×

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Authors: Tong Li ×
Shuffle
01.
arXiv (CS.AI) 2026-06-16

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

arXiv:2602.12670v4 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

02.
arXiv (CS.LG) 2026-06-16

Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes

arXiv:2606.17043v1 Announce Type: cross Abstract: When pretrained VLA policies are fine-tuned through online RL, each rollout episode produces only a single binary outcome (success or failure), yet the actor update requires per-transition supervision. Existing approaches commonly reduce this sparse outcome to a single scalar reward or advantage signal, which conflates distinct forms of transition-level feedback and provides limited guidance once basic task success becomes achievable. First, a single scalar signal conflates the two objectives of viability and efficiency; once basic success is achieved, the binary label provides no gradient to distinguish efficient completions from slow ones. Second, real-world rollouts mix autonomous and intervention segments; naively assigning episode outcomes across these boundaries introduces incorrect credit assignment. To address these issues, we propose Hierarchical Advantage-Weighted Behavior Cloning (HABC), which trains separate critic heads for these two objectives on different data subsets and combines their outputs with a state-adaptive balance. A state-adaptive gate $g_t$ merges their one-step advantages, prioritizing viability when success is uncertain and shifting to efficiency only when viability is high, and converts the result into per-transition weights on the actor loss. Intervention-aware credit assignment further restricts outcome labels to segments executed by the current policy, preventing supervision from leaking across intervention boundaries. In real-robot experiments on three contact-rich bimanual tasks, HABC raises success from supervised fine-tuning (SFT) baselines of 36%, 44%, and 12% to 92%, 88%, and 38%.

03.
medRxiv (Medicine) 2026-06-16

Efficacy of Ergothioneine Supplementation on Postpartum Fatigue, Sleep Quality, and Quality of Life: A Randomized, Double-Blind, Placebo-Controlled Trial

Background: Postpartum asthenia, characterized by severe fatigue, sleep disturbances, and physiological stress, lacks effective targeted interventions. Ergothioneine (EGT) is a unique, naturally occurring antioxidant that actively accumulates in mitochondria, offering a compelling therapeutic rationale for systemic recovery. This study aimed to evaluate the efficacy of EGT in accelerating postpartum functional restoration and alleviating fatigue. Methods: This single-center, randomized, double-blind, placebo-controlled trial enrolled 40 postpartum women (SF-36 total score [≤] 70) who had ceased breastfeeding. Participants were randomized (1:1) to receive either 120 mg/day of EGT or a matched placebo for 30 days. Efficacy was assessed using the SF-36, Pittsburgh Sleep Quality Index (PSQI), Fatigue Scale-14 (FS-14), and Traditional Chinese Medicine (TCM) asthenia scale. To rigorously evaluate the treatment effects, advanced statistical modeling, including Linear Mixed-Effects Models (LMM) and Analysis of Covariance (ANCOVA) adjusted for baseline covariates, was employed. Results: All 40 participants completed the trial. The EGT group demonstrated robust and accelerated functional recovery. Notably, significant improvements in sleep quality (p = 0.0361) and systemic fatigue (p = 0.0059) were observed as early as Day 15. Importantly, EGT yielded a statistically significant between-group superiority in alleviating mental fatigue compared to placebo at Day 15 (p = 0.0313). By Day 30, the EGT cohort exhibited substantial within-group improvements across all primary metrics, including SF-36 (+35.94%, p = 0.0006) and FS-14 (-27.78%, p = 0.0011). Furthermore, as an additional physiological benefit, EGT induced a selective and significant reduction in hepatic transaminases (ALT: -30.42%; AST: -17.44%) within normal limits, a trend not observed in the placebo group. EGT was exceptionally well-tolerated with no treatment-related adverse events. Conclusions: EGT supplementation (120 mg/day) safely accelerates postpartum functional recovery, offering rapid relief from mental fatigue and sleep disturbances within 15 days, while concurrently optimizing hepatic physiological status. These preliminary clinical signals warrant confirmation in larger, adequately powered cohorts. Trial Registration: ChiCTR2500114171; Prospectively registered on 2025-12-08.

