每天知道
你的领域
出了什么

The paper presents a new parameter-efficient adaptation method called ChebyMA (Chebyshev Manifold Adaptation). ChebyMA adopts weight matrices through a multi-surface superposition of Chebyshev polynomial bases evaluated on learnable coordinates and combined via trainable coefficient matrices, replacing standard linear projections with highly expressive continuous function approximation. Theoretically, we establish an Approximation Expressivity Theorem, proving from the perspective of function approximation theory that single-manifold ChebyMA guarantees convergence in Frobenius norm error of reconstruction. Besides, drawing on Kolmogorov $n$-width intuition, we demonstrate the expressive advantages of multi-manifold superposition ($S > 1$) in decoupling high-dimensional complex features. Experimental results on Computer Vision CIFAR datasets(CIFAR-10, CIFAR-100)\cite{CIFAR} and Natural Language Processing (AG News, SST-2) datasets demonstrate that ChebyMA consistently achieves a superior parameter-accuracy Pareto front compared to standard full-parameter fine-tuning, LoRA\cite{LoRA}, TLoRA\cite{TLoRA}, and StelLA\cite{StelLA}. ChebyMA significantly outperforms other tested methods in tested datasets, validating its solid theoretical foundation for generality with purely vectorized computations.

The rapid advancement of large language models (LLMs) has led practitioners to increasingly rely on them for answering questions about hardware description languages (HDLs). Because HDL is ultimately synthesized into physical hardware, an imprecise or redundant answer can propagate into timing violations or non-synthesizable logic that surface only late in the design flow, making the quality of HDL answers especially consequential. However, the quality of LLM-generated responses, particularly in comparison with answers provided by human experts, remains unclear. To investigate this question, we collect 6,246 HDL Q&A posts with accepted answers from Stack Overflow and curate them into a dataset, organized into a taxonomy of four main categories (Conceptual, Debugging, Generation, and Optimization) and ten subcategories. Using this dataset, we design a user study conducted with 19 HDL engineers with one to three years of experience. Our findings reveal a pervasive over answering tendency: LLMs supply correct content but bury it under redundant alternatives (65.7%) and verbose padding (69.1%), while nearly half of answers (49.0%) fail to fully align with expert answers yet participants still preferred LLM responses for readability (58.3%). Motivated by these findings, we propose a multi-agent framework for improving LLM-based HDL question answering. We evaluate answer quality using an LLM-as-Judge and two structural metrics: the number of core answers, which reflects redundancy since LLMs often provide multiple alternative solutions, and the length of non-core content, which reflects verbosity. Evaluated on the four mainstream LLMs, our framework increases the average core-answer quality score from 3.71 to 4.67 (+0.96) and the non-core content quality from 3.72 to 4.23 (+0.51), on a five-point scale.

AI agents increasingly act within the same clinical, political, scientific, and social systems that behavioral scientists study. Evaluating these systems requires source-level diagnosis: the same behavioral pattern may arise from an agent representational substrate or from the roles, objectives, interaction structures, and governance rules that shape its expression. This Perspective proposes a diagnostic framework for AI agent behavior: layer attribution. The foundational computational layer defines what behaviors are possible through architecture, memory, perception, attention, and representation. The behavioral modulation layer shapes how those capacities are expressed through identity, resources, objectives, social interaction, institutional constraints, and governance. The framework clarifies three consequences: surrogate validity is a model-task-layer relation, human-AI divergence provides diagnostic evidence, and governance requires source attribution before intervention. Treating AI agents as behavioral actors therefore requires evaluation methods that determine where behavior originates before deciding how to explain, validate, or govern it.

This paper provides an experimentally verified formal law for calculating the uplift that diversity of thought provides in Large Language Model (LLM) ensembles. From first principles, we derive an exact decomposition of LLM ensemble lift into rescue and damage masses, which yields a compact heuristic for calculating uplift. From this we extract the metrics which predict ensemble performance: an accuracy-adjusted correctness correlation, $φ_{\mathrm{adj}}$, together with the accuracy gap and collective accuracy of the pair. We test the law on 767,520 inferences from ten open-weight models over two graduate-level science benchmarks, together with a novel agentic cybersecurity benchmark in which each model conducts digital-forensics investigations by multi-turn tool use in a network-isolated sandbox (23,520 graded trials including abstentions); all votes are released openly. Calibrated once on SuperGPQA at a 40:60 vote split, the heuristic predicts lift on the calibration set with Spearman's $ρ=0.84$ and, with its coefficients frozen, transfers to two datasets never used in calibration ($ρ=0.51$ on GPQA Diamond and $0.84$ on the forensic tasks), whilst the measured swap mass tracks realised lift with $R^2\ge 0.96$ throughout. Raw $φ$ has almost no predictive power ($R^2\le 0.09$ throughout); the accuracy-adjusted $φ_{\mathrm{adj}}$ is markedly superior ($R^2=0.67$ on SuperGPQA), and the heuristic combining these metrics is the most stable pre-pooling predictor across the three datasets.

