每天知道
你的领域
出了什么

Coding agents do not simply execute instructions; the wording of those instructions changes how much work they perform, what kind of work they perform, and how much that work costs. We present a preregistered study across multiple reasoning models, two real coding-agent harnesses, and controlled software tasks with hidden evaluation. The main finding is that several common prompt habits create substantial extra work without improving success. Asking for multiple approaches causes agents to develop and discard several solution paths before implementing one. Telling them to think deeply mainly produces longer visible reasoning, while demanding maximum certainty encourages repeated checking, extra tests, additional turns, and longer execution. Misleading architectural hints can also push agents toward unsupported lines of investigation. By contrast, prompts that define scope, request the smallest sufficient change, and include a clear stopping rule preserve diagnosis and validation while avoiding unnecessary work. This shows that effective prompts are not merely shorter; they are better bounded. We further show that different kinds of waste propagate through different channels. Some remain mostly in reasoning, while others expand into tool use, latency, repeated testing, and context growth. The agent harness itself can matter even more than the prompt, because system instructions, turn structure, and tool policy strongly shape total cost. Overall, prompt design is an operational control over coding-agent behavior. Efficient agents require prompts that focus work, avoid unnecessary exploration, and stop once the task is complete.

Search-augmented large language model agents are increasingly capable of solving knowledge-intensive tasks, but their behavior when a multi-hop question is fundamentally unanswerable remains poorly understood. Existing abstention benchmarks largely expose defects at the surface of single-hop queries and therefore cannot reveal failures that emerge only after valid intermediate reasoning and retrieval. We introduce HopRefusalBench, the first controlled benchmark of refusal within multi-hop search, comprising 889 unanswerable questions constructed from KILT-grounded entity paths. It crosses three causes of unanswerability (answer unknown, false premise, and underspecified context) with root, middle, and terminal topologies, making premise verification, intermediate-bridge validation, and terminal stopping separately observable. We further propose a final-outcome taxonomy spanning target-aware refusal, pseudo-refusal, hallucinated completion, and search-budget exhaustion, together with source-aware trajectory metrics for post-trigger continuation and token waste. Across ten frontier proprietary and open-weight models in search-augmented mode, the best model achieves a target-aware correct halting rate (TCHR) of only 42.9%. Root and middle items are consistently harder than terminal items, and all models attain their highest TCHR on false premises and their lowest on underspecified questions. Yet when pooled across categories, 84.7--98.4% of each model's explicit refusal-like responses identify the correct rationale, localizing the main bottleneck to committing to an appropriate non-answer; failed trajectories instead diverge into hallucination or search-budget exhaustion. These results establish refusal in multi-hop search as a consequential evaluation problem and provide a foundation for diagnosing and improving the reliability of search-augmented agents.

The rapid dissemination of multimodal content has intensified the spread of fabricated news, presenting a substantial threat to social integrity. A formidable challenge for current detection systems is identifying misinformation related to novel events in zero-shot scenarios. Prevailing zero-shot methods typically assess news items in isolation via semantic matching, a strategy that fails to recognize the recycled disinformation tactics from past campaigns and lacks the sophisticated reasoning needed to identify subtle, cross-modal discrepancies. To surmount these deficiencies, we introduce MRAFnd, a novel \underline{M}ultimodal \underline{R}etrieval-\underline{A}ugmented Framework for Zero-Shot \underline{F}ake \underline{N}ews \underline{D}etection. MRAFnd emulates a collaborative team of analysts to verify news veracity. The framework initiates with Multimodal Similarity-based News Retrieval to assemble a corpus of contextually analogous articles from an unlabeled reference database. Subsequently, during the Bifurcated Evidential Reasoning stage, agents perform a dual-directional analysis to extract critical patterns from the retrieved evidence. Finally, a Multi-Agent Collaborative Debate, involving Analyst and Arbiter agents, engages in a structured discourse to arrive at a definitive and robust conclusion. Comprehensive experiments on three benchmark datasets reveal that MRAFnd markedly surpasses state-of-the-art baselines, achieving an accuracy gain of up to 2.35% on the demanding Weibo-21 dataset.