04.
arXiv (CS.AI) 2026-06-16

RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments

arXiv:2606.15862v1 Announce Type: new Abstract: Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailBench, a data-grounded simulation benchmark for evaluating tool-using LLM agents in single-store supermarket operation. RetailBench models retail management as a partially observable decision process and is designed to support thousand-day-scale simulations. In this environment, agents must manage pricing, replenishment, supplier selection, shelf assortment, inventory aging, customer feedback, external events, and cash-flow constraints. We evaluate seven contemporary LLMs under representative agent frameworks over a 180-day evaluation horizon and compare them with a privileged oracle policy. Results show substantial variation across models: only a small subset survives the full evaluation horizon, and even the strongest LLM runs remain substantially behind the oracle policy in final net worth and sales outcomes. Behavioral analysis attributes these gaps to incomplete evidence acquisition, surface-level decision making, and the lack of a consistent long-horizon policy. RetailBench provides a controlled testbed for studying reliable autonomy in economically grounded long-horizon decision-making.

05.
arXiv (CS.LG) 2026-06-19

Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures

arXiv:2606.19365v1 Announce Type: new Abstract: Diffusion models have become essential for high-fidelity 3D MRI synthesis, yet their deployment remains constrained by substantial GPU resource demands arising from hundreds of U-Net evaluations per sample and a highly heterogeneous kernel behavior. This paper performs a comprehensive performance analysis of the state-of-the-art medical diffusion model, Med-DDPM, across three generations of NVIDIA architectures to study kernel-level runtime breakdowns, instruction-mix characteristics, memory system utilization, warp-level activities, and profiler priority-score estimates. We show that training is overwhelmingly dominated by cuDNN convolution and implicit-GEMM kernels, with inefficiencies arising from memory-access patterns, tensor-layout conversions, and limited Tensor Core utilization. Guided by these insights, we evaluate two architecture-aware optimizations TF32 Tensor Core activation and a 3D channels-last layout and demonstrate that they reduce SM cycles by up to 100x, cut dynamic instructions by 100x, raise Tensor Core utilization from 1.45 to 9.98x, and increase IPC by 7% on A100, all without degrading synthesis quality.

06.
arXiv (CS.CV) 2026-06-12

Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models

Text-guided image editing with visual autoregressive (VAR) generators requires controlling both what the model samples and where the sampled change is written back into the image code. Existing VAR editors mainly operate on token streams, features, or flat next-token logits, leaving two native structures of bitwise-residual VAR models underused: the per-bit Bernoulli prediction head and the additive multi-scale residual code field from which the image is assembled. We propose BitResEdit, a training-free editor for bitwise-residual VAR generators such as Infinity. BitEdit performs source-negative guidance by tilting the post-CFG per-bit log-odds along a source–target contrast computed on a shared edited prefix, then projects each update into a closed-form Bernoulli-KL trust region around the clean CFG sampler. ResEdit converts the sampled bits into per-scale continuous-code residuals, gates them with a localization mask, and re-injects them through the generator's native sum-of-scales. Together they couple decision-time bit guidance with combination-time code composition, so masked-out latent features are preserved exactly by code arithmetic while localized, scale-aware edits are applied inside the target region. On PIE-Bench with Infinity-2B, BitResEdit attains the strongest text alignment among same-backbone VAR editors, improving CLIP on the edited region by +1.07 over the strongest prior editor while keeping background preservation competitive with it. Ablations show BitEdit and ResEdit play complementary roles in target alignment and background preservation.

07.
arXiv (CS.CL) 2026-06-12

LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis

Mental disorders are highly prevalent worldwide, but the shortage of psychiatrists and the inherent subjectivity of interview-based diagnosis create substantial barriers to timely and consistent mental-health assessment. Progress in AI-assisted psychiatric diagnosis is constrained by the absence of benchmarks that simultaneously provide realistic patient simulation, clinician-verified diagnostic labels, and support for dynamic multi-turn consultation. We present LingxiDiagBench, a large-scale multi-agent benchmark that evaluates LLMs on both static diagnostic inference and dynamic multi-turn psychiatric consultation in Chinese. At its core is LingxiDiag-16K, a dataset of 16,000 EMR-aligned synthetic consultation dialogues designed to reproduce real clinical demographic and diagnostic distributions across 12 ICD-10 psychiatric categories. Through extensive experiments across state-of-the-art LLMs, we establish key findings: (1) although LLMs achieve high accuracy on binary depression–anxiety classification (up to 92.3%), performance deteriorates substantially for depression–anxiety comorbidity recognition (43.0%) and 12-way differential diagnosis (28.5%); (2) dynamic consultation often underperforms static evaluation, indicating that ineffective information-gathering strategies significantly impair downstream diagnostic reasoning; (3) consultation quality assessed by LLM-as-a-Judge shows only moderate correlation with diagnostic accuracy, suggesting that well-structured questioning alone does not ensure correct diagnostic decisions. We release LingxiDiag-16K and the full evaluation framework to support reproducible research at https://github.com/Lingxi-mental-health/LingxiDiagBench.

