中 EN
登录 注册账户

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达，利用大语言模型自动生成交叉领域文献分析简报。

登录 注册账户
02.
arXiv (CS.CV) 2026-06-17

Revisiting Structural Dependency in Autoregressive Multi-Task Table Recognition via Order-Independent Cell-Level Representations

作者:
Takaya Kawakatsu↗

Multi-task table recognition jointly addresses table structure prediction, cell localization, and cell content recognition within a unified framework. Existing approaches often rely on autoregressive decoders to generate table structures and reuse their hidden states for cell localization and content recognition. This autoregressive generation process can make cell representations order-dependent, degrading global consistency across cells. This paper proposes a structural refinement module that produces order-independent cell features through non-causal attention. This design enables parallel inference of cell contents while conditioning each cell on global context encoded in the refined features. Experiments on two large datasets demonstrate consistent gains in cell localization and end-to-end recognition, while reducing overall inference time by around threefold.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CL) 2026-06-11

Multi-task Learning is Not Enough: Representational Entanglement in Dual-output Second Language Speech Recognition

作者:
Seung Hwan Cho↗Young-Min Kim↗

Second-language (L2) speech recognition often requires transcriptions of pronunciations and intended meanings. Multi-task learning (MTL) is a natural approach because it assumes that shared representations benefit both outputs. However, this paper shows that this assumption does not hold across Korean and English. MTL improves meaning but degrades surface transcription, especially in English, where the degradation scales with surface-meaning divergence measured by Levenshtein edit distance. Encoder analysis links these patterns to encoder-level entanglement, with Korean preserving distinct task representations while English produces nearly identical ones. Cross-task decoder analysis shows that the meaning dual-output decoder adapts with a unique representation, while the surface dual-output decoder remains constrained by the encoder. These findings motivate the design of MTL frameworks that mitigate encoder-level entanglement to reduce surface degradation in dual-output L2 automatic speech recognition.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.AI) 2026-06-16

Explainable deep learning improves human mental models of self-driving cars

作者:
Eoin M. Kenny↗Akshay Dharmavaram↗Sang Uk Lee↗Tung Phan-Minh↗Shreyas Rajesh↗Yunqing Hu↗Laura Major↗Momchil S. Tomov↗Julie A. Shah↗

arXiv:2411.18714v3 Announce Type: replace-cross Abstract: Self-driving cars increasingly rely on deep neural networks to achieve human-like driving. The opacity of such black-box planners makes it challenging to accurately anticipate when they will fail, with potentially catastrophic consequences. While research into interpreting these systems has surged, most of it is confined to simulations or toy setups due to the difficulty of real-world deployment, leaving the practical utility of such techniques unknown. Here, we introduce the Concept-Wrapper Network (CW-Net), a method for faithfully explaining the behavior of machine-learning-based planners that causally grounds their reasoning in human-interpretable concepts without sacrificing performance. We deploy CW-Net on a real self-driving car and show that the resulting explanations improve the human driver's mental model of the vehicle, allowing them to better predict its behavior, particularly in surprising situations. This demonstrates that explainable deep learning integrated into self-driving cars can be both understandable and useful in a realistic deployment setting. We anticipate our method could be applied to other safety-critical systems, such as autonomous drones and robotic surgeons, as well as to other architectures, such as end-to-end learning systems and vision-language-action models. Overall, our study establishes a deployment-validated pathway to interpretability for autonomous agents, which could help make them more transparent and safe.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.CL) 2026-06-16

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention

作者:
Zhen Yang↗Mingyang Zhang↗Feng Chen↗Ganggui Ding↗Liang Hou↗Xin Tao↗Ying-Cong Chen↗

Recent progress in large language models (LLMs) has focused on test-time scaling to improve reasoning via increased inference computation, but often at the cost of efficiency. We revisit test-time behavior and uncover a simple yet underexplored phenomenon: reasoning uncertainty is highly localized-only a small subset of high-entropy tokens dominantly affects output correctness. Motivated by this, we propose Minimal Test-Time Intervention (MTI), a training-free framework that enhances reasoning accuracy and stability with minimal overhead. MTI includes: (i) Selective CFG intervention, applying classifier-free guidance only at uncertain positions; and (ii) Lightweight negative-prompt guidance, reusing the main model's KV cache to approximate unconditional decoding efficiently. MTI yields consistent gains across general, coding, and STEM tasks-e.g., +9.28% average improvement on six benchmarks for DeepSeek-R1-7B and +11.25% on AIME2024 using Ling-mini-2.0-while remaining highly efficient.

