Searcharxiv⌕ Search

arXiv subjects

Bingzhe Li

Publications and source records attributed to Bingzhe Li.

At least 19 recordsLinked to original sources

MatrixSplat: Matrix-Parallel and Feature-Scalable 3D Gaussian Splatting Rendering on GPUs

3D Gaussian Splatting (3DGS) has emerged as a mainstream representation for real-time novel view synthesis and 3D reconstruction. However, existing 3DGS rendering pipelines are poorly aligned with modern GPU architectures: depth-sorted alpha compositing introduces strong per-pixel sequential dependencies, limiting parallelism and resulting in scalar FMA-dominated execution that underutilizes high-throughput matrix units such as Tensor Cores. This mismatch becomes more severe for multimodal and semantically enriched 3DGS, where high-dimensional features must be accumulated from millions of Gaussians, leading to rapidly increasing computation and memory costs. We propose MatrixSplat, a matrix-parallel rendering framework for feature-scalable 3DGS on modern GPUs. We first identify the sequential dependency of alpha compositing as a key obstacle to efficient high-dimensional feature rendering, and adopt an order-independent weighted accumulation formulation that transforms feature rendering into matrix-oriented computation. Our framework features three key designs: (i) a tile-based splatting pipeline that maps feature accumulation to warp-level matrix-multiply-accumulate execution on Tensor Cores; (ii) a warp-granularity Gaussian packing strategy that mitigates visibility irregularity and improves feature reuse; and (iii) a lazy channel-batched feature-fetching pipeline that reduces shared-memory pressure, maintains high warp occupancy, and overlaps memory access with matrix execution for high-dimensional features. On Mip-NeRF 360, LERF, and 3D-OVS, MatrixSplat achieves up to 3.8$\times$ speedup over 3DGS and 2$\times$ over TC-GS while maintaining rendering quality and semantic accuracy, and further reduces render-kernel time by up to 36.7$\times$ for high-dimensional features. Integrated into existing fast renderers, it provides an additional 1.69-2.84$\times$ speedup.

cs.CV↗

LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models

Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require, wasting compute, latency, and context budgets. While introducing length-based efficiency rewards during reinforcement learning offers a natural remedy, existing methods struggle with two fundamental challenges: the optimal balance between correctness and efficiency is non-stationary throughout training, and intrinsic reasoning budgets vary drastically across problems. Relying on static reward weights and global length constraints inevitably forces a compromise between degraded accuracy and unrealized compression. To overcome these limitations, we propose LEAD (Length-Efficient Adaptive and Dynamic reasoning), a method that replaces static heuristics with online, self-adaptive mechanisms. LEAD dynamically calibrates the correctness--efficiency trade-off at each step using a Potential-Scaled Instability, directing optimization capacity to the most informative learning signal. Furthermore, it estimates an adaptive per-problem target length online based on the model's own correct rollouts, applying a symmetric efficiency reward that penalizes both overthinking and over-compression. Evaluated on five mathematical reasoning benchmarks, LEAD achieves the highest accuracy and Accuracy-Efficiency Score among RL-trained efficient-reasoning methods in our matched comparisons while producing substantially shorter outputs than the base model.

cs.LG↗

DeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers

Retrieval-augmented generation (RAG) lets a large language model (LLM) answer questions by retrieving relevant passages from a large corpus. However, RAG struggles with multi-hop questions, which require chaining facts spread across several documents through intermediate entities that the question never mentions. Graph-based RAG methods retrieve once from the entities a question names and so rarely recover the full evidence chain. Iterative RAG methods recover it step by step, but their accuracy is limited by the many tasks they ask the LLM to perform, such as planning the sub-questions, deciding their dependencies, rewriting them as answers arrive, and keeping track of what is known. We propose DeFT-RAG, a RAG framework built on three components. First, DeFT-RAG generates one self-contained sub-question at a time from the original question and the sub-questions answered so far with their answers (QA pairs). Each sub-question names every entity it asks about, which removes the need to plan, track dependencies or rewrite, and lets the LLM focus on a single fine-grained task at a time. Second, DeFT-RAG moves the remaining LLM work outside the LLM: rule-based updates to a QA table that keeps track of what is known, and yes/no decisions made by a fine-tuned lightweight decision model. Third, DeFT-RAG caches the QA pairs and reuses an answer when a later question asks a sub-question with the same meaning. On MuSiQue, 2WikiMultiHopQA and HotpotQA, DeFT-RAG achieves the best accuracy among thirteen baselines with both gpt-4o-mini and Qwen3.6 as the backbone, while giving the LLM fewer input tokens than any other iterative method. With a QA cache shared across 1,000 MuSiQue questions, 23.1% of sub-questions are answered from the cache, which reduces LLM calls by 12.9% without lowering accuracy.