08.
arXiv (CS.CV) 2026-06-16

Structural Energy Guidance for View-Consistent Text-to-3D Generation

Text-to-3D generation based on diffusion models often suffers from the Janus problem, leading to inconsistent geometry across viewpoints. This work identifies viewpoint bias in 2D diffusion priors as the main cause and proposes Structural Energy-Guided Sampling (SEGS), a training-free and plug-and-play framework to improve multi-view consistency. SEGS constructs a structural energy in the PCA subspace of U-Net features and injects its gradient into the denoising process. It can be easily integrated into SDS/VSD pipelines without retraining. Experiments show that SEGS reduces the Janus Rate by about 10% on average and improves View-CS scores across multiple baselines, including DreamFusion, Magic3D, and LucidDreamer. This method effectively alleviates viewpoint artifacts while preserving appearance fidelity, providing a flexible solution for high-quality text-to-3D content generation.

09.
arXiv (quant-ph) 2026-06-11

Residual-Squeezing Mechanism of Mismatch in Inverse-Squeezing Kennedy Receivers

arXiv:2601.19093v4 Announce Type: replace Abstract: The discrimination of quantum states is fundamental to quantum information processing. Inverse-squeezing Kennedy (IS-Kennedy) receivers can outperform the coherent-state BPSK Helstrom benchmark at the same energy by converting transmitter-side squeezing into an effective coherent-state separation gain, without violating the Helstrom bound for the squeezed-state alphabet. This work investigates how squeezing mismatch degrades this mechanism. We show that imperfect inverse squeezing transforms the ideally nulled output into a residually squeezed state, thereby altering the photon-number statistics before detection. This residual-squeezing picture reveals a strong physical asymmetry between squeezing-magnitude and squeezing-phase mismatches. Magnitude mismatch produces an energy-independent error floor in the high-signal-energy regime, whereas phase mismatch generates a residual squeezing term that grows with signal energy. In the small-residual-squeezing regime, this leads to a polynomial growth of the leading error contribution and a rapid collapse of the SQL advantage. We also identify a parity-step effect in photon-number-resolving detection: because the nulled residual squeezed vacuum contains only even photon numbers, increasing detector resolution improves the high-energy robustness only when the effective saturation threshold crosses the next even photon number. These results identify phase locking as the dominant bottleneck for IS-Kennedy-type non-Gaussian receivers under unitary squeezing mismatch and provide design guidelines for robust squeezed-state quantum receivers.

10.
arXiv (CS.CL) 2026-06-11

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decoding (GCD) has been widely adopted to improve the reliability of LLM-generated code by enforcing syntactic validity. In this paper, we reveal a counterintuitive risk: this reliability-oriented technique can itself become an attack surface. We uncover a new jailbreak attack, termed CodeSpear, that exploits GCD to induce LLMs into generating malicious code. Our experiments show that simply applying a benign code grammar constraint can effectively jailbreak LLMs. To address this vulnerability, we propose CodeShield, a safety alignment approach that robustly preserves safe behavior even under attacker-controlled grammar constraints. CodeShield aligns the model in the code modality by teaching it to generate honeypot code under GCD. Such code is semantically harmless, so it does not implement the malicious request, and structurally diverse, so it is difficult to suppress through grammar tightening. At the same time, CodeShield still preserves natural-language refusals when natural language is available. Experiments on 10 popular LLMs across 4 benchmarks show that CodeSpear outperforms representative jailbreak baselines and increases the attack success rate by more than 30 percentage points on average. CodeShield also restores safety under CodeSpear while preserving benign utility. Our findings reveal a fundamental risk of GCD and call for greater attention to its potential security implications.