阅读与讨论 → 访问原文 →
06.
medRxiv (Medicine) 2026-06-16

Sleep regularity outweighs sleep duration as a predictor of disease

作者:
Windred↗D. P↗Burns↗A. C↗Reynolds↗Sansom↗Lechat↗B. C↗Scott↗Adams↗Steven↗Saxena↗…

Sleep regularity, the consistency of sleep-wake timing from one day to the next, is more strongly associated with longevity than adequate sleep duration. Whether this relationship persists across common diseases is unknown. We compared sleep regularity vs. sleep duration as risk factors for 199 diseases and disorders, using ten million hours of objective sleep-wake data (N=60,998, age[mean{+/-}SD]=62.8{+/-}7.8, 55% female). Multivariable-adjusted risks of incident diseases/disorders for regular/irregular and short/adequate sleepers were compared across 9.5 years of follow-up. Irregular sleep predicted risks for 131 diseases/disorders, more than double the number predicted by short sleep duration (63). Irregular sleep was a superior predictor than short sleep duration for 90 diseases/disorders, including circulatory, metabolic, digestive, renal, infectious, neurological, and musculoskeletal conditions, and mental disorders, whereas short sleep duration was the superior predictor for only 9 diseases/disorders. For models where short sleep duration explained disease risks, 83% were improved by adding sleep regularity. Sleep regularity was a stronger predictor of diseases/disorders than sleep duration in this cohort and should be considered an essential dimension of sleep health.

阅读与讨论 → 访问原文 →
08.
arXiv (quant-ph) 2026-06-12

Continuum Neural Momentum Eigenstate for Variationally Solving Quasiparticles

作者:
David D. Dai↗Marin Solja\v{c}i\'c↗

arXiv:2606.12928v1 Announce Type: cross Abstract: We design the first neural quantum state for continuum particles that, for any chosen allowed momentum $\mathbf{k}$, is by construction an exact eigenstate of total momentum with eigenvalue $\mathbf{k}$. Our architecture, EVE, enables off-the-shelf VMC to solve for momentum-sector ground states. We test EVE on 2D bosons with mutual $1/r$ interactions, finding that a single unified ansatz is capable of describing four qualitatively different states: superfluid, roton, crystal, and phonon. At different densities, we extract the underlying phase of matter from the dispersion's shape. At $r_s = 20.0$, we see the roton minimum at finite $k$ expected of a superfluid. At $r_s = 100.0$, we see striking zone folding indicative of crystalline order, with periodically spaced minima representing floating crystals connected by phonon arcs in between. Using density-density correlation functions, we confirm the phase diagnoses and probe the excitations' correlation structures. Finally, we analyze the roton's phase texture and find unexpected multi-particle phase strings, formed when several vortex dipoles merge, leaving two vortices connected by a phase slip.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.LG) 2026-06-16

GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization

作者:
Haotian Liu↗Yihao Liu↗Jingwei Ni↗Siyuan Huang↗Xinpeng Liu↗Pengyu Cheng↗Jiajun Song↗Ruijin Ding↗Junfeng Li↗Zhechao Yu↗Mengyu Zhou↗Hongteng Xu↗…

arXiv:2606.16771v1 Announce Type: new Abstract: As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities. This shift demands new algorithms capable of optimizing diverse and potentially competing objectives simultaneously. To address this, existing methods such as Group reward-Decoupled Policy Optimization (GDPO) decompose the overall score into independent reward groups, then compute the RL loss separately within each group. However, this strategy still encounters multi-reward conflicts: a single rollout can yield positive advantages on certain reward dimensions but negative ones on others, causing opposing signals to cancel each other out during aggregation, further hindering RL training efficiency. Inspired by Dynamic sAmpling Policy Optimization (DAPO), which improves RL training efficiency by filtering out ineffective rollouts with near-zero advantages, we propose Group-Dynamic reward-Decoupled Policy Optimization (GD$^2$PO). Specifically, GD$^2$PO employs a conflict-aware filtering mechanism to mask out rollouts suffering from severe reward-wise disagreement. By preventing conflicting signals from canceling each other out, this masking strategy preserves and enhances the magnitude of effective RL advantages, thereby significantly accelerating learning efficiency. Furthermore, we introduce query-level reweighting to dynamically adjust the update intensity of each query based on its overall reward consensus. Experiments on various multi-reward scenarios, including tool calling and human preference alignment, demonstrate that GD$^2$PO consistently and significantly outperforms existing baselines. The code is available at https://github.com/Qwen-Applications/GD2PO.