Large language model agents have shown strong capabilities in generating coherent and contextually appropriate responses, yet robust long-horizon dialogue remains limited by the lack of external memory that is traceable, updatable, and diagnostically transparent. Existing memory-augmented agents often store memories as isolated records or overwritable states, making it difficult to preserve how information originates, evolves, conflicts, or becomes obsolete over time. We propose TrajWiki, a trajectory-based memory framework for long-horizon conversational agents. Instead of treating memory as static entries, TrajWiki represents each memory as a source-grounded evolution trajectory, maintained through immutable episodic snapshots and claim-level operations such as ADD, REVISE, and DEPRECATE. To reduce fragmentation and retrieval cost, TrajWiki further introduces Memory Wiki, a persistent intermediate layer that incrementally compiles dialogue history into structured and interlinked wiki pages capturing salient entities, events, quantities, topics, and conflicts. At inference time, queries are routed hierarchically from relevant wiki pages to linked memory trajectories, then to corresponding snapshots and source messages for evidence-grounded answer synthesis. Experiments on LoCoMo and MedMT show that TrajWiki improves long-horizon dialogue performance across both open-source and closed-source LLM backbones, while providing greater interpretability and diagnostic visibility into memory evolution, retrieval failures, and answer generation.

Conversational investment advisors influence not only what users know, but also how they make subsequent decisions as market conditions evolve. Existing evaluations primarily assess response quality or observed outcomes, leaving the long-horizon pathway from advisor language to investor behavior difficult to audit. We introduce ShiJianBench, an offline framework for evaluating conversational investment advisors through matched investor trajectories under fixed historical market feedback. At its core is a multi-agent investor simulator with explicit evolving state variables, motive-driven deliberation, long-term memory, and dialogue-grounded updates. The simulator is calibrated against aggregate behavioral patterns from 7,199 real users, and advisor policies are evaluated using separate investor-side, service-side, and content-side metrics under a hard compliance gate. Experiments on Chinese fund-market traces from 2021 to 2026 identify a stable leading group of LLM advisors that combines substantially stronger personalized content with competitive investor-side trajectory outcomes. These results reveal a systematic distinction between producing a high-quality response and delivering an effective long-horizon intervention, motivating trajectory-aware evaluation of conversational advisors.

In social learning, agents learn not only from direct evidence but also through interactions with their peers. We investigate the role of imprecision in such interactions and ask whether it can improve the effectiveness of the collective learning process. To that end we propose a model of social learning where beliefs are equivalent to formulas in a propositional language, and where agents learn from each other by combining their beliefs according to a fusion operator. The latter is parametrised so as to allow for different levels of imprecision, where a more imprecise fusion operator tends to generates a more imprecise fused belief when the two combined beliefs differ. In this context we describe both difference equation models and agent-based simulations of social learning under a variety of conditions and with different initial biases. The results presented suggest that for populations with a strong initial bias towards incorrect beliefs some level of imprecision in fusion can improve learning accuracy across a range of learning conditions. Furthermore, such benefits of imprecision are consistent with a stability analysis of the fixed points of the proposed difference equation models.

Interaction between users and LLM agents is increasingly multimodal: conversations interleave text with images, and a later question may target either. Yet most agent memories are designed around text, and even the few that support multimodal conversations still fail on vision-related questions. We trace this failure to an assumption behind the similarity search they rely on: in the index space, a query lies close to the relevant evidence that answers it. In multimodal settings, two gaps break it. By the modality gap, a query lies closer to memory content of its own modality than to evidence in another, even in a trained joint embedding space. By the similarity-relevance gap, the content most similar to a query is often not the evidence that answers it, most acutely when a query carries both text and image and its evidence resembles neither part alone. We present V-Mem, a multimodal agentic memory system that routes retrieval by the modality of the query and that of the target evidence, both recognized from the query alone. To cross the modality gap, V-Mem organizes the conversation into rounds and returns the target-modality content from the same round as the match, without comparing across modalities. To close the similarity-relevance gap, it searches with an LLM-generated anchor that sits closer to the relevant evidence than the query does: a hypothetical caption for a text-only query seeking an image, and an enriched search anchor, the query text plus relevant keywords extracted from the query image, when the evidence is reachable only by combining the two. On Mem-Gallery, V-Mem reaches an LLM-judge score of 0.82 versus 0.56 for the second best, with the largest margin on questions carrying an image (0.87, no baseline above 0.47); on LoCoMo it scores 0.69 versus 0.58.