11.
arXiv (CS.CL) 2026-06-11

DEFINED: A Data-Efficient Computational Framework for Fine-Grained Creativity Assessment in Debate Scenarios

Human creativity has emerged as a critical competency in the era of large language models. Assessing creativity in complex, open-ended environments is a grand challenge in data mining, currently hindered by a reliance on standardized simple tasks and the scarcity of fine-grained expert data. As an ecologically valid assessment context, debate reflects multiple dimensions of creativity, encompassing both divergent thinking and convergent thinking. Moreover, debate is a data-rich domain, with a large volume of publicly accessible materials. Current mainstream automated scoring methods are poorly suited to complex settings such as debate, and therefore still rely on costly human evaluation. To this end, this paper proposes DEFINED, a data-efficient computational framework for fine-grained creativity assessment in debate scenarios. DEFINED operationalizes debate creativity through a hierarchical eight-dimensional metric system, implemented via a pre-trained autoregressive language model with a hierarchical scoring head that supports both fine-grained and coarse-grained evaluation. Statements and their associated expert scores were obtained from authentic debate competitions, and a constrained data augmentation strategy was employed to address the elite bias inherent in the original data. DEFINED adopts a mixed-granularity training strategy enabling robust learning from limited fine-grained supervision annotated by trained graduate experts. To rigorously validate ecological validity beyond synthetic benchmarks, we incorporate an empirical study with debate-naive participants, utilizing these authentic data to serve as a qualitative case study for mid-to-low proficiency populations. Across our evaluation protocol, our scoring model achieves accurate and stable scoring, outperforming prompt-based large language model evaluators and existing debate scoring methods.

12.
arXiv (CS.AI) 2026-06-18

SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety

arXiv:2606.18936v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in AI for Science (AI4Science) workflows, from scientific question answering and literature analysis to laboratory planning and autonomous discovery. This progress creates an urgent need for safety benchmarks that evaluate not only scientific competence, but also whether models recognize and avoid risks in high-stakes scientific contexts. Existing AI4Science safety datasets cover several disciplines and task formats, leaving the underlying risk dimensions underspecified. We introduce SciRisk-Bench, a benchmark designed to evaluate AI4Science safety from two complementary perspectives: explicit risk dimensions and scientific disciplines. SciRisk-Bench covers 7 disciplines, 31 subdisciplines and 10 risk dimensions. In the experimental section, we evaluate both mainstream LLMs and science-oriented LLMs across risk dimensions, disciplines, and sub-disciplines, enabling fine-grained diagnosis of where scientific models remain unsafe.

13.
arXiv (CS.CV) 2026-06-11

MedVeriSeg: Teaching LISA-Like Medical Segmentation Models to Verify Query Validity Without Extra Training

Despite recent progress in text-prompt-based medical image segmentation, existing LISA-like MLLM-based methods typically generate masks regardless of whether the target specified in the query is present, leading to hallucinated segmentation. In this work, we propose MedVeriSeg, a training-free query verification framework that enables LISA-like medical segmentation models to reject false segmentation queries. MedVeriSeg first quantifies the response quality between the [SEG] token and image features through a Similarity Response Quality Scoring Module. To further improve robustness, it employs a Lightweight Routed Multi-Agent Verification Module, which fuses quantitative score evidence with qualitative agent evidence to comprehensively verify the validity of the query. To support systematic evaluation, we construct MedVeriSeg-Bench, a benchmark designed for query verification in medical image segmentation. Experimental results demonstrate that MedVeriSeg effectively identifies false segmentation queries and reduces hallucinated segmentation, while maintaining a high acceptance rate for valid queries, thereby largely preserving the segmentation utility of LISA-like medical segmentation models.

14.
arXiv (CS.AI) 2026-06-15

LLM-Powered AI Agent Systems and Their Applications in Industry

arXiv:2505.16120v3 Announce Type: replace Abstract: The emergence of Large Language Models (LLMs) has reshaped agent systems. Unlike traditional rule-based agents with limited task scope, LLM-powered agents offer greater flexibility, cross-domain reasoning, and natural language interaction. Moreover, with the integration of multi-modal LLMs, current agent systems are highly capable of processing diverse data modalities, including text, images, audio, and structured tabular data, enabling richer and more adaptive real-world behavior. This paper comprehensively examines the evolution of agent systems from the pre-LLM era to current LLM-powered architectures. We categorize agent systems into software-based, physical, and adaptive hybrid systems, highlighting applications across customer service, software development, manufacturing automation, personalized education, financial trading, and healthcare. We further discuss the primary challenges posed by LLM-powered agents, including high inference latency, output uncertainty, lack of evaluation metrics, and security vulnerabilities, and propose potential solutions to mitigate these concerns.