阅读与讨论 → 访问原文 →
10.
arXiv (math.PR) 2026-06-12

Explosion and non-explosion in pure birth Crump–Mode–Jagers branching processes

作者:
Oleksii Galganov↗Andrii Ilienko↗

arXiv:2601.06850v2 Announce Type: replace Abstract: In this short note, we provide an explicit sufficient condition for non-explosion of Crump–Mode–Jagers branching processes with pure birth reproduction. It shows that the standard sufficient condition for explosion, namely the convergence of the series of reciprocals of the birth rates, is – at least for rate sequences without excessive oscillations – remarkably close to being necessary. At the same time, it is not necessary in full generality: we construct a counterexample which also yields a general preferential attachment tree without fitness with an infinite path and no vertices of infinite degree, thereby answering an open question previously raised in the literature.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.CV) 2026-06-24

GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstruction

作者:
Chenrui Fan↗Paolo Favaro↗

Camera-prompted text-to-video (T2V) models are increasingly used to synthesize virtual camera captures, such as orbiting objects or moving through static scenes. For these outputs, visual plausibility is insufficient: the generated frames should also provide coherent multi-view evidence for a single static 3D scene. We introduce GeoT2V-Bench, a reconstruction-based diagnostic benchmark for evaluating whether camera-prompted T2V clips can support explicit rigid 3D reconstruction. Our pipeline estimates per-frame camera intrinsics and poses with VGGT-style geometry estimation, fits DeformableGS, derives a static MedianGS proxy by temporal-median aggregation, and renders this proxy along the estimated camera path. Instead of producing a pass/fail label or a single scalar score, GeoT2V-Bench reports a continuous reconstruction profile covering apparent image motion, estimated trajectory behavior, MedianGS static rendering error, static-render flow agreement, and the gap between flexible and static fits. On a fair-format four-seed evaluation with 3,840 completed reconstructions from 12 open-weight model configurations and 80 GeCo-Eval static-scene prompts, we find that visible motion, static rendering error, flow agreement, and flexible-vs-static behavior often disagree. GeoT2V-Bench therefore captures complementary failure modes that emerge when generated videos are tested as global static-scene acquisitions.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.AI) 2026-06-17

TRACE: Learning to Compute on Circuit Graphs

作者:
Ziyang Zheng↗Jiaying Zhu↗Jingyi Zhou↗Qiang Xu↗

arXiv:2509.21886v3 Announce Type: replace Abstract: Learning to compute, the ability to model the functional behavior of a circuit graph, is a fundamental challenge for graph representation learning. Yet, the dominant paradigm is architecturally mismatched for this task. This flawed assumption, central to mainstream message passing neural networks (MPNNs) and their conventional Transformer-based counterparts, prevents models from capturing the position-aware, hierarchical nature of computation. To resolve this, we introduce TRACE, a new paradigm built on an architecturally sound backbone and a principled learning objective. First, TRACE employs a Hierarchical Transformer that mirrors the step-by-step flow of computation, providing a faithful architectural backbone that replaces the flawed permutation-invariant aggregation. Second, we introduce function shift learning, a novel objective that decouples the learning problem. Instead of predicting the complex global function directly, our model is trained to predict only the function shift, the discrepancy between the true global function and a simple local approximation that assumes input independence. We validate this paradigm on various circuits modalities, including Register Transfer Level graphs, And-Inverter Graphs and post-mapping netlists. Across a comprehensive suite of benchmarks, TRACE substantially outperforms all prior architectures. These results demonstrate that our architecturally-aligned backbone and decoupled learning objective form a more robust paradigm for the fundamental challenge of learning the functional behavior of a circuit graph.