Generating long-form content from extensive internal reports remains challenging for organizations operating under strict privacy and security constraints, where proprietary cloud-based LLM APIs are often not viable. While locally deployed open-weight models offer a privacy-preserving alternative, existing retrieval-augmented generation (RAG) approaches on smaller models frequently lack effective global planning and accumulate factual inconsistencies over long outputs. To address these limitations, we present RH-RAG, a multi-agent framework for secure and trustworthy long form generation using local language models. RH-RAG decomposes generation into three coordinated stages: a Planner Agent that constructs a global document outline from high-level semantic summaries, a Writer Agent that incrementally generates coherent section-wise content using bounded coherence memory, and a Checker Agent that mitigates hallucinations through natural language inference-based factual verification and an attestation-driven revision loop. The framework further employs a dual-level retrieval index that supports efficient planning and fine-grained contextual generation on consumer-grade hardware. Evaluations across literary, financial, and legal domains demonstrate that RH-RAG consistently improves factual grounding, semantic coherence, and document-level alignment compared to standard and hierarchical RAG baselines, while achieving reliability competitive with proprietary cloud-based systems without compromising data privacy.

Lifelong LLM agents increasingly adapt through external learning states that store past interactions as retrievable memories or reusable skills, yet existing benchmarks rarely account for how the path of accumulated experience shapes what agents transfer and retain. In this work, we establish PATH-Bench, a benchmark for path-dependent evaluation of lifelong agents. PATH-Bench estimates directed task relationships via multi-model in-context learning, constructs probe-centered sequences with controlled helpful and interfering histories, and repeatedly evaluates probe tasks to measure average performance, forward transfer, backward transfer, and forgetting. We evaluate eight representative agents on single-turn code generation and multi-turn tool-use tasks under positive- and negative-dominant histories. Benchmark results show that experience utility depends jointly on how experience is represented and on the task's interaction structure, that strong transfer does not ensure retention, and that later experience can reshape gains acquired earlier in the learning path. Based on these findings, we propose Selective Experience Use (SEU), an agent harness that regulates how path-accumulated experience influences each new task, admitting helpful items while filtering out potential interference. SEU consistently reduces forgetting while improving forward transfer in the majority of settings. The PATH-Bench provides both a controlled evaluation framework and actionable guidance for designing more selective and robust lifelong agents.

Agents are increasingly expected to act not only as task executors, but also as decision-makers on behalf of human users. This shift requires agents to accumulate evidence over long horizons, interpret implicit user preferences, and compare multiple candidates under partial observations. In this work, we propose DunphyBench, a new benchmark for evaluating agents on long-horizon human-centered embodied decision-making, where the agent must navigate through multiple embodied housing environments and make decisions that align with multi-dimensional human preferences. Unlike standard embodied reasoning tasks that often focus on procedural planning or immediate goal completion, our setting requires agents to integrate multimodal, multi-source input into coherent knowledge that supports complex reasoning across long horizon. The evaluation results reveal that there is a substantial gap between current agents and human performance. Furthermore, our diagnosis of state-of-the-art VLM-driven agents reveals that memory management is one of the bottlenecks, where raw multimodal history introduces noise that hinders decision quality. Motivated by this finding, we design MeMento, a preference-conditioned multimodal memory compressor that selectively compresses decision-relevant information from long-horizon history based on user preferences with a fixed set of memory tokens. Experiments show that MeMento helps VLM-driven agents improve accuracy by 7.18%, while reducing memory usage by 85.38% compared to the strongest baseline.