15.
arXiv (CS.CV) 2026-06-16

FrameOracle: Learning What to See and How Much to See in Videos

Vision-language models (VLMs) advance video understanding but operate under tight computational budgets, making performance dependent on selecting a small, high-quality subset of frames. Existing frame sampling strategies, such as uniform or fixed-budget selection, fail to adapt to variations in content density or task complexity. To address this, we present FrameOracle, a lightweight, plug-and-play module that predicts both (1) which frames are most relevant to a given query and (2) how many frames are needed. FrameOracle is trained via a curriculum that progresses from weak proxy signals, such as cross-modal similarity, to stronger supervision with FrameOracle-41K, the first large-scale VideoQA dataset with validated keyframe annotations specifying minimal sufficient frames per question. Extensive experiments across five VLMs and six benchmarks show that FrameOracle reduces 16-frame inputs to an average of 10.4 frames without accuracy loss. When starting from 64-frame candidates, it reduces inputs to 13.9 frames on average while improving accuracy by 1.5%, achieving state-of-the-art efficiency-accuracy trade-offs for scalable video understanding.

16.
arXiv (CS.CV) 2026-06-16

MMLongEmbed: Benchmarking Multimodal Embedding Models in Long-Context Scenarios

Recent advancements have significantly expanded the theoretical context windows of Multimodal Embedding Models (MEMs). However, larger context windows do not necessarily translate into effective comprehension and representation of long-context multimodal inputs, which remains a critical bottleneck for real-world deployment. To address the lack of systematic evaluation in this setting, we introduce MMLongEmbed, the first comprehensive benchmark for evaluating MEMs in long-context scenarios. MMLongEmbed comprises four retrieval tasks spanning multiple context-length ranges, covering text, document, and video modalities. Through extensive evaluation of state-of-the-art models, we find that current architectures rely heavily on superficial feature matching and struggle to capture deep semantic and structural dependencies. We further observe that performance degradation varies systematically with context length and key information placement. Moreover, models exhibit substantially different robustness to redundant contextual information across modalities. For reproducibility, the benchmark and code are publicly available.

17.
arXiv (CS.LG) 2026-06-18

BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training

arXiv:2606.18650v1 Announce Type: new Abstract: As Large Language Model (LLM) datasets scale to trillions of tokens, data selection has emerged as a critical frontier to filter out uninformative noise and construct adaptive learning trajectories. Beyond static heuristic filtering, advanced data selection methods for LLM training largely follow two paradigms, each with fundamental limitations. Influence-based methods provide principled bi-level objectives but require intractable inverse-Hessian computations, while excess-loss methods are computationally efficient but rely on a static reference model that becomes misaligned with the evolving proxy model during training. We propose BLADE (Bi-Level Adaptive Data sElection), a Hessian-free framework for data selection. BLADE reformulates the bi-level optimization problem underlying influence-based methods as a penalized single-level objective via Lagrange multipliers, avoiding inverse-Hessian computation while revealing a principled connection to excess-loss based data selection. The resulting objective recovers an excess-loss form but replaces the static reference model with a dynamic one that stays synchronized with training. Theoretically, we prove that this penalized formulation guarantees first-order convergence. For efficient online batch selection, we instantiate BLADE as a memoryless randomized block-coordinate Frank-Wolfe algorithm. Extensive experiments show that BLADE consistently outperforms state-of-the-art data selection baselines, providing a practical recipe for LLM training.

18.
arXiv (CS.CV) 2026-06-17

AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving

Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes. While state-of-the-art (SOTA) methods use parallel planning architectures, they fail to explicitly couple speed decisions with agent behavior along the driving path, leading to suboptimal coordination. To address this, we propose a cascaded framework that transforms longitudinal planning from an independent prediction task into a path-conditioned reasoning process. On the model side, we introduce an anchor-based regression design that conditions longitudinal prediction on the lateral drive path, and reformulate longitudinal planning as 1D displacement prediction along the path. This reduces geometric uncertainty and sharpens the model's focus on interaction-driven dynamics. On the data side, we introduce a planning-oriented data augmentation strategy that simulates rare safety-critical events by programmatically inserting agents and relabeling longitudinal targets to enforce collision avoidance. Evaluated on the challenging Bench2Drive benchmark, our method achieves SOTA performance with a driving score of 89.07 and a success rate of 73.18%, demonstrating significantly improved coordination and safety. Further evaluation on Fail2Drive confirms strong generalization to rare edge cases where parallel formulations typically fail. Project page:https://yanhaowu.github.io/AlignDrive/.