Large language models (LLMs) can plan tool-mediated scientific work, but scientific instruments remain difficult to connect to such agents: vendor APIs may load only inside acquisition host processes, facilities may prohibit cloud-hosted agents, and natural-language interfaces can emit physically unreasonable arguments. We present a method for connecting local LLMs to scientific instruments through the Model Context Protocol (MCP). It combines: (1) a schema-bound tool surface that validates requests against physical bounds before adapter dispatch; (2) a vendor-neutral, host-process adapter pattern separating language-side reasoning from instrument-side execution; (3) a persistent lifecycle for long-running live-processing jobs; and (4) MCP-prompt-registered skills that compose typed tools into reusable multi-step protocols. Our open-source reference server exposes 30 typed tools, 5 live-job types, and 6 skills through a physics-plausible simulator implementing the same protocol surface. Validation is software-only: all 120 hardware-independent tests pass deterministically, while 15 local-LLM integration tests pass 12-15 of 15 across runs because of model nondeterminism. A preliminary single-run probe across five open tool-calling LLMs indicates that the schema-bound interface can be driven locally by small open-weight models without cloud dependency; it is not a benchmark and has no confidence intervals. The method provides a bounded, testable, and reproducible foundation for closed-loop agentic instrumentation research.

LLM agents can leak privacy (e.g., paths, emails) and credentials (e.g., API keys) as agent observations (e.g., tool outputs, shell logs, and file reads) are appended to provider-bound transcripts. Existing placeholder redaction is brittle: it can miss embedded or cross-turn references, over-redact benign lookalikes, and destroy the structure useful for reasoning. We present SlotGuard, a local transcript boundary that can hide sensitive data while retaining agents' performance. SlotGuard rewrites structural bindings as typed, suffix-aware slots, replaces secrets with format-preserving synthetic values, links cross-turn references with a lightweight session graph, and restores raw values only inside the trusted runtime. On controlled repository-oriented agent transcripts, SlotGuard removes all 20,814 annotated structurally sensitive characters across 9,229 paths and reduces credential leakage to 0.0% across 852 planted values. It remains close to raw-transcript task success across four upstream models, while generic redaction drops to 2.5%. Transcript rewriting takes a median of 14.424~$μ$s per agent turn. The code is publicly accessible at https://github.com/illinoisdata/SlotGuard.

The problem of fair multi-agent coordination in decentralized settings is one of the most pressing challenges for building efficient collaborative systems. Resource allocation is based on optimized collective arrangements accounting for agents' needs. Such coordination should not only be computationally efficient but also account for fairness, i.e., equitable redistribution of costs incurred by all agents. Recent literature has proposed several algorithms that efficiently determine optimal plan combinations balancing system-wide efficiency and individual discomfort of agents in a centralized setting. However, these works do not address equitable resource optimization in fully decentralized scenarios, specifically, the optimized redistribution of discomfort among coordinating agents so that none experiences a discomfort level that could lead to loss of incentive or polarization that can disrupt planned operations. In this work, we study the problem of optimizing three objectives: (i) system-wide efficiency, (ii) individuals' comfort and (iii) fairness (i.e., balancing of incurred discomfort costs) in decentralized multi-agent coordination. We design a novel model to optimize those three orthogonal objectives, without any substantial increase in communication and computational overhead. Through experiments on two real-world datasets, we validate the model and demonstrate that it can achieve fairer optimization outcomes, while satisfying agents' preferences and system goals.

Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing. However, LLMs often suffer from hallucinations and lack of relevant knowledge when dealing with question answering (QA) tasks. To mitigate these issues, knowledge graphs (KGs) have been utilized to enhance LLM reasoning. Nevertheless, KGs often contain noise and errors, while existing KG-enhanced LLM approaches are generally unable to identify and filter such noisy and erroneous content, which can instead amplify hallucinations and pose challenges for reliable reasoning. Uncertain knowledge graphs (UKGs), which associate each triple with a confidence score to quantify uncertainty, offer a promising direction to address this challenge. Compared with prior work, we investigate how to leverage UKGs to support LLMs for QA. We propose Debate-on-Graph (DoG), a new framework that enables LLMs and UKGs to collaborate adaptively for reliable reasoning. Specifically, we first design a heuristic search algorithm tailored for UKGs to extract reliable and question-relevant subgraphs, thereby reducing noise and errors in retrieved knowledge. We then introduce a Multi-Agent Debate mechanism, which yields reliable answers through adaptive adversarial debates, aiming to fully exploit the knowledge in UKGs while preserving the reliability of retrieved evidence. Extensive experiments on four benchmark QA datasets show that DoG achieves state-of-the-art performance over existing LLM reasoning methods and KG-based baselines, while enabling reliable and adaptive reasoning. Our code is available at https://github.com/seucoin/Debate-on-Graph.