The emergence of Agentic AI systems, characterized by autonomous reasoning, multi-agent collaboration, tool orchestration, adaptive decision-making, and persistent memory, represents a fundamental shift from traditional AI pipelines to dynamic software ecosystems. While AI Technical Debt (AITD) has been widely studied in machine learning and software engineering, existing models assume static, component-level architectures and fail to capture the dynamic and emergent behaviors of agentic environments. To address this gap, this paper introduces Agentic Technical Debt (AgTD), defined as technical debt that emerges, accumulates, propagates, and amplifies due to the autonomous and collaborative nature of Agentic AI systems. Building on our prior systematic scoping review of 31 AITDs across seven root-cause categories, we employ a theory-informed transformation methodology to reinterpret these debts in Agentic AI through direct transformation, contextual transformation, and manifestation expansion. We present the first systematic mapping of established AITDs to their agentic manifestations, showing how conventional debts evolve into system-level liabilities, including memory inconsistencies, orchestration fragility, cascading failures, and unsafe autonomous decision-making. Our findings show that technical debt extends beyond software artifacts to encompass agent behaviors, coordination mechanisms, and interactions among agents, tools, and execution environments. We further examine its implications for AI Trust, Risk, and Security Management (AI TRiSM), highlighting impacts on trustworthiness, governance, security, operational resilience, and Sustainability Technical Debt. Overall, this work establishes AgTD as a foundational software engineering construct and provides a transformation framework, taxonomy, and research agenda for managing technical debt in autonomous multi-agent AI systems.

Multi-agent debate commonly exchanges complete rationales even when disagreements concern only a few intermediate claims. We introduce Localized Multi-Agent Debate (LMAD), an inference-time protocol that represents agent rationales as nodes, locates their earliest conflict, and restricts debate to the corresponding local segments. Guarded resolution extends a shared committed state so that later conflicts can be addressed without reopening accepted steps. We evaluate LMAD on four multi-hop question-answering benchmarks using ten backbones from four model families. Our method achieves the highest macro-averaged judge accuracy across all ten backbones, outperforming the strongest conventional baseline by up to 7.20 percentage points.

Large language models (LLMs) are integral to complex intellectual tasks, yet output quality remains constrained by user-provided prompts. Iterative multi-turn prompting often leads to context degradation and diminishing cognitive returns. We present PAWNI (Prompt Architecture Wizard using Neural Intelligence), an agentic conversational interface of eight agents that transforms unstructured queries into structured prompts through guided question-and-answer dialogue informed by a self-evolving knowledge base. Rather than optimising the model's response, PAWNI optimises the question itself by front-loading intent clarification. We also propose a three-tier framework of 18 prompt elements across Essential, Enhancement, and Elevation categories. To evaluate system behaviour and validate a measurement protocol, we conducted an exploratory within-subjects study (N=4) across four complex tasks, integrating 32-channel EEG, NASA-TLX workload, and behavioural metrics. Participants produced more structurally complete prompts with PAWNI (42% to 91% of assessed elements), rated LLM outputs higher across all quality dimensions, and reported lower workload (39.6 vs. 21.7 NASA-TLX). Every participant reached satisfactory output in a single turn, compared to 1-12 turns unaided. While effect sizes are unstable due to sample size, direction consistency supports the hypothesis that optimising prompt formulation front-end is a critical lever for human-AI collaboration.

Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely constrained by high computational latency and exposure bias arising from sequential autoregressive decoding. Conversely, while specialized diffusion policies enable low-latency, parallel execution, training them from scratch typically yields narrow, single-task architectures that lack holistic visual-linguistic reasoning. Successfully transforming pre-trained autoregressive generalists into parallel diffusion models could combine multi-task cognitive intelligence with execution efficiency, yet this transition presents a formidable architectural challenge due to mismatched attention patterns (causal versus bidirectional) and divergent optimization objectives. To bridge this divide, we introduce WAM-Diff2, a multi-task discrete diffusion VLA framework powered by a three-stage hierarchical distillation strategy. By structuring the architectural shift through progressive block-wise adaptation, block-wise distillation, and model-wise cross-scale distillation, WAM-Diff2 preserves the underlying semantic foundations of the base model while accelerating inference. Extensive evaluations across driving understanding, perception, and planning benchmarks demonstrate that WAM-Diff2 effectively mitigates exposure bias and achieves performance parity with autoregressive baselines. Crucially, the autoregressive-to-diffusion transition yields a 2.8x decoding speedup, which scales to an ultimate 15.1x acceleration when combined with system-level optimizations including FlashInfer and CUDA Graphs.