阅读与讨论 → 访问原文 →
13.
arXiv (math.PR) 2026-06-17

Full $\Gamma-$expansion for the level-two large deviation rate functionals of non-reversible one-dimensional diffusions with periodic boundary conditions

作者:
Claudio Landim↗Christian Maura↗

arXiv:2606.17859v1 Announce Type: new Abstract: Consider the diffusion process \begin{equation*} dX_{\epsilon}(t) = \mss b(X_{\epsilon}(t)) \, dt + \sqrt{2\, \epsilon\, \mss a(X_\epsilon(t))} \, dW_{t}, \end{equation*} on the one-dimensional torus $\bb T = [0,1)$. Here $\epsilon$ is the temperature, $W_{t}$ a Brownian motion on $\bb T$ and $\mss a$, $\mss b$ functions of class $C^{2}(\bb T)$ satisfying further conditions. Denote by $\mss P(\bb T)$ the set of probability measures on $\bb T$ equipped with the weak topology, and by $\ms I_{\epsilon}\colon \mss P(\bb T)\to [0,+\infty)$ the level two large deviation rate functional of the diffusion $X_{\epsilon}(\cdot)$. We derive a full $\Gamma-$expansion of $\ms I_{\epsilon}$, as $\epsilon \to 0$, expressing it as \begin{equation*} \ms I_{\epsilon} = \frac{1}{\epsilon} \;\ms J^{(-1)} \; +\; \ms J^{(0)} \;+\; \sum_{p=1}^{\widehat{\mf q}}\frac{1}{\theta^{(p)}_{\epsilon}}\;\ms J^{(p)}\,, \end{equation*} where $\ms J^{(-1)}$, $\ms J^{(0)}$, $\ms J^{(p)} \colon \mss P(\bb T)\to [0,+\infty]$ represent rate functionals, independent of $\epsilon$, and $\theta^{(p)}_{\epsilon}$ are the time-scales at which the Markov process $X_{\epsilon}(\cdot)$ exhibits a metastable behaviour.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.AI) 2026-06-11

Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends

作者:
Jinshan Lai↗Jianwei Hu↗Baoyang Jiang↗Fengchun Zhang↗Leyuan Wang↗Haotian Li↗Yida Wang↗Tingxuan Huang↗Xi Ren↗Qiang Ma↗

arXiv:2606.12207v1 Announce Type: cross Abstract: Embodied intelligence now spans navigation, household assistance, manipulation, autonomous driving, aerial agents, and multimodal large-model control. This expansion has made benchmark construction a central bottleneck for reliable evaluation. Unlike static datasets, embodied benchmarks combine task specifications, environments, robot data, demonstrations, annotations, metrics, evaluation scripts, and release policies into a single evaluation system. This survey reviews the literature through a five-stage construction pipeline: requirement and task construction, data acquisition, data cleaning and annotation, benchmark suite generation and metric definition, and evaluation execution with diagnostic feedback. For each stage, the survey analyzes the transition from manual curation to traditional automation, foundation-model assistance, and agentic closed-loop workflows. It also compares qualitative construction costs across human labor, data and asset acquisition, compute and simulation, validation and debugging, governance and maintenance, and rework risk. The main conclusion is that automation does not simply reduce benchmark cost. Instead, it often shifts cost toward validation, auditability, version control, and long-term governance. Progress in embodied evaluation will therefore depend not only on larger benchmark suites, but also on construction pipelines that are diagnosable, auditable, and responsibly refreshable.

阅读与讨论 → 访问原文 →
15.
arXiv (math.PR) 2026-06-17

Killed resolvents and measure-valued stopping gains for reflected optimal stopping with max-type rewards