Designing effective Lean proof agents is a central challenge in formal mathematical reasoning. Beyond building stronger provers, recent work emphasizes the workflow around Lean: how an agent decomposes proof obligations, uses tools and compiler feedback, diagnoses failures, repairs proofs, and maintains structured proof context. Motivated by code-level self-evolving agents, we study whether such workflows can be evolved rather than hand-designed. We present a self-evolving Lean proof agent in which a small fixed, trusted runtime wraps a fully mutable workspace: the proof workflow, prompts, and tools. Unlike most self-evolving systems, which optimize against a fixed external benchmark, our system coevolves the agent and its benchmark. Between generations, the highest-scoring agent (the champion) revises the active task distribution through a mastery-throttled curriculum update that introduces harder proof obligations only after the current level is mastered, and a single-anchor recalibration re-runs the champion on the updated benchmark to keep scores comparable as difficulty rises. All evolution stays inside a Lean-grounded verification loop: however the agent rewrites itself, a success counts only when its behavior yields Lean-verified proofs under a trusted snapshot, and each attempt must emit a machine-readable, Lean-grounded proof context whose representation may evolve but whose groundedness is enforced. We run the coevolving trajectory and a fixed-benchmark baseline for 15 active generations and compare them on a held-out miniF2F test split. The best coevolving agent reaches a 45.1% held-out solve rate, versus 12.7% for the seed and 32.0% for the best fixed-benchmark agent, showing that verifier-grounded self-evolution can improve Lean proof workflows under a coevolving benchmark.

Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results. Current evaluation metrics reduce such a trajectory to a binary success flag or compare it against a reference by exact matching. A success flag cannot distinguish a sound solution from one that succeeds by luck, and says nothing about why a failed run went wrong. Exact matching penalizes plans that are valid but reordered or decomposed differently from the reference. We reframe trajectory evaluation as a distance between the agent's execution graph and a set of valid solution graphs, and instantiate it via an unbalanced fused Gromov-Wasserstein transport problem over attributed dependency graphs. The resulting score, termed \otap{} (Optimal Transport for Agentic Planning), is a pseudo-metric that is provably invariant to dependency-preserving reorderings and has bounded sensitivity to redundant steps. Its unbalanced marginals handle missing or hallucinated steps without forcing a match, and its soft coupling accommodates variation in plan granularity. On controlled perturbations and three public benchmarks, \otap{} separates valid from invalid trajectories in a regime where semantics-only metrics score below chance. Its accuracy is highest when the dependency graph is recovered exactly, and drops only when the graph is inferred heuristically from free-text traces.

Large language model (LLM) agents offer a generative approach to simulating human behavior under conditions that may have few or no direct historical analogues, a common challenge in disaster and infrastructure-disruption planning. However, this generative capacity creates a validity problem: individually plausible agent reasoning may fail to reproduce empirical population behavior. We evaluate whether empirical grounding improves the statistical realism of LLM-agent simulations during disruptions. Specifically, we develop an empirically grounded LLM-agent framework that embeds demographic profiles from the American Community Survey, baseline routines from the American Time Use Survey, and urban spatial context into agent initialization, memory, decision prompts, and activity execution. An independent household survey conducted during the July 2024 Philadelphia heatwave is reserved as an external validation benchmark. Compared with an ungrounded LLM-agent baseline, the grounded model improved reconstruction of normal daily routines, increasing mean correlation with empirical activity profiles from 0.528 to 0.912 and reducing mean squared error from 0.066 to 0.008. Under heatwave conditions, the grounded model better reproduced survey-derived activity profiles, increasing mean correlation from 0.349 to 0.836 and reducing mean squared error from 0.098 to 0.012. The grounded model captured 46.4% of observed heatwave response amplitude, compared with 20.6% for the ungrounded baseline. These findings show that empirical grounding can make LLM agents more statistically credible simulators of population behavior while revealing remaining gaps in modeling human adaptation during disruptions.