Conformal prediction (CP) is a distribution-free framework for uncertainty quantification that has recently been adapted to large language models (LLMs), providing prediction sets with finite-sample coverage guarantees under exchangeability. Yet for LLMs, nonconformity scores are often induced by an inference pipeline, not just a fixed model, making them depend not only on the data distribution but also on configurable factors such as the prompt template, decoding parameters, and deployment setting. Since such configurations are routinely modified in practice but rarely treated as a source of shift, their impact on CP validity remains poorly understood. We call this configuration shift and study it systematically along three axes: prompt template, decoding temperature, and weight quantization. In a broad empirical study spanning $9$ LLMs, $4$ datasets, and $4$ nonconformity scores, we find that configuration shift consistently erodes CP validity, often driving empirical coverage below the target. By contrast, efficiency is largely preserved: valid prediction sets remain close in size to the i.i.d. baseline. We derive coverage lower bounds that attribute this loss to a discrepancy between calibration and test score distributions, and use their finite-sample plug-in versions as empirical diagnostics of shift severity. We further show that these findings lead to practical mitigations: bound-inspired recalibration is effective with limited test examples, while fragility-aware calibration ensembling recovers much of the lost coverage without test data.

Long-term memory is essential for LVLM agents to maintain consistency and integrate information across extended multimodal interactions. Existing agent memory systems, however, often reduce visual experiences into textual summaries or rely on static retrieve-then-reason pipelines, which are inefficient at query time and brittle when questions require image-text binding, temporal updates, or visual details. We propose Prospective Multimodal Memory Compilation, a framework that shifts part of the memory reasoning process from query time to memory consolidation time. Given accumulated multimodal interactions, a Questioner predicts future question candidates, a Planner compiles question-conditioned multimodal memory programs, and a Doubter verifies whether the planned evidence path can support the predicted answer. The verified question-program pairs form a structured question bank for efficient query-time routing and evidence retrieval. Experiments on multimodal long-term memory benchmarks show that our method improves answer quality and visual evidence recall while reducing query-time token and latency costs. Extensive ablations analyze the effects of self-feedback, dynamic planning, raw-image access, and question bank coverage.

Large vision--language models (VLMs) can reason step by step about complex visual scenes, but this open-ended, autoregressive chain-of-thought (CoT) approach is poorly suited to safety-critical, rule-governed settings such as industrial surveillance, where decisions must be bounded, deterministic, and low-latency. Because CoT inference cost scales jointly with reasoning length and the number of concurrent streams, it creates a throughput bottleneck that precludes the real-time, multistream monitoring required for industrial accountability. Here we present MonitorVLM-v2, a deployment-oriented framework that recasts VLM-based safety assessment as probabilistic inference over a finite regulatory decision space, compressing multimodal reasoning into single-step rule-ID predictions and reducing decoding from a variable-length sequence to a single token. We introduce symbolic policy optimization (SymPO), a novel contrastive policy optimization algorithm that sharpens decision boundaries within this finite symbolic space, together with an entropy-driven triage mechanism that routes uncertain predictions to human reviewers for expert confirmation. In a four-month prospective deployment across 10 concurrent camera feeds in an operational underground mining facility, MonitorVLM-v2 achieved a 19.45-fold increase in inference speed and identified 2.78 times as many confirmed violations as the site's routine manual inspection workflow, demonstrating the practical value of compressed symbolic decision-making for real-time, auditable industrial monitoring.

Embedded Language Flows (ELF) rely primarily on full non-causal attention for iterative denoising, repeatedly incurring quadratic sequence-mixing cost at each sampling step. Gated Delta Networks (GDNs) provide an efficient recurrent alternative, but their standard causal formulation cannot directly capture the bidirectional context required by ELF. We introduce DeltaFlow, a noise-adaptive bidirectional GDN backbone for continuous language denoising. We study two variants: DeltaFlow-A, which alternates scan directions across layers, and DeltaFlow-P, which performs parallel forward and backward scans within each layer. We further introduce noise-adaptive memory control and scheduled Temporal State Consistency (TSC) to stabilize hidden representations across nearby noise levels. On OpenWebText, using a 32-step stochastic differential equation sampler, DeltaFlow-P reduces generated perplexity from 24.218 for the full-attention ELF baseline to 21.228 while maintaining comparable unigram entropy, with 36B training-token exposure compared with 45B for the baseline. In a denoiser-only benchmark, DeltaFlow-P achieves a 2.72x throughput speedup over the full-attention baseline at a sequence length of 16k. These results show that DeltaFlow is a promising alternative to dense attention for efficient continuous language denoising.