作者:
Louis Shuo Wang↗Jiguang Yu↗Ye Liang↗

arXiv:2606.17517v1 Announce Type: new Abstract: We study an infinite-horizon optimal stopping problem for a normally reflected two-dimensional diffusion in the positive quadrant with nonsmooth max-type reward \(G(x_1,x_2)=x_1\vee \alpha x_2\). The paper develops a conditional measure-theoretic framework for the associated reflected obstacle problem. The main innovation is to show that the stopping gain \(\Gamma=c+rG-\mathcal LG\) is a signed measure, not a function: the kink of \(G\) generates an explicit negative surface measure on \(\Delta=\{x_1=\alpha x_2\}\). We then prove that the correct potential representation uses the resolvent of the reflected diffusion killed on first entry into the stopping set, rather than the unrestricted reflected resolvent. Under explicit monotonicity, regularity, and measure-superharmonicity assumptions, we derive an epigraph representation, a continuation-side boundary-trace condition, and a candidate verification theorem. The framework clarifies hidden regularity and uniqueness assumptions in multidimensional nonsmooth optimal stopping.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.AI) 2026-06-12

Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming

作者:
Tingqiang Xu↗Hangrui Zhou↗Tianle Cai↗Alex Gu↗Kaifeng Lyu↗

arXiv:2606.12864v1 Announce Type: cross Abstract: Despite strong performance in competitive programming, the role of Large Language Models (LLMs) in supporting human learning in the same setting remains largely unexplored. In this work, we introduce UOJ-Bench, a benchmark designed to evaluate not only the problem-solving ability of LLMs, but also their ability to identify errors in human-written code – a crucial educational activity traditionally supported by running test cases over online judge systems. UOJ-Bench consists of three distinct tasks: code generation, code hacking, and code repair, all constructed from real-world code submissions on the Universal Online Judge (UOJ) and evaluated through UOJ's native judging infrastructure. Our results show that under one-shot evaluation, even the strongest models fail to identify errors in more than 50% of a set of submissions that have been found to be incorrect by UOJ users. While test-time scaling improves success rates to above 90%, the substantial computational costs incurred from model inference limit its practicality for large-scale deployment. Despite these limitations, we find that the best-performing models under test-time scaling can uncover errors in over 5% of full-score submissions across roughly 30 problems, suggesting that frontier LLMs can already provide complementary signals beyond standard judging systems.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.CL) 2026-06-12

Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs

作者:
Sudhanshu Agrawal↗Risheek Garrepalli↗Raghavv Goel↗Christopher Lott↗Fatih Porikli↗Mingu Lee↗

Diffusion LLMs (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs (AR-LLMs) with the potential to operate at significantly higher token-generation rates. To unlock this potential, we present Spiffy, a speculative decoding algorithm to accelerate dLLM inference while provably preserving the model's output distribution. This work addresses the unique challenges involved in applying ideas from speculative decoding of AR-LLMs to dLLMs. Spiffy performs auto-speculation to eliminate the overheads of an independent draft model, structuring draft states in the form of a novel directed draft graph to take advantage of the bidirectional, blockwise nature of dLLM generation. These draft graphs are calibrated offline to maximize acceptance rates and are dynamically pruned during inference for improved computational efficiency. We present a detailed formulation of Spiffy and demonstrate its ability to accelerate LLaDA, Dream, and SDAR models in combination with KV caching and threshold-based dynamic unmasking leading to up to $8.6\times$ reduction in model inferences and $6.3\times$ acceleration in token rate.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.CL) 2026-06-16

EffGen: Enabling Small Language Models as Capable Autonomous Agents

作者:
Gaurav Srivastava↗Aafiya Hussain↗Chi Wang↗Yingyan Celine Lin↗Xuan Wang↗

Most existing language model agentic systems today are built and optimized for large language models (e.g., GPT, Claude, Gemini) via API calls; while powerful, this approach faces several limitations including high token costs and privacy concerns for sensitive applications. We introduce EffGen, an open-source agentic framework optimized for small language models (SLMs) that enables effective, efficient, and secure local deployment. EffGen makes four major contributions: (1) Enhanced tool-calling with prompt optimization that compresses input prompts by up to 70-80% (and 57% on average across our benchmarks) while preserving task semantics, (2) Intelligent task decomposition that breaks complex queries into parallel or sequential subtasks based on dependencies, (3) Complexity-based routing using five factors to make smart pre-execution decisions, and (4) Unified memory system combining short-term, long-term, and vector-based storage. Additionally, EffGen unifies multiple agent protocols (MCP, A2A, ACP) for cross-protocol communication. Results on 13 benchmarks show EffGen outperforms LangChain, AutoGen, and Smolagents with higher success rates, faster execution, and lower memory. Our results reveal that prompt optimization and complexity routing have complementary scaling behavior: optimization benefits SLMs more (11.2% gain at 1.5B vs 2.4% at 32B), while routing benefits large models more (3.6% at 1.5B vs 7.9% at 32B), providing consistent gains across all scales when combined. EffGen is released under the Apache 2.0 License, ensuring broad accessibility for research and commercial use, with the code available at https://github.com/ctrl-gaurav/effGen, the Python package at https://pypi.org/project/effgen/ (pip install effgen), and the project website and documentation at https://effgen.org/ and https://docs.effgen.org/.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.AI) 2026-06-18

RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents

作者:
Ruishan Fang↗Siyuan Lu↗Chenyi Zhuang↗Tao Lin↗

arXiv:2606.19047v1 Announce Type: new Abstract: Multi-turn tool-use RL is bottlenecked by the rapid depletion of informative samples in static datasets. We observe that the gradient signal in GRPO concentrates on tasks with the highest rollout reward variance, a consequence of the Popoviciu upper bound. Consequently, samples near the agent's capability boundary – where successes and failures are roughly balanced – contribute disproportionately large policy gradients. As training progresses, this boundary continuously shifts, which gradually depletes the pool of informative samples in a static dataset. We propose RODS (Reward-driven Online Data Synthesis) to resolve this depletion. RODS closes the loop between RL training and data generation by repurposing the progress reward variance as a practical, zero-cost boundary detector that requires no extra inference beyond the rollouts already computed for training. It continuously identifies such boundary samples, synthesizes new multi-turn variants matching their structural complexity (e.g., API topology and dependency depth) via a skill-aligned resampling pipeline, and manages a dynamic replay buffer that co-evolves with the policy. Starting from 400 human seeds and maintaining an active training pool of ~800 samples, RODS achieves comparable performance to a 17K-sample offline pipeline while requiring roughly 20x fewer trajectories, and improves over fixed-data RL and environment augmentation in our controlled setting.

阅读与讨论 → 访问原文 →
21.
arXiv (quant-ph) 2026-06-17

Average entropy of Bogoliubov-Kubo-Mori random state ensemble

作者:
Sohail↗Lu Wei↗

arXiv:2606.17960v1 Announce Type: cross Abstract: Random states play a foundational role in different branches of modern quantum science. In this work, we study a recently proposed random state ensemble induced from von Neumann entropy through the Bogoliubov-Kubo-Mori (BKM) metric. In particular, we derive an exact yet explicit formula of average entanglement entropy over BKM ensemble. In obtaining the formula, we only make use of properties of normalization constant of the ensemble in the absence of its correlation kernel, contrary to average entropy computation of other ensembles. This new framework paves the way for calculating higher-order cumulants of BKM ensemble beyond the average.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.CL) 2026-06-11

Doc-to-Atom: Learning to Compile and Compose Memory Atoms

作者:
Xingjian Diao↗Wenbo Li↗Yashas Malur Saidutta↗Avinash Amballa↗Lazar Valkov↗Srinivas Chappidi↗

Long input sequences are central to document understanding and multi-step reasoning in Large Language Models, yet the quadratic cost of attention makes inference both memory-intensive and slow. Context distillation mitigates this by compressing contextual information into model parameters, and recent work such as Doc-to-LoRA amortizes context distillation into a single forward pass that generates one LoRA adapter per document. However, producing a single monolithic adapter for all queries leads to irrelevant-query interference, limited compositional recall, and poor scalability to long-document reasoning. To address these challenges, we propose Doc-to-Atom (Doc2Atom), a compositional parametric memory framework that decomposes each document into semantically typed knowledge atoms. Each atom is compiled into an independent micro-LoRA adapter and a provenance retrieval key. At inference time, a lightweight query router selects and assembles only the relevant atoms into a query-specific adapter, which is then injected into a frozen base model. The entire system is trained end-to-end through a multi-objective distillation framework. Experiments on six diverse QA benchmarks demonstrate that Doc2Atom outperforms Doc-to-LoRA baselines while reducing the memory cost of document internalization.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.AI) 2026-06-17