Mixture of Experts (MoE) architectures have emerged as a dominant paradigm for scaling Large Language Models (LLMs). However, MoE inference on conventional hardware is constrained by three fundamental bottlenecks. These encompass the massive memory bandwidth required to fetch non-contiguous expert weights, the non-deterministic scatter-gather traffic generated by input-dependent token routing, and the tail-latency dependency imposed by synchronous expert output aggregation. To address these challenges, we propose ThAME, a three-dimensional (3D) heterogeneous multi-chiplet architecture for MoE inference. ThAME employs Ferroelectric Field-Effect Transistor (FeFET)-based non-volatile and DRAM-based volatile memory chiplets with a co-designed compute mapping strategy that aligns the distinct computational profiles of attention mechanisms and expert routing. Furthermore, we design a specialized Network-on-Chip communication backbone optimized to mitigate the bottlenecks associated with non-deterministic token routing traffic across the combinatorial space of input-dependent MoE traffic patterns. Experimental results demonstrate that ThAME outperforms state-of-the-art counterparts by up to 15.7x in terms of speedup and improves energy efficiency by up to 9.8x.

Building long-horizon robot agents requires composing closed-loop pipelines — perception, belief update, planning, and control — whose components run at different clocks and with variable latency. Today, these systems are often assembled with ad-hoc concurrency and pub/sub conventions that make timing and input-consumption semantics implicit, yielding schedule-dependent behavior that is hard to reproduce, debug, and reuse. Current solutions typically solve parts of this problem at either the algorithmic or the systems layer, but not both. In this work, we propose Retriever, which spans the entire stack: an asynchronous decision model, a programming model, a runtime, and an example closed-loop agent pipeline. Retriever represents an agent as a graph of stateful causal stream functions executed on explicit run clocks. We formalize this view via an asynchronous environment-agent loop over continuous-time streams and show that finite-memory causal policies can be represented by compositions of these operators. Retriever compiles these graphs into a runtime that supports multiple backends, enabling systematic debugging across running environments and deterministic replay from logged asynchronous data. We evaluate Retriever through a real-robot case study together with controlled studies of runtime overhead and deterministic replay behavior.

Sparse autoencoders (SAEs) compress model activations into sparse codes, but equal reconstruction error and sparsity can preserve different linearly decodable signals. We formalize this ambiguity as a matrix-valued distortion between optimal ridge-prediction operators and train decoder-preserving SAEs by combining this distortion with reconstruction loss. In a rank relaxation, an isotropic task prior saturates per-mode omission costs without changing PCA's ordering, whereas a structured prior can change which modes are retained. A controlled sparse experiment shows that a declared prior protects held-out combinations from its task subspace. On GPT-2 small block 8, DPSAE reduces held-out decoder distortion by 10.6--11.4% across three paired runs while matching reconstruction NMSE. The same checkpoints pass an average natural-text output-KL noninferiority test, but one matched Pythia pair shows no improvement in probes restricted to a few sparse features. These results show that reconstruction quality does not determine which refitted linear readouts survive sparse compression, and that readout preservation is distinct from learning cleaner benchmark concepts or preserving every frozen-model behavior.

As scalability becomes increasingly important in recommendation modeling, recent architectures have advanced the modeling of two broad sources of ranking signals along separate paths: non-sequence features, including user, item, context, and cross features; and sequence features from user behavior histories. Wukong and HSTU have emerged as representative scalable backbones for these paths: Wukong scales high-order non-sequence feature-interaction modeling, while HSTU scales long user-behavior sequence modeling. Despite their complementary strengths, practical architectures that combine these two types of feature modeling remain underexplored. We present WHALE, a scalable unified recommendation architecture that jointly models non-sequence and sequence features on top of Wukong and HSTU. Each WHALE layer contains a Wukong module, an HSTU module, and an attention-based fusion module in which Wukong-derived interaction representations query HSTU-derived behavior representations. This design keeps both backbones active throughout the network and enables progressive Wukong-HSTU exchange, allowing high-order feature crosses to repeatedly retrieve fine-grained evidence from long user histories. To make WHALE practical for industrial deployment, we introduce customized Triton kernels and other model-systems co-design techniques to improve training and inference efficiency. On large-scale industrial recommendation data, WHALE achieves consistent gains in offline experiments. Additionally, it delivers positive online gains with a modest serving-throughput trade-off. The method has been deployed in production systems. Overall, WHALE provides a practical example of how these two sources of information can be scalably unified in an industrial recommendation model.