The continued development of LLMs toward persistent and adaptive intelligence increasingly requires long-term memory mechanisms that preserve and reuse information across interactions. Existing memory systems either compress and structure histories for efficient access or perform deep research over broader trajectories. The former lowers online cost but may omit temporal, causal, or cross-step dependencies, while the latter improves evidence coverage at substantial latency and inference cost. This raises a key question: can a memory system achieve strong answer quality while maintaining low online latency? We introduce Router-Mem, an evidence-conditioned progressive execution framework for long-horizon agent memory. Router-Mem first applies a shared low-cost retrieval prefix to obtain evidence. A lightweight sufficiency router then predicts whether the context supports early termination, which enable a single-token decision at inference time. It is trained with evidence-level supervision and rationale-conditioned representation distillation. When evidence is insufficient, Router-Mem reuses retrieval hits to expand memory blocks and perform deeper analysis and aggregation. Experiments on AMA-Bench and BEAM show that Router-Mem achieves 55.17% and 38.77% score while reducing average inference time by 27.3% and 25.5% compared with full memory execution.

Reliable decision-support in digital agriculture requires accurate predictions and well-calibrated uncertainty estimates, particularly for dense prediction tasks such as semantic segmentation. Ensemble methods provide strong uncertainty quantification, but their computational and memory demands limit practical use, while single-model approximations often trade off uncertainty quality for efficiency. We propose ST-LoRA, a parameter-efficient ensemble framework that builds diverse ensemble members from a single training trajectory by combining Low-Rank Adaptation (LoRA) with snapshot ensembling. Each member shares a frozen pretrained backbone and differs only in lightweight low-rank adapters, reducing trainable parameters to under 10% of the full model while preserving ensemble diversity. We evaluate across two agricultural datasets - GrowliFlower-L (cauliflower, open field) and BUP20 (sweet pepper, glasshouse) - using SegFormer and Mask2Former, covering in-distribution performance, calibration under distribution shift, and out-of-distribution detection. Ablations show feed-forward layers, not attention layers, are the critical LoRA target for dense prediction, contrary to the attention-only convention from language models. ST-LoRA matches or exceeds full-rank ensembles in segmentation accuracy and calibration across both datasets and architectures, while substantially reducing training time, inference latency, memory footprint, and storage requirements. Against efficient baselines - Snapshot Ensemble, MC Dropout, and Deep Deterministic Uncertainty - ST-LoRA consistently matches or outperforms them in image/pixel-level OoD detection, calibration stability under shift, and cross-seed variance, with far fewer parameters and lower compute. These results show LoRA-efficient ensemble adaptation is a highly effective, practical approach for uncertainty-aware agricultural vision systems.

Constructing photorealistic Free-Viewpoint Videos (FVVs) of dynamic scenes from a set of posed 2D images has been an intriguing yet challenging task in computer vision. Methods based on neural rendering achieve high-fidelity image quality in FVV construction. However, most of these methods are unable to achieve real-time rendering and often require complete video sequences to train. Despite the existence of some online training methods capable of rendering FVVs in real time, they struggle to meet the requirements for storage and training time for downstream applications. To overcome this problem, we propose Struct-GStream, which can achieve efficient FVV streaming using structured 3D Gaussians (3DGs). Specifically, we introduce dynamic anchor points to generate structured 3DGs to construct basic scenes and model approximate scene movements based on the assumption of local rigidity in object motion. Besides, we introduce a global free 3DGs patching strategy involving free 3DGs' generation, pruning, and optimization to patch and model deficient areas and emerging objects. Our method achieves fast training at low bitrates while maintaining high rendering quality. Extensive experiments demonstrate that Struct-GStream significantly outperforms existing online training methods for FVV construction in terms of training time, storage, and rendering quality while maintaining competitive rendering speed.