cs.CL↗

ClunoGS: Compact Language 3D Gaussian Splatting via Unified Optimization

Language 3D Gaussian Splatting enables open-vocabulary scene understanding by associating Gaussian primitives with language features. These semantic attributes increase model storage, while most existing 3DGS compression methods are designed mainly to preserve RGB rendering quality. One straightforward approach is to apply sparsification and quantization sequentially. However, pruning based only on rendering quality can remove Gaussians that have small RGB contributions but are important for semantic prediction. Once removed, their semantic information cannot be recovered by later quantization. We propose ClunoGS, a compact framework for Language 3DGS that combines semantics-aware Gaussian sparsification and vector quantization in a unified constrained objective. Semantic supervision is used during sparsification, and the objective jointly considers rendering quality, semantic accuracy, and compactness. We optimize the unified objective with alternating primal, sparsification, quantization, and dual updates. We evaluate ClunoGS on open-vocabulary localization and segmentation using the LERF and ScanNet-10 benchmarks. Under aggressive compression, our unified, semantics-aware formulation substantially alleviates the degradation of semantic representations caused by sequential compression and semantics-agnostic Gaussian sparsification. Ablations further show that jointly coordinating sparsification and quantization better preserves semantic accuracy than applying them independently.

cs.CV↗

SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval

Large language model (LLM) agents increasingly rely on persistent memory to support long-term reasoning and personalized interactions. However, information collected from external sources can introduce security risks when untrusted claims (i.e., atomic statements) are later treated as authorized preferences, policies, or permissions. Existing defenses typically rely on content-based filtering or coarse-grained provenance tracking, which either fail to prevent unauthorized memory use or block legitimate information, sacrificing memory utility. To address these limitations, we propose SAFE-Mem, a fine-grained memory governance framework that improves security while preserving legitimate memory use. First, SAFE-Mem annotates each claim with three governance labels (i.e., kind, authority, and scope) to capture its provenance and permitted use. Second, governance-aware retrieval matches query requirements with claim permissions to block unauthorized influence while retaining legitimate information. Third, a governance-enabled memory graph connects source sentences, claims, and entities to support provenance tracking and efficient retrieval. Across four LLM backbones on MPBench and LoCoMo, SAFE-Mem attains the lowest attack success among defenses that retain legitimate memory, at least 77% below the strongest of them, and the highest answer accuracy of all evaluated defenses, improving it by up to 15 points. The code is available at https://github.com/LVenum/SAFE-Mem.

cs.CR↗

CUA-Recovery: Benchmarking Error Recovery in Long-Horizon Computer-Use Agents

As computer-use agents (CUAs) move to long-horizon workflows spanning multiple applications, undetected errors can silently corrupt persistent state and cause cascading failures in subsequent actions. Reliable error detection and recovery have become critical bottlenecks for building robust CUAs. However, existing benchmarks focus primarily on end-to-end task performance, providing limited insight into whether agents can detect and recover from errors during execution. The few benchmarks that evaluate recovery rely largely on manually injected errors, which may not reflect the types or horizons of failures induced by real agent policies. We introduce CUA-Recovery, a benchmark comprising test and training suites across multiple desktop applications. We construct it using ReRail, a framework for synthesizing long-horizon tasks and trajectories in a persistent desktop environment. ReRail composes MyPCBench tasks into new long-horizon workflows with executable ground truth, collects verifier-confirmed failures from multiple policies, and turns them into verified recovery trajectories. CUA-Recovery comprises a human-verified test suite of 2,250 erroneous states over 100 tasks and a training suite of 8.6K trajectories over 377 tasks. Evaluation on the test suite shows that agents struggle both to recognize inherited errors and to complete the task. Across six agents and six takeover depths, Error Awareness Rate (EAR) reaches at most 44.0% and Pass@3 at most 25.5%. After fine-tuning Qwen3.5-35B-A3B on the training suite, its average EAR rises from 19.9% to 35.2% on held-out recovery states, and its Rubric Score goes from 5.0% to 16.1%. It also gains 15.3 points on MyPCBench and 10.8 points on Odysseys for Pass@3, showing that the training trajectories help both with recovery and with completing tasks from a clean start. Our code is available at https://github.com/xu-hu-2002/CUA-Recovery.