Today's data-centric applications demand cache architectures that can scale with growing workloads while maintaining high performance and energy efficiency. Fundamental issues such as excessive area consumption and leakage power are increasingly challenging traditional SRAM-based caches, thereby motivating the exploration of non-volatile alternatives. Among these, racetrack memory (RTM) stands out due to its remarkable storage density, achieved through nanowires hosting sequential magnetic domains that can be manipulated via domain wall or skyrmion techniques. Despite its advantages, racetrack memory's inherent serialized access introduces considerable shift overhead, leading to elevated energy consumption and latency. In this paper, we analyze the placement strategies in conventional RTM-based last-level caches and identify that current methods trigger redundant shift operations as a shift intended to read one block fails to preposition other blocks subsequently accessed. To resolve this, we introduce an innovative data placement and replacement scheme that intelligently groups correlated blocks, ensuring that a single shift not only retrieves the target block but also aligns subsequent blocks closer to the access port. Our simulation results using the gem5 simulator and the SPEC CPU2017 benchmarks reveal that our scheme reduces shift overhead by 49.0% and cache energy consumption by 35.9% with negligible performance impact. In addition, this scheme exhibits robust scalability to longer nanowire tracks for higher cache density.

Graph Neural Network (GNN) inference on billion-scale graphs is challenging due to the large memory footprint of features and embeddings and high disk I/O costs in out-of-core settings. Existing distributed GNN systems incur high communication times and infrastructure costs, while disk-based GNN systems are primarily tailored to training and experience massive wasted reads during inference on the entire graph. We present Taurus, a single-machine system for GNN inference on graphs that do not fit in RAM, supporting both exact full-graph inference and fanout-sampled inference. To avoid random and repeated feature gathers, Taurus reformulates layer-wise inference as source-centric broadcasts over sequential SSD scans, backed by a pipelined GPU-CPU-SSD hierarchy, topology-aware reordering, pending-message eviction, and a GPU-resident store for high-degree vertices. It further uses non-buffered sequential reads and GPU-backed writes to reduce page-cache pollution, host-memory pressure, and write overheads. On out-of-core graphs with up to $269M$ vertices, $4B$ edges, and $514$ GiB of features, Taurus outperforms the strongest layer-wise baseline, DGI, by $7$-$25\times$, and vertex-wise baselines by $40$-$140\times$.

Modern mobile applications predominantly execute concurrent Multimodal Large Language Models (MLLMs) to provide ubiquitous intelligence. However, satisfying this demand within edge environments faces significant challenges due to multi-task concurrency and strictly coupled hard constraints. To address these issues, we propose EdgeCoInfer, a framework enabling granularity-adaptive deployment by co-optimizing inter-model functional module sharing and intra-model fine-grained partitioning. We solve the underlying Mixed-Integer Non-Linear Programming (MINLP) problem via a Hybrid Evolutionary Hierarchical Reinforcement Learning (HE-HRL) paradigm, which synchronizes a Genetic Algorithm (GA) for discrete model placement with a Soft Actor-Critic (SAC) agent for continuous resource allocation. To navigate the sparse feasible region, we introduce a feasibility-guided constructive execution mechanism, integrating a constructive cut-step decoder with pre-act pruning and a two-phase curriculum strategy for stable adaptation. Experimental results demonstrate that EdgeCoInfer ensures a 100% task completion rate in high-concurrency scenarios, achieving a 76% reduction in system cost and 71.88% memory savings compared to state-of-the-art baselines.

Serverless multi-model LLM systems multiplex popularity-skewed model catalogs over shared GPU pools, yet typically schedule each request independently. Tool-using agents break this abstraction: a session repeatedly calls an LLM across short tool gaps, carries a long reusable KV prefix, and is judged by session completion time (SCT). Load-only routing can separate a continuation from both its model and KV state, while round-based model multiplexing can delay even a correctly placed continuation until the target model's next slot. Both failures are especially costly for hundred-billion-parameter models: their weights constrain residency, while long-context KV is expensive to reconstruct or move. We present Talaria, a session-aware serverless multi-model serving system that makes session continuity a joint placement-and-admission decision. Its router ranks placements by model residency, KV locality, and instance pressure, while soft reservations account for likely returns in the last serving instance's admission budget. Session-prefill (SP) admits budget-eligible continuations before the active model slot closes. An instance-local substrate keeps HBM addresses stable, preserves host-restorable KV, and stages weights across model switches. On a single TP=8 server, we replay 30 SWE-Bench model-sessions (960 calls) over three models, each with more than 100B total parameters. Against an otherwise identical round scheduler with SP, host-KV restoration, and D2D staging disabled, Talaria cuts p50 SCT from 1000 s to 189 s and p95 from 2296 s to 867 s, speedups of 5.3x and 2.6x.