Vector symbolic architectures (VSA) are widely used for reasoning in neuro-symbolic (NeSy) AI, yet high-dimensional codebooks often create severe memory bottlenecks that limit scalability and deployment. In this paper, we propose Gram-Space, a compression framework that applies Gram-Schmidt orthogonalization to represent codebook vectors in a compact orthonormal coordinate system. Gram-Space preserves the dot-product structure required by matrix-based VSA operators, which supports numerically equivalent execution of matrix similarity, probability vectorization, and attention score computations. We provide a correctness analysis showing that inner products are preserved under the orthonormal basis representation. Using modern GPU hardware, we benchmark the Gram-Space framework on standard neuro-symbolic reasoning datasets. Experimental evaluations across state-of-the-art VSA models show that Gram-Space reduces model-level GPU memory usage by up to 15.75x and improves inference latency by up to 3.62x. Profiling results further indicate that Gram-Space reduces allocation-heavy overhead in codebook-associated stages and improves hardware utilization for NeSy workloads.

The emergence of transformer-based deep learning models has brought unprecedented performance across various domains, particularly in natural language processing and computer vision. However, deploying these models, especially on resource-constrained devices, poses significant challenges due to their high computational complexity and large memory size and bandwidth requirements. This complexity has led researchers to use low-bit model weights to reduce memory usage and improve efficiency. In addition to reducing processing and memory demands, quantization introduces another useful property: value locality, where the extremely large number of parameters are restricted to a limited range of values. To fully take advantage of this locality, this paper presents DeVIT, an acceleration method for vision transformers that leverages differential computation to enable multiplier-less matrix multiplication.

Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial reasoning for tasks such as 3D question answering. However, this design generates thousands of tokens per scene, resulting in substantial computational and memory overhead. While token compression has been extensively studied in 2D VLMs, existing approaches rely on semantic relevance or attention-based selection that overlook the structured spatial nature of 3D tokens. Moreover, redundancy in 3D representations cannot be resolved by spatial proximity alone, as object-level token imbalance persists even after spatial aggregation. To address this, we propose 3DZip, a three-stage token compression framework that first applies coarse voxelization to remove point-level redundancy, then selects anchor tokens based on feature-space diversity via a Determinantal Point Process, and finally merges remaining tokens under spatial constraints to preserve geometric coherence. Experiments on three 3D question answering benchmarks demonstrate that 3DZip consistently outperforms existing compression methods, retaining 94.7% of the original performance with only 128 tokens, achieving a $1.92\times$ faster inference speed.

Video large language models (Video-LLMs) represent videos as dense sequences of visual tokens, whose length grows with the temporal and spatial extent of the input. These tokens often contain substantial redundancy arising from repeated visual patterns, leading to unnecessary computation in the subsequent language-model processing. Existing token compression methods, including pruning and merging, perform compression online during inference, repeatedly incurring additional computation for each input video and often relying on model-specific designs that limit their generality, we instead rethink this paradigm by shifting the costly compression process offline. We propose ONCE, a plug-in video token compression framework that introduces an offline-to-online paradigm: a frequency-aware global codebook is learned once in the visual feature space and reused for lightweight online compression through codebook lookup and aggregation, reducing repeated per-video computation and the need for model-specific compression designs. Extensive experiments across multiple video understanding benchmarks and against diverse compression baselines demonstrate that our approach achieves a strong accuracy-efficiency trade-off, maintaining competitive performance while achieving the lowest inference latency among compared methods.

Streaming VideoLLMs process frames causally while visual tokens grow continuously, making compression essential for controlling prefilling latency and memory. Existing training-free methods independently rank tokens, ignoring marginal-gain interactions among retained tokens. We argue that streaming video token compression should instead be formulated as set selection, where each candidate is valued by what it adds beyond the tokens already retained. Unlike existing set-wise methods designed for offline tasks, streaming makes causal, frame-by-frame pruning decisions, so modeling cross-frame interactions requires an explicit historical reference. This creates a reference-set dilemma: the reference must adequately represent previously conveyed content while remaining bounded for real-time inference. We introduce NovaCov, to our knowledge the first training-free, plug-and-play set-wise token compressor designed for streaming video. NovaCov maintains a capacity-bounded, recency-weighted Historical Reference Bank and optimizes a dual-branch submodular coverage objective that preserves representative current-frame content while prioritizing information insufficiently covered by history. Both branches are facility-location functions, so greedy selection retains the classical (1-1/e) approximation guarantee. Across streaming and offline benchmarks, NovaCov outperforms existing training-free compression methods, retaining 99.6% of ReKV accuracy while reducing LLM prefilling latency by 46%.