cs.AI↗

PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas

Computer-use agents (CUAs) are commonly evaluated against fixed task specifications, but users may omit requirements, add constraints, or require approval before consequential actions. Completing the benchmark instruction does not guarantee serving the person who asked. We introduce PersonaCUABench, which holds 74 tasks across 11 domains fixed and varies only who asks. A persona agent, playing one of 44 personas in four groups, rewrites each instruction in that user's own words and answers the CUA's questions, while the CUA sees only the dialogue, never the profile or the original instruction. Across nine backbones (3,330 runs), mean task completion falls by 36% relative to the original requests. The losses have two sources: in 59.9% of cells that lose points, the agent engages with what the user asked for and still gets it wrong, and 11.2% are stops the user requested that the checker scores as failures. Even when a persona request is fully completed, the user gives the top satisfaction rating in only 62.7% of cells, against 84.1% for the original requests. CUAs should therefore be evaluated not only on task completion but also on whether they meet the requirements and constraints users express. Code: https://github.com/MatrAIx-ai/PersonaCUABench. Project page: https://matraix.ai/research/persona-cua.html

cs.HC↗

Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance

Multi-agent systems (MAS) built from large language models coordinate specialized agents to tackle complex tasks, but effective workflows are difficult to design in advance. Test-time evolution refines workflows using execution feedback, yet broad revisions can disturb useful components, while re-executing unchanged requests can incur redundant computation. Inspired by the interplay of inheritance and selection in biological evolution, we introduce Inherit-MAS, which makes inheritance explicit at the workflow and execution levels. A meta-model first synthesizes a workflow of worker agents with declared roles, communication inputs, and tool permissions, and a separately prompted judge scores each executed candidate and diagnoses its deficiencies. In ordinary refinement rounds, \emph{workflow inheritance} starts from the latest completed candidate, may discard removable nodes judged unhelpful, and applies a validated edit to address the diagnosed deficiency. When the new candidate executes, \emph{execution inheritance} inherits eligible stored results only if the complete resolved request and execution context match, avoiding redundant model and tool calls. With GPT-4o-mini workers, Inherit-MAS achieves 55.4\% completion on WorkBench and 49.7\% joint F1 on HotpotQA FullWiki, outperforming EvoAgent, EvoMAS, and TacoMAS. With Qwen3-32B workers, it also exceeds these evolving-MAS baselines on both benchmarks. Compared with rerunning the same controller with execution inheritance disabled, execution inheritance reduces worker-token usage by 29.1\% on WorkBench and 34.6\% on HotpotQA, and total token usage by 5.3\% and 18.1\%.

cs.LG↗

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents

Agentic memory is becoming essential for long-horizon AI agents, yet many existing systems rely on autoregressive LLMs to control how memories are organized, retrieved, and used, placing expensive generation on the critical path of memory operations. We introduce \textbf{\method}, a new agentic memory architecture inspired by System-One/System-Two cognition. System One captures fast, lightweight decision-making, whereas System Two performs slower, deliberative reasoning. Jev-Mem brings this division of labor to agentic memory through a dedicated System-One control plane, a structured multi-relational memory plane, and a System-Two reasoning plane. The System-One controller governs memory typing and relational organization during construction, and dynamically performs query routing, retrieval-budget allocation, graph traversal, candidate scoring, and adaptive stopping during retrieval. System Two is invoked only for complex reasoning and answer synthesis. This design improves both memory effectiveness and system efficiency: on LoCoMo Jev-Mem achieves an overall LLM-as-a-Judge score of 0.777, an 11.0\% relative improvement over the strongest baseline, while reducing memory construction time to 158\,s, a 6.6$\times$ speedup over the fastest competing memory system, and lowering average query latency to 0.93\,s, a 36.7\% reduction.