Although mixture-of-experts, MoE, models have been increasingly adopted to scale large language models with moderate computation cost, it remains challenging to deploy MoE inference over resource-constrained and bandwidth-limited edge infrastructures. Existing distributed MoE serving methods mainly rely on exact expert placement, caching, replication, or communication scheduling, while overlooking the functional similarity among experts, which provides an opportunity to reduce cross-server token transmission. Therefore, this paper introduces a similarity-aware expert allocation and distributed deployment framework, dubbed OrderMoE, which aims to accelerate edge MoE inference while balancing inference latency, communication overhead, server workload, and inference quality. OrderMoE first constructs an expert similarity model based on router-induced logits representations and partitions experts in each MoE layer into multiple similarity groups. Then, it develops a similarity-aware expert grouping and deployment strategy to improve local similarity coverage across edge servers. Since reducing remote expert invocation and preserving exact inference quality are conflicting objectives, OrderMoE further designs a quality-aware and trajectory-aware runtime server-expert selection algorithm to decide whether a token should invoke its remote target expert or use a feasible local substitute expert. Experimental results on a real distributed edge testbed show that OrderMoE significantly reduces average latency, tail latency, cross-server traffic, and remote expert invocation ratio, while introducing only small and controllable inference quality degradation.

Single-stream autoregressive decoding of large language models is bound by memory bandwidth: each generated token requires one full forward pass through the target model, and successive passes cannot be parallelized. Speculative decoding restructures this computation: a small draft model proposes $K$ tokens autoregressively, the target model scores all of them in one batched pass, and a rejection-sampling rule provably preserves the target model's output distribution. We present a from-scratch, device-agnostic (CUDA/MPS/CPU) implementation and an empirical study across five draft/target backend configurations on a consumer Apple-silicon laptop. Distribution equivalence is verified at three levels, culminating in a two-sample test over roughly 9,200 real-model tokens per method ($χ^2 = 162.5$, dof $= 200$, $p = 0.976$) and exact greedy-sequence agreement. The best configuration reaches a measured $1.61\times$ wall-clock speedup at $K=6$, on an acceptance profile declining from 69.7% at $K=1$ to 37.8% at the optimum, while three of five configurations decelerate, either because the draft fails to out-speed a small target or because the quantized Metal backend executes "parallel" verification serially, an effect we isolate and quantify. The failures are as instructive as the successes: speculative decoding pays off only when verification is genuinely batch-parallel and the draft/target latency gap is real.

Linear attention promises constant-time recurrent inference but degrades sharply on associative recall. We formulate attention recall as a spherical-packing problem and introduce Kernelized Linear Attention Activations (KATA), a framework whose feature maps are derived from first principles by certifying nonnegative attention weights through a self-dual homogeneous cone. Building on this observation, we show that rank-one positive semi-definite (PSD) features offer a favorable capacity--interference tradeoff. KATA recovers a parameter-free convex output gate and characterizes associative capacity through the Welch interference floor. For tolerances above this floor, KATA enlarges the state without adding parameters and admits spherical codes with exponentially many keys in the projection dimension. We implement KATA as fused Triton kernels at two operating points: a flash-attention-style forward up to ${\sim}1.6\times$ FlashAttention-2 throughput, and an exact $O(T)$ chunked-state form that reaches ${\sim}11\times$ FlashAttention-2 forward throughput at $131$k tokens. An associative scan of the first-order feature lowers the inter-chunk recurrence depth to $O(\log(T/C))$ for chunk size $C$ and averages ${\sim}2.4\times$ the throughput of a matched sequential linear-attention baseline. On long-range MQAR and repeated-key overwrite, several KATA variants outperform Gated DeltaNet, with parameter counts and state sizes reported alongside accuracy. Induction preserves near-perfect recall, while kernel benchmarks show that the maps can be implemented efficiently. KATA retains $0.985$ MQAR at a $16\times$ out-of-distribution length, approaching the softmax with roughly one quarter of the KV-cache entries. Experiments on 340M-parameter LLMs reveal a feature-dependent fluency trade-off and clarify how positional embeddings, delta rules, and decay gates interact with feature geometry.

Long-horizon rollout generation has become the dominant systems bottleneck in agentic reinforcement learning (RL). As agents interact with environments over many turns, trajectories rapidly grow to tens of thousands of tokens, making synchronous RL training increasingly constrained by rollout. We propose WAR, a workload-aware rollout system that substantially accelerates synchronous agentic RL by jointly optimizing decoding and scheduling. WAR is built on a key observation: the optimal rollout optimization strategy depends on runtime load: (1) Under low load, WAR enables model-free speculative decoding with SuffixDecoding, which reuses suffix patterns from previously completed trajectories as speculative drafts for future rollouts. Unlike model-based drafters, SuffixDecoding introduces no additional draft model and avoids GPU contention with rollout generation. (2) Under high load, where saturated batched decoding leaves limited room for speculative speedup, WAR shifts the optimization focus to cache-aware scheduling. A global scheduler places requests across rollout replicas based on cache locality, trajectory progress and server load, reducing redundant KV-cache recomputation and mitigating load imbalance. By combining decoding-level suffix reuse with system-level rollout scheduling, WAR delivers robust throughput improvements across workload regimes without changing the underlying RL algorithm. WAR improves long-context agentic rollout throughput by 1.4x under low load and up to 1.6x under high load. These results show that WAR removes a major rollout bottleneck in synchronous agentic RL and provides a practical path toward scalable long-context agent training.