LLM agents accumulate long trajectories of reasoning steps, tool calls, and environment feedback, making the KV cache a major inference bottleneck. KV cache compaction can reduce this cost, but most prior methods assume a static context where future queries are known or can be approximated offline. Agents instead require online compaction: new information must be compressed before future relevance is known, using proxy queries cheap enough for the inference path. We study online compaction across token eviction (TE) and attention matching (AM), adapting both to compact agent turns and comparing cheap proxy sources such as boundary, repeat-prefill, and delayed future-generation queries. Experiments on BrowseComp-Plus and WideSearch show that immediate compaction often hurts performance, whereas delaying compaction to use the agent's future queries recovers much of the gap. Moreover, TE is often more robust than AM under imperfect proxies. Across models at different scales, TE preserves most of the accuracy while reducing KV cache by 80%, and can improve throughput over the no compaction baseline. These results position proxy-query selection as a core design choice for practical online KV compaction.

Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets. Existing methods primarily improve which original KV pairs are retained. We introduce RestoreKV, which complements this selection-based formulation with learned restoration under the same total KV budget. Our key insight is that, although the information lost through eviction is context-specific, the mechanism for generating its compact complement can be shared across contexts. After context prefill, a few restore tokens attend to the full KV cache in a single LoRA-adapted pass, generating a compact, context-conditioned restore cache. The base importance scorer and eviction rule remain unchanged, and the adapters are disabled for all subsequent queries and decoding. RestoreKV is trained through parameter-efficient self-distillation from the frozen full-cache model, optimizing only $0.4%$ of the parameters and requiring no task-specific tuning. Across four backbones and four long-context benchmarks, RestoreKV substantially reduces compression-induced degradation. On Qwen3-4B, it improves 59 of 60 paired, budget-matched settings across five base eviction methods; at a $5%$ budget, it raises KVzip from $38.2$ to $73.2$ on RULER-4K. Applied to KVzip+, RestoreKV reaches $86.4$ RULER accuracy at $16\times$ compression on the KVPress Benchmark, while adding less than $0.5%$ one-time cache-construction overhead in a 32K-context evaluation. Our project page is available at https://paper.pnu-cvsp.com/RestoreKV/

We introduce OptGear, a foundation model designed for efficient on-device deployment, real-tim inference, and strong task capability. It includes a dense model (1M, 270M, and 1B) with a context length of 64K. We designed a new hybrid architecture that combines a convolutional key-value gated mixer with local-global attention to reduce the KV-cache memory that tends to increase exponentially with long context. This architecture delivers up to X4.9 faster prefill and decoding speeds on the NPUs compared to models of a similar scale models. From a 2T tokens candidate corpus, OptGear is trained on a curated 0.5T tokens subset without knowledge distillation. This is the most data-efficient of the existing foundation models. All models are released with open weights and deployment binaries for ONNX, Qualcomm NPU, and Apple ANE making OptGear a practical base for edge applications that need fast, memory-efficient inference and strong task capabilities. Furthermore, to expand the ecosystem of on-device generative language models, we are introducing the OptGear-1M that can be deployed on Micro-Controller Units (MCUs), a Tiny Language Model (TLM). OptGear-1M is the first generative language model to achieve 20 TPS with W4A32 quantization on the ARM Cortex-M7 CPU of the STM32H747I-DISCO.

The widespread adoption of generative AI enables students to outsource cognitive effort to increasingly capable assistants, creating an illusion of competence while undermining the independent reasoning that education aims to cultivate. We investigate whether adversarial machine learning can be repurposed to protect educational exercises against such corrosive reliance. Our approach uses multimodal multiple-choice questions whose visual components can be protected with subtle visual perturbations that steer AI solvers toward designated incorrect answers. These responses form a statistical fingerprint: students who blindly copy a solver reproduce the induced answer pattern more frequently than genuine students. We study the feasibility of this paradigm under realistic black-box assistant assumptions using three of the most common state-of-the-art multimodal language models: Anthropic's Claude, Google's Gemini, and OpenAI's ChatGPT. By using accessible surrogate models, we optimize adversarial perturbations that induce consistent response patterns. Those patterns enable principled detection through statistical hypothesis testing. These findings establish both the promise and the limitations of fighting machine-assisted reasoning with the vulnerabilities of the machines themselves.