19.
arXiv (CS.AI) 2026-06-19

Playful Agentic Robot Learning

arXiv:2606.19419v1 Announce Type: cross Abstract: Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reusable skills are acquired only after explicit instructions. We study Playful Agentic Robot Learning, where an embodied coding agent uses self-directed play as a continual skill-learning stage before downstream tasks arrive. We introduce RATs, Robotics Agent Teams designed for play-time skill acquisition. During play, RATs proposes novel yet learnable exploratory tasks, plans and executes robot-code policies, verifies intermediate progress, diagnoses failures, retries with dense, step-level feedback, and distills successful executions into a persistent code skill library. At test time, the agent reuses relevant skills from this frozen library to help solve new tasks. Experiments in LIBERO-PRO and MolmoSpaces show that play-learned skills improve held-out downstream tasks over no-play and random-play baselines, with 20.6 and 17.0 percentage-point gains over CaP-Agent0 on LIBERO-PRO and MolmoSpaces, respectively. Moreover, the learned skills can be plugged into other inference-time Code-as-Policy agents by simply retrieving them into the context, improving RoboSuite and real-world transfer by 8.9 and 8.8 points, respectively, without finetuning the underlying model.

20.
arXiv (CS.CL) 2026-06-17

EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent

As LLM-based shopping agents enter production, existing benchmarks fail to capture how a shopper's requirements arrive: stated implicitly in the query, recorded in a profile, or revealed only when the right question is asked. Benchmarks that expose full intent upfront and grade only the final choice can neither pose this long-horizon challenge nor explain which requirement an agent missed. To address this gap, we introduce EComAgentBench, a benchmark of 662 tasks grounded in real Amazon products and reviews. Each task scatters these requirements across a visible query, a tool-gated profile, and scripted clarification; an agent must uncover hidden intent, verify candidates against attributes and review evidence, and commit to a single product within 100 tool calls. Moreover, typed, source-tagged rubrics grade every task, attributing each failure to a requirement and its source. Construction is automated yet reliable, with every answer fixed in code before any text is generated and every sample validated. Our evaluation of seven models reveals that even the strongest attains only 57.1% overall accuracy, and rubric satisfaction degrades from visible to hidden sources. Overall, we believe EComAgentBench will serve as a reproducible foundation for moving shopping agents from single-query search toward dependable assistance over long horizons.

21.
arXiv (CS.CL) 2026-06-17

GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?

Game generation is an emerging application of coding agents, requiring models to transform natural-language specifications into playable interactive systems. Unlike traditional coding tasks, game generation takes place within a game engine, where scripts, scenes, assets, rendering, and runtime interactions must jointly produce coherent gameplay. We formalize end-to-end game generation as the problem of producing a complete game artifact that realizes a specification through observable player-game interaction in a target environment. We argue that evaluating this setting requires three desiderata: Engine Grounding, Artifact Completeness, and Interactive Verification. We propose an interaction-grounded evaluation framework that assesses executable gameplay through replayed demonstrations and rubric-guided multimodal judging. We instantiate this framework as GameCraft-Bench, a benchmark comprising 140 Godot tasks across 15 game families. Evaluations of frontier coding agents show that end-to-end game generation remains highly challenging: the strongest agent achieves only 41.46%, and most agents score below 40%. Further analysis reveals that while agents often implement recognizable mechanics, they struggle to deliver complete games with sufficient content, functional visual feedback, and coherent presentation. See https://tongxuluo.github.io/gamecraft-bench-website for demos, code, and data.

