale. We estimate this scale from two moments and use it to predict, without additional free parameters, the…

  PDF

  Summarize this
• arXiv cs.ROSep 19

  DiagGen: Agentic Generation of Deformable Assets with Sim-based Diagnostics for Robotic Simulation

  Guanxiong Chen, Yiduo Qu, Qianjun Xia, Pengyu Jing, Yixian Cheng +10

  While simulation-ready deformable assets are essential for in-silico robotic manipulation tasks, existing generation frameworks typically assess physical plausibility after generation, leaving an object's simulated response unused as feedback for repairing upstream errors. We present DiagGen, an agentic framework that turns a single in-the-wild image into a simulation-ready deformable asset through a generate--simulate--diagnose--refine loop. DiagGen constructs part-aware geometry and material parameters, then uses a VLM (vision-language model)-based agent to select semantically informative regions, probe them in a physics simulator, observe material responses, and route evidence-backed repair cues to the responsible generation stage. Experiments on 40 assets show that diagnostics provides useful repair cues and can moderately improve the quality of generated deformable assets. Finally, we show that unlike assets generated from visual foundation models which may not be simulatable, DiagGen-generated deformables can be directly dropped into a high-fidelity physical simulator for the planning and simulation of contact-rich pick-and-place tasks. The project's website is…

  Code
• arXiv cs.LGSep 19

  When Does Adversarial Refinement Help? A Negative Result and Open Problem in Adapting R3GAN to Time Series Imputation

  Yufeng He

  Diffusion models and transformers have supplanted GANs for multivariate time series imputation, largely on grounds of GAN training instability. R3GAN (NeurIPS 2024) removes that instability via regularized relativistic losses with provable convergence, raising a natural question: do stable, modern GANs revive adversarial imputation? We adapt R3GAN to 1D temporal data with a coarse-to-fine refinement framework and a frequency-domain discriminator, and audit 14 saved configurations across 3 datasets. Because these are heterogeneous single runs, the evidence is descriptive rather than a matched causal ablation. We report a negative result. All five saved mean/zero-start configurations improve by 48.4-70.2%. Among eight eligible non-legacy linear-start configurations, the mean change is -0.7% (range -3.0% to +1.1%); a separate -21.9% legacy logging anomaly is retained for provenance but excluded from that aggregate. In a saved Weather comparison, standalone R3GAN-1D underperforms BRITS by 5.8x. Crucially, we argue the common explanation (that GANs optimize distributional rather than point-wise objectives) cannot be the whole story, since diffusion models also optimize distributional…

  AI30PDF

  Summarize this
• arXiv cs.CRSep 19

  An LLM-Assisted AutoML Framework for Intrusion Detection in IoT Networks

  Li Yang

  Internet of Things (IoT) systems are increasingly deployed in smart homes, transportation, energy systems, and critical infrastructure. This broad connectivity improves service intelligence, but also enlarges the attack surface of IoT networks. Machine Learning (ML)-based Intrusion Detection Systems (IDSs) are widely used to identify malicious network threats and protect IoT systems, but developing effective ML-based IDS models often requires human expertise and repeated manual decisions on many procedures, including data pre-processing, feature selection, model selection, and hyperparameter tuning. Automated Machine Learning (AutoML) reduces this burden by automating steps of the ML pipeline using optimization techniques, but conventional AutoML methods can consume substantial optimization time because they explore broad candidate model families and large hyperparameter spaces. This paper proposes a Large Language Model (LLM)-assisted AutoML framework for IoT intrusion detection. The proposed framework uses an LLM as a policy generator that converts dataset profiles into bounded and validated AutoML policies for automated data balancing, automated feature engineering, and…

  PDF

  Summarize this
• arXiv cs.DMSep 19

  Counting and Covering in Nearest-Neighbour Representations of Boolean Functions

  Martin Anthony

  We study the number of prototypes needed to represent Boolean functions by nearest-neighbour classification. There are two distinct settings: the prototypes may be arbitrary points of Euclidean space, or they may themselves be required to lie in the Boolean cube. For unrestricted prototypes, we strengthen a known lower bound for almost all Boolean functions. The bound applies simultaneously to nearest-neighbour voting rules with any number of voting neighbours, and substantially narrows the gap with the known general upper bound. We obtain a VC-dimension bound for classes with a bounded number of prototypes, and show that it is sharp in order in dimensions at least four. We then study Boolean prototypes, beginning with symmetric threshold functions. A connection with covering designs expresses the minimum number of prototypes at every threshold level exactly in terms of a covering number, and leads to further exact results for related monotone functions, including disjunctive extensions and a characterisation of when a representation with a single negative prototype is possible. For a uniformly random Boolean function, the Boolean nearest-neighbour complexity, as a proportion of…