When does a committed intermediate stage in an LLM reasoning pipeline earn its cost? Constrained Path Reasoning (CPR) pairs a source-aware path hypothesis with stage-level accounting. Search generates provisional states; trusted or validated invariants can constrain hard, while other proposals remain soft and revisable. CPR predicts that task-compatible commitments can factor transitions, concentrate candidate mass, induce regularity, and expose feedback when their gains exceed propagated error and execution cost. The formalism covers discrete commitments and continuous flows and measures effective branching, endpoint concentration, and cost per usable output. Across 1,180 generated QCQPs and 40 engineered degenerate polynomial instances (2,140 endpoints), residual triage recovers 63.0% of repair-all's additional feasible yield with 17.7% of its attempts. Fixed-LLM accounting (270 unique calls shared across nested arms) finds usable yield of 41.1% direct, 90.0% after formalization and deterministic execution, 20.0% after one-shot convexification, and 21.1% for the full path. In 120 paired-condition calls, a two-action rollback rule reaches 90% usable yield versus 36.7% for the feedback-conditioned selector. Two endpoint probes separate source from validation: a 72-output cross-trajectory transplant reduces entropy and acceptable mass; a 24-output same-call self-proposal pilot gives unchanged two-repeat collision entropy, 25.0% versus 8.3% usable yield, and 1/8 deterministically confirmed endpoint checks. Model-generated states supply hypotheses; trusted execution earns constraint strength.

Efficient large language model (LLM) inference on edge platforms is limited not only by model size, but also by shape-dependent performance differences across execution backends. Static backend assignment cannot exploit this variation, while independent per-operator selection can introduce costly device and framework switches. This paper presents a transition-aware backend dispatch approach for edge transformer inference. The approach combines current operator features with the previously selected backend to preserve beneficial shape-specific choices while avoiding unnecessary transitions. Ordered traces are collected from full-model inference runs of seven transformer models, and four common operator classes are benchmarked across PyTorch eager CPU, PyTorch eager CUDA, and ONNX Runtime CPU on an NVIDIA Jetson platform. The dispatch policies are evaluated through measurement-backed trace replay using observed operator costs and transition costs measured from actual backend switches. Supported operators are selected dynamically, while operators outside the dispatch scope retain a static assignment. Across 9,584 ordered operator instances and 278 exact shape groups, transition-aware dispatch reduces replayed latency, energy, and energy-delay product relative to the best static policy by 17.4%, 14.4%, and 28.5% on average, respectively. It also reduces switching relative to operator-local selection. Leave-one-model-out evaluation improves all three objectives for six of seven held-out models and improves energy for all seven. These results demonstrate that incorporating operator shape and backend-transition context can improve selective backend dispatch for edge transformer workloads.

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved remote sensing (RS) multimodal understanding. Language-conditioned segmentation is crucial for fine-grained target understanding in Unmanned Aerial Vehicle (UAV) videos. However, this task remains challenging due to the prevalence of small, visually ambiguous targets and dynamic aerial perspectives. In this paper, we propose SkyVLaM, a multimodal large language model for UAV video understanding. SkyVLaM constructs sparse tokens directly from patch-level video representations through a temporal basis perceiver, regularizes the sparse basis to encourage complementary temporal cues, and adaptively selects a temporally coherent dense segment for high-resolution inspection. The resulting sparse and dense tokens are jointly processed by a large language model for query-conditioned segmentation. We further build SkyVid, consisting of SkyVid-VGCG and SkyVid-RVOS for video grounded conversation generation and referring video object segmentation, respectively. SkyVid contains 101 videos, 33.6K frames, and 1.53M pixel-level object instances. Experiments show that SkyVLaM provides a more effective allocation of the visual token budget and improves language-conditioned video segmentation in UAV scenarios.