22.
arXiv (CS.CL) 2026-06-16

daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization

GPU kernel optimization represents a paradigm where functional correctness is assumed and execution efficiency is the objective. We present daVinci-kernel, a reinforcement learning framework that couples skill discovery with skill exploitation through a dynamically evolving skill library. daVinci-kernel jointly trains three agents sharing one LLM backbone: a Skill Selection Agent that retrieves relevant techniques via BM25 and LLM reranking, a Policy Agent that generates multi-turn CUDA/Triton kernels conditioned on selected skills, and a Skill Summary Agent that distills successful rollouts into reusable skills. Candidate skills are added only after execution-based verification confirms reproducible speedups. All three agents share a single LLM backbone, are initialized via a structured SFT cold start on diversity-filtered data, and are then jointly optimized end-to-end with multi-turn REINFORCE and per-agent advantage estimation. On KernelBench, daVinci-kernel-14B achieves 37.2%, 70.6%, and 32.2% on Level 1, Level 2, and Level 3 under the Fast$_1$ threshold, outperforming the strongest prior RL-trained model, Dr.Kernel-14B.

23.
arXiv (CS.LG) 2026-06-16

Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain

arXiv:2606.00558v2 Announce Type: replace Abstract: Transfer learning aims to facilitate the learning of a target domain by transferring knowledge from a source domain. The source domain typically contains semantically meaningful samples (*e.g.*, images) to facilitate effective knowledge transfer. However, a recent study observes that the noise domain constructed from simple distributions (*e.g.*, Gaussian distributions) can serve as a surrogate source domain in the semi-supervised setting, where only a small proportion of target samples are labeled while most remain unlabeled. Based on this surprising observation, we formulate a novel problem termed *Semi-Supervised Noise Adaptation* (SSNA), which aims to leverage a synthetic noise domain to improve the generalization of the target domain. To address this problem, we first establish a generalization bound characterizing the effect of the noise domain on generalization, based on which we propose a Noise Adaptation Framework (NAF). Extensive experiments demonstrate that NAF effectively leverages the noise domain to tighten the generalization bound of the target domain, leading to improved performance. The codes are available at https://github.com/AIResearch-Group/SSNA.

24.
arXiv (CS.CV) 2026-06-15

IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products

Industrial products such as valves and circuit breakers are defined by dense technical specifications that govern procurement, compatibility, and safety across supply chains. These specifications are scattered across multiple heterogeneous product images, including specification tables, nameplates, and technical drawings, yet whether Multimodal Large Language Models (MLLMs) can reliably recover them remains underexplored. To fill this gap, we introduce IndustryBench-MIPU, the first large-scale benchmark for multi-image industrial product understanding, built around structured attribute extraction – recovering property-value pairs from product images. This task jointly probes text recognition on specification tables and nameplates, visual reasoning over technical drawings, domain knowledge to decode industrial terminology, and cross-image evidence integration to assemble scattered specifications. Concretely, the benchmark comprises 4,559 products across 27,652 images with 103,703 annotations spanning 18 industrial categories, constructed through multi-model consensus and three-tier quality assurance. Evaluating nine MLLMs under both single-image and product-level multi-image settings reveals a stark completeness gap: models achieve high precision (86–94%) but the best recovers only 49.9% of product-level attributes; moving from single-image to multi-image extraction costs 15–34 percentage points of recall. Multi-image completeness, not single-image accuracy, is the core bottleneck. Dataset and code are publicly available.

25.
arXiv (CS.AI) 2026-06-19

Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents

arXiv:2606.19704v1 Announce Type: new Abstract: Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes. This paper aggregates the largest coordinated deep-dive of one MCP-based industrial-agent benchmark to date: fourteen parallel implementation studies covering new asset classes (including a multi-modal visual extension), alternative orchestrations, retrieval strategies, reasoning modes, infrastructure optimizations, and evaluation-methodology probes. Consolidating those studies with seven prior agent benchmarks, we argue that aggregate-score leaderboards systematically underspecify deployed-agent evaluation. Rankings derived from aggregate scores do not transfer to out-of-distribution settings; recent public-to-hidden competition retrospectives provide direct empirical evidence of this rank instability. We propose ranking configurations by predictive validity, the correlation between in-sample and out-of-sample rank, rather than in-sample mean, and report a twelve-tier measurement apparatus that exposes the deployment-relevant dimensions HELM and its agent-era successors collapse. The position is operationalized through three falsifiable out-of-distribution criteria with explicit thresholds; existing evidence partly supports it but is too thin to confirm. We close with a pre-registered pilot design and a field-level vision for what the next generation of agentic benchmarks should report.