  PDF

  Summarize this
• arXiv cs.LGSep 19

  The Role of Coordinates in Pareto Regret for Adversarial Multi-Objective Bandits

  Changkun Guan, Mengfan Xu

  Adversarial multi-objective bandits hold the potential to help us optimize choices (arms) whose reward is a multidimensional vector chosen by an adversary and whose performance is measured by Pareto regret. We define loss as one minus reward and measure the easiness of a coordinate by the smallest cumulative loss of the arms on it, and call the coordinate easier when this quantity is smaller. Existing work suggests that in theory an easier coordinate may reduce Pareto regret. However, in practice, one may not know which coordinate is easier. On the negative side, we show that this lack of information eliminates the possibility: a smaller cumulative loss does not improve the worst-case order of Pareto regret. Precisely, let \(L_d\) be the smallest cumulative loss along coordinate $d$ over $T$ rounds. For \(K\ge4\) arms, \(T\ge6\) rounds, and at least 2 coordinates, we prove that the minimax expected Pareto regret is \(Ω(\min\{T-L_0,\sqrt{K(T-L_0)}\})\). It is monotonically decreasing in \(L_0\), even when \(L_0=\min_d L_d\) itself is known. On the positive side, this result motivates the possibility that other coordinates, not just the easy one, may suffice to attain the optimal…

  PDF

  Summarize this
• arXiv cs.CLSep 19

  OmniEdu: Open Foundation Models for Learning and Teaching

  Hao Liang, Qihan Lin, Meiyi Qiang, Linzhuang Sun, Hengyi Feng +3

  Educational foundation models must solve problems, understand curriculum structure, diagnose learner difficulties, and provide appropriate instructional support. Existing educational language models often focus on either problem solving or tutoring, with training mixtures organized by source or task rather than capability. We present OmniEdu, an open family of foundation models for K-12 learning and teaching. Its instruction-tuning corpus combines over 100 educational resources and general instruction sources, organized around four capabilities: subject competence, curriculum grounding, diagnostic reasoning, and pedagogical action and scaffolding. Our pipeline integrates deterministic cleaning, semantic auditing and rewriting, task-specific quality scoring, token-budgeted diversity selection, and pedagogical instruction assignment. It yields 69,999 examples and 15.96M supervised response tokens, including 60,951 education-specific examples. We fine-tune 4B, 9B, and 27B models and evaluate curriculum grounding, K-12 problem solving, and pedagogical tutoring, alongside general capability. Education-oriented tuning consistently improves all three educational benchmark groups across…

  PDF

  Summarize this
• arXiv cs.LGSep 19

  Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone

  Chenyu Zhu, Ruoyu Zhao, Zhichao Lu

  Modern Transformer design and compression both reduce to allocating capacity under a budget. The standard scalars for these decisions, #Params and #FLOPs, capture size and compute but not architectural structure: two architectures with identical parameter budgets but different depth-width, head, or FFN allocations receive identical scores yet behave differently. We propose Neural Spectral Capacity (NSC), a closed-form scalar grounded in the singular-value spectrum of each weight matrix. Under standard random initialization, the Marchenko-Pastur law renders NSC computable from the architectural specification alone, with no model instantiation, data, or gradients. Its layer-wise additive structure admits NSC-DP, an exact dynamic-programming solver returning the architecture globally maximizing NSC under resource constraints in seconds on a CPU -- a guarantee that black-box search over existing training-free proxies cannot provide. Empirically, NSC outperforms #Params, #FLOPs, and representative training-free proxies in ranking across seven Transformer and CNN families (on FlexiBERT, $τ= 0.505$ on pairs differing in #Params by less than 10%, where #Params collapses to 0.082); NSC-DP…

  PDF

  Summarize this
• arXiv cs.PFSep 19

  Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving

  Muhammad Abdur Rab Siddiqui, Daniela Rojas, Chen Yang, Wenqi Cui, Yuanyuan Shi +1

  Large language models (LLMs) and agentic AI systems are creating rapidly growing inference energy demands as model sizes grow and reasoning trajectories extend. While in practice, many queries do not require the capabilities of the largest available model, and routinely directing such queries to a high-capability model can introduce unnecessary, considerable computation and energy consumption. In this paper, we investigate whether adaptive routing across a heterogeneous pool of LLMs can reduce this energy burden without substantially compromising task performance. We design a language-model-based router that reads in each query and selects an answer model from a fixed candidate pool. The candidate models are first profiled through an offline tournament that records their correctness, latency, power, and GPU energy for each query. Using these measurements, the router is trained through supervised fine-tuning followed by group relative policy optimization (GRPO) with the tailored paradigms. Results demonstrate that learned routing can selectively allocate expensive model capacity based on query context and improve the accuracy-energy tradeoff in multi-LLM serving. Across seven…

  PDF

  Summarize this