We study the problem of sequentially evaluating a new large language model (LLM) on a fixed question set using historical performance data from prior LLMs. Our goal is to construct a confidence sequence (CS) for the model's capability on this question set and to design active querying rules that shrink the CS width as quickly as possible. For CS construction, we invert a family of test supermartingales and focus on two representative approaches: a reverse information projection (RIPr)-based approach and a testing-by-betting-based approach. We first study these approaches under an oracle setting, and demonstrate the oracle optimality of the RIPr-based construction. We then propose a growth-oriented querying rule that aims to maximize the worst-case one-step expected log-increment over the endpoints of the current CS. In practice, we build these test supermartingales and the querying rule on predictions of question-level correctness learned from historical data. We then analyze the shrinkage behavior of the resulting CSs and identify two key factors that slow the shrinkage rate of CSs: accumulated prediction mismatch and the spikiness of the querying distribution. Finally, motivated by this analysis, we propose several mixture querying rules that combine growth-oriented querying, prediction refinement, and uniform exploration, trying to mitigate the effects that slow the shrinkage rate. We provide experiments comparing different querying rules for the RIPr-based and testing-by-betting-based CSs across several synthetic testing datasets. Interestingly, we observe that the simplest querying rule, uniform sampling, can sometimes outperform more adaptive querying rules for both methods.

LLM constraint reasoners are often evaluated near the random-SAT phase transition, confounding density and solver hardness. We test instance-level transfer while near-matching clause density. At aligned size bins, with near-matched density and matched maximum clause width, we compare proof-hard expander-Tseitin and proof-easy ladder-Tseitin formulas, pigeonhole anchors, and density-mismatched controls. Theory separates their resolution hardness; a solver-specific Glucose mean-conflict proxy differs by up to $51\times$, and five other solvers preserve the direction. Across three included models (243 instances each; a fourth is excluded for abstention), the near-matched-density accuracy gaps range from $-32$ to $+20$ points, with a pooled gap of $+1.7$ points ($p=0.74$) and a wrong-signed correctness-versus-conflict association ($r=+0.15$). A proof-preserving relabeling lowers accuracy in all five clusters for one model (mean $-93$ points) but not another, exposing model-surface sensitivity. In a preregistered extension, provider-reported completion-token spend does not consistently increase with the proxy after accounting for formula length and censoring. At 16k, the reasoning model spends more on proof-easy matched formulas and exhausts its budget on the solver-easiest UNSAT family; the 32k C1 gap is absent. These scoped dissociations concern verdict accuracy and observed token spend, not certificate solving, exact proof length, or allocation efficiency.

Large language models confabulate chemical objects (molecular formulas, space groups, formation energies) in fluent reasoning traces, concentrated on long-tail entities where confidence is least trustworthy. Deterministic, database-grounded verification can catch and repair such errors without the coverage cost of blanket retrieval; the binding constraint, we find, is detection, not repair. Our tiered verifier extracts each checkable claim, checks it against authoritative databases and physics, and feeds the reference into a gated correction loop. Across four models and 528 condition-pinned prompts, gated correction cuts committed-formula error from 22% to 4% at $3.2\times$ fewer retrievals than blanket augmentation, beating a conversational oracle. Repair succeeds wherever a flag fires (80--97%); the bottleneck is in-loop detection recall. Grounding improves the final answer only when the verifier's scope reaches the deliverable (83% to 90%), and the lift appears only where extractable long-tail error exists: absent on near-ceiling physical constants, large on isotope half-lives (11% to 0%).

We present a continuous geometric framework that models the discrete algebraic operations of the Transformer architecture as an integro-differential equation (IDE) on a semantic fiber bundle $\calE = \calM \times \R^d$. Beginning from a single geometric axiom — that the token sequence forms a discrete $1$-manifold equipped with a canonical measure lattice — we translate every core component of the modern Transformer (RMSNorm, RoPE, Softmax Attention, FFN, Residual Stream, SGD, Weight Decay) into a cohesive vocabulary of differential geometry, measure theory, and stochastic calculus. The resulting framework yields quantitative predictions spanning entropic optimal transport (Attention as a Schrödinger bridge) and non-equilibrium thermodynamics (SGD as Itô diffusion violating detailed balance). We conduct a six-part experimental campaign across five architectures (Qwen3, LLaMA\nobreakdash-3.1, Gemma\nobreakdash-3, GPT-2, Mistral) spanning $124$M to $8$B parameters. The empirical observables are quantitatively consistent with the geometric predictions: the $ε^{-1/2}$ Lipschitz scaling calibration at machine precision ($R^2 = 1.000$), the Lie--Trotter operator-splitting torsion, the symmetric ablation instability confirming the Dual-Law of Topological Stability, the $\calO(1/\sqrt{k})$ thermodynamic suppression of Poincaré recurrence on the RoPE torus, the thermodynamic context-limit phase transition, and the Non-Equilibrium Steady State parameter vortex — verified across two optimizers (AdamW and Pure SGD) to exclude momentum artifacts. The results demonstrate that analyzing Transformers through the lens of continuous stochastic differential geometry provides a predictive descriptive vocabulary for the stability limits, context bounds, and optimization dynamics of Large Language Models.