Riemann-Bench: A Benchmark for Moonshot Mathematics

作者:
Suhaas Garre↗Erik Knutsen↗Sushant Mehta↗Edwin Chen↗

arXiv:2604.06802v2 Announce Type: replace Abstract: Recent AI systems have achieved gold-medal-level performance on the International Mathematical Olympiad, demonstrating remarkable proficiency at competition-style problem solving. However, competition mathematics represents only a narrow slice of mathematical reasoning: problems are drawn from limited domains, require minimal advanced machinery, and can often reward insightful tricks over deep theoretical knowledge. We introduce Riemann-Bench, a private benchmark of expert-curated problems designed to evaluate AI systems on research-level mathematics that goes far beyond the olympiad frontier. Problems are authored by Ivy League mathematics professors, graduate students, and PhD-holding IMO medalists, and routinely took their authors weeks to solve independently. Each problem undergoes double-blind verification by two independent domain experts who must solve the problem from scratch, and yields a unique, closed-form solution assessed by programmatic verifiers. We evaluate frontier models as unconstrained research agents, with full access to coding tools, search, and open-ended reasoning, using an unbiased statistical estimator computed over 100 independent runs per problem. Our results reveal that all frontier models currently score below 10%, exposing a substantial gap between olympiad-level problem solving and genuine research-level mathematical reasoning. By keeping the benchmark fully private, we ensure that measured performance reflects authentic mathematical capability rather than memorization of training data.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.CV) 2026-06-15

Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents

作者:
Seoyoung Choi↗Minseok Ko↗Hyunseok Lee↗Kunwoong Kim↗Woomin Song↗Chanseok Jeon↗Jinwoo Shin↗

Graphical User Interface (GUI) agents are increasingly used to automate complex computer tasks across applications, websites, and operating systems. To improve their reliability, recent work has introduced experiential memory, where agents retrieve prior trajectories to guide decision-making in similar states. More recent approaches further extend this idea to visual memory by storing and retrieving screenshots from past interactions, providing agents with richer contextual information than text-only memories. However, the effect of visual memory in GUI agents remains insufficiently understood: it is unclear which failures visual memory mitigates, or which failures it exacerbates. To systematically analyze the effect of visual memory, we introduce a taxonomy of four GUI agent failures (i.e., cognitive failure, visual state misunderstanding, hidden operation blindness, and grounding error) that map to distinct stages of the perception-reasoning-action pipeline. We find that prepending full-image memory has a divergent effect on the failure distribution: it reduces state-level failures but worsens action-level ones, and increases hidden operation blindness and grounding error. Motivated by this finding, we propose Action-Grounded Visual Memory (AGMem), an action-grounded memory framework for GUI agents. The core idea of AGMem is to store image crops that capture the local GUI region closely related to a successful action or a recovery, rather than storing full screenshots. Experiments on OSWorld show that AGMem improves task success rates by 33.3 % over full-image memory. These results demonstrate that AGMem is an effective representation for visual memory in GUI agents.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.AI) 2026-06-17

MemTrace: Probing What Final Accuracy Misses in Long-Term Memory

作者:
Xianxuan Long↗Zhikai Chen↗Shenglai Zeng↗Shouren Wang↗Kai Guo↗Jiliang Tang↗

arXiv:2606.17328v1 Announce Type: new Abstract: LLM agents increasingly maintain long-term memory of user facts across sessions. Yet such memory is usually evaluated by aggregating accuracy over question rows or episodes. Because this approach scores question rows independently, even when several questions probe the same fact, it cannot show how that fact behaves as conditions change. We introduce MemTrace, a benchmark whose unit of measurement is the knowledge point: a single typed fact about the user, rather than an individual question. MemTrace probes each fact along three controlled dimensions: memory age, defined by how many sessions ago the fact appeared in the history; question type, covering current state, earlier state, and trajectory of change; and evidence condition, covering present, missing, and contradicted-by-false-premise settings. Evaluating 13 memory-system configurations across four paradigms, we find that similar pooled accuracy hides different failures: recovering a fact's current and earlier states does not imply tracking how it changed, and safe abstention does not imply correcting a false premise. The dominant bottleneck is evidence use, not retrieval: when systems fail, the evidence was retrievable 10 times more often than it was missing. These results suggest that improving long-term memory requires better use of reachable evidence, not simply more storage or retrieval.

阅读与讨论 → 访问原文 →