cs.AI↗

A Universal Context-Reuse Layer for Cross-Model KV Sharing

Modern large language model (LLM) serving systems increasingly operate over repeated or shared context, yet each model typically performs its own prefill computation even when another model has already processed the same input. Existing KV-cache reuse mechanisms substantially reduce redundant computation within a single model, but generally assume that the producer and consumer of a cache are identical. We study \emph{cross-model KV sharing}, which translates the KV state produced by a source model into a representation that can be consumed by a different target model, including models that differ in scale, architecture, attention configuration, tokenizer, and model family. We evaluate the approach in both within-family and cross-family settings. For Qwen2.5-7B $\rightarrow$ Qwen2.5-1.5B, translated KV states improve LongBench2 accuracy from 27.59\% to 34.48\%, a gain of 6.89 percentage points over the native 1.5B baseline, while reducing handoff cost relative to native target prefill. For the cross-family Qwen2.5-1.5B $\rightarrow$ Gemma-2-2B setting, KV handoff reduces target-side prefill cost by up to 67.05\% at 4K context length while maintaining decoding perplexity close to native-model baselines. In a more heterogeneous Llama3.1-70B $\rightarrow$ Qwen2.5-7B setting, cross-family handoff achieves 44.0\% accuracy compared with 45.7\% for native Qwen2.5-7B inference, while reducing measured latency from 899ms to 138ms. These results provide initial evidence that KV states can serve as transferable computational representations rather than strictly model-local caches, and motivate \emph{context mobility} as a systems abstraction for reducing redundant prefill across heterogeneous LLM and multi-agent inference workflows.

cs.LG↗

Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?

Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assumed to improve factual correctness. However, how the parameter-efficient fine-tuning methods affect hallucination behavior remains insufficiently understood, especially on QA datasets. In this work, we systematically investigate the impact of PEFT on hallucination detection through a comprehensive empirical study across three open-weight LLM backbones and three fact-seeking QA benchmarks. For each model, we evaluate performance using seven unsupervised hallucination detection methods spanning three complementary approaches: semantic consistency based detectors, confidence based detectors, and entropy based detectors. This multifaceted evaluation enables us to characterize how PEFT reshapes uncertainty across different detection paradigms. In conclusion, our experimental results show that PEFT consistently strengthens hallucination detection ability, substantially improving AUROC across a wide range of hallucination detectors. Besides, further analyses using linear probes and representation diagnostics indicate that PEFT methods primarily reshapes how uncertainty is encoded and surfaced, comparing with injecting new factual knowledge into the models.

cs.CL↗

HORIZON: A Read-Efficient Firmware for DNA Storage with Horizontal Layout

DNA storage is a promising medium for long-term archiving, but its read performance is limited by coarse-grained random access. Existing random-access DNA storage designs suffer from high read amplification because their sequential layouts co-locate frequently and infrequently accessed data under the same primer pair, where any read must retrieve all associated strands even when only a small fraction is needed. We present HORIZON, a read-efficient allocation policy for DNA block devices that reduces read amplification through activity-aware horizontal placement. HORIZON first introduces a horizontal layout distributing writes round-robin across primer pairs, rather than filling each sequentially. It classifies newly written blocks in the write buffer as active or inactive, tracks recent primer-pair accesses using a sliding-window temperature model, and allocates blocks based on block activity and primer-pair occupancy. Simulations show HORIZON consistently reduces read amplification compared with state-of-the-art schemes across MSR and FIU traces and synthetic filesystem workloads.

cs.ET↗

Knowledge-Driven Hybrid SSD Management Enhanced by Fine-Tuned LLMs

A hybrid Solid-State Drives (SSDs) integrates different modes of flash cells (e.g., single-level cell (SLC) and Quad-Level Cell (QLC)) and enables them to convert between each other, achieving both high performance and storage capacity. However, this hybrid design introduces a significantly larger design space than traditional SSDs with additional design factors such as flash conversion and data migration across different flash modes, leading to higher optimization complexity. Efficient management of such complexity requires deep hybrid SSD knowledge and dynamic adjustment mechanisms. Large language models (LLMs) offer a promising solution through their contextual reasoning and adaptive coordination capabilities. In this work, we explore the potential of using LLMs in understanding and efficiently managing hybrid SSD design space. We find that leveraging LLMs for knowledge-guided optimization of management parameters enables substantial performance gains. Building on these insights, we propose LLM-hybridSSD, an integrated optimization framework that formulates hybrid SSD management as a parameter-tuning problem, employs an LLM-based tuner for adaptive configuration, and applies reinforcement learning-based fine-tuning to align local lightweight models with domain-specific knowledge. Experimental results show an average 58.92% increase in throughput and a 28.56\% reduction in write amplification (WA) compared with state-of-the-art schemes under different real-world workloads.

cs.AR↗

V-Mem: Modality-Routed Retrieval for Long-Term Multimodal Agentic Memory

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.

cs.AI↗

VeriHGN: Heterogeneous Graph-Based Congestion Prediction for Chip Layout Verification

As Very Large Scale Integration (VLSI) designs continue to scale in size and complexity, layout verification has become a central challenge in modern Electronic Design Automation (EDA) workflows. In practice, congestion can only be accurately identified after detailed routing, making traditional verification both time-consuming and costly. Learning-based approaches have therefore been explored to enable early-stage congestion prediction and reduce routing iterations. However, although prior methods incorporate both netlist connectivity and layout features, they often model the two in a loosely coupled manner and primarily produce numerical congestion estimates. We propose VeriHGN, a verification framework built on an enhanced heterogeneous graph that unifies circuit components and spatial grids into a single relational representation, enabling more faithful modeling of the interaction between logical intent and physical realization. Experiments on industrial benchmarks, including ISPD2015, CircuitNet-N14, and CircuitNet-N28, demonstrate that VeriHGN achieves the best or near-best performance over state-of-the-art methods in prediction accuracy and correlation metrics.

cs.AR↗

LAANN: I/O-Aware Look-Ahead Search for Disk-Based Approximate Nearest Neighbor Search

Approximate nearest neighbor search (ANNS) is a fundamental primitive in large-scale retrieval, recommendation, and AI systems. As vector datasets grow to billions or even trillions of items, disk-based ANNS systems have emerged to handle this scale by storing vector data and index structures on storage systems, but their query performance remains dominated by I/O latency. Existing disk-based ANNS systems primarily optimize I/O efficiency or overlap I/O with computation, but they treat CPU computation and I/O access as largely separate components. This separation misses a critical opportunity: selectively processing candidates already cached in memory before making I/O decisions can reduce unnecessary disk accesses and improve search quality. However, exploiting this opportunity is challenging because excessive computation can delay critical I/O operations, while poorly chosen computation provides little benefit, potentially increasing overall query latency. In this paper, we present LAANN, a disk-based ANNS system that makes graph search explicitly I/O-aware by co-optimizing CPU computation and I/O access. LAANN combines three techniques: look-ahead search, which adapts the search strategy across query stages to balance I/O reduction and timely I/O issuance; a priority I/O-CPU pipeline, which uses I/O waiting time to process candidates cached in memory according to their expected impact on upcoming I/O decisions; and a fast lightweight in-memory graph index, which provides high-quality initial candidates to accelerate convergence and reduce disk accesses. Experiments on million- and billion-scale datasets demonstrate that LAANN substantially outperforms state-of-the-art disk-based ANNS systems. At Recall@10 = 0.9, LAANN achieves 1.41x-4.66x higher throughput, 29%-79% lower latency, and 1.59x-6.34x fewer I/O operations.

cs.DB↗

DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs

Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and high communication overhead. When agents exchange raw responses or reasoning traces, incorrect intermediate reasoning may be adopted and amplified, leading to confident but wrong consensus; multi-round communication also increases token consumption, latency, and inference cost. In this paper, we propose a controlled-communication coordination framework named DarkForest. DarkForest first keeps agents independent, so each agent produces an answer without seeing the others' outputs. It then parses the raw responses into structured candidate records, groups semantically equivalent candidates into clusters, and estimates a calibrated belief distribution over these clusters using agent reliability, confidence, parse quality, support-pattern reliability, and independence corrections. A coordinator receives only policy-permitted evidence from this belief state with controlled communication. Experiments on six reasoning benchmarks show that DarkForest achieves leading overall quality, improves the strongest baseline by up to 30.7\% on benchmark metrics, and reduces token consumption by up to $6.5\times$ compared with communication-heavy baselines.

cs.AI↗

Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations

Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the empirical foundations of these systems remain fragile: existing benchmarks are often underscaled, evaluation metrics are misaligned with semantic utility, performance varies significantly across backbone models, and system-level costs are frequently overlooked. This survey presents a structured analysis of agentic memory from both architectural and system perspectives. We first introduce a concise taxonomy of MAG systems based on four memory structures. Then, we analyze key pain points limiting current systems, including benchmark saturation effects, metric validity and judge sensitivity, backbone-dependent accuracy, and the latency and throughput overhead introduced by memory maintenance. By connecting the memory structure to empirical limitations, this survey clarifies why current agentic memory systems often underperform their theoretical promise and outlines directions for more reliable evaluation and scalable system design.

cs.CL↗