×

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。

作者: Lin Liu ×
换一批
01.
arXiv (CS.AI) 2026-06-11

StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery

arXiv:2606.11851v1 Announce Type: new Abstract: Open-ended scientific discovery asks agents to move beyond executing analyses for predefined questions. Across multiple rounds of exploration, a discovery agent must decide which phenomena warrant investigation while avoiding overinterpretation, where emerging claims exceed the evidential scope of the analyses supporting them. This creates an evidence-calibration problem: the exploration trajectory must be coupled with claim status so that evidence can guide both what to investigate next and what can be claimed. We introduce StatefulDiscovery, a discovery framework that externalizes investigation state and uses it to coordinate frontier selection, evidence acquisition, and claim adjudication. We evaluate StatefulDiscovery across 40 real-data discovery tasks. Compared with several baselines, StatefulDiscovery produces more claims overall judged to be both well-supported and high-value. Ablations indicate that structured hypotheses, local adjudication, and frontier control contribute to performance. Together, these results suggest that explicit discovery state can couple exploration with evidence-calibrated claim formation.

02.
arXiv (CS.CV) 2026-06-18

Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation

Recent progress has shown promise in distilling multi-step video diffusion models into efficient few-step students. Among them, Distribution Matching Distillation (DMD) and its successor DMD2 achieved strong generation quality and fast convergence. However, due to the nature of the reverse Kullback–Leibler (KL) objective, these methods exhibit two persistent failure modes: a substantial drop in sample diversity, and visibly over-saturated outputs that deviate from real-video appearance. In this work, we propose Data-Forcing Distillation (DFD), a simple post-training framework that restores diversity and fidelity in DMD with only a single-line of code change. At its core is the teacher score discrepancy to guide the student toward the real-data distribution, pulling it to missing modes (mitigating mode collapse) and away from problematic modes absent in real data (avoiding over-saturation). We provide an in-depth theoretical analysis of our framework and validate our approach on text-to-video, image-to-video, and autoregressive video generation. With only 100–300 steps of finetuning, DFD effectively restores diversity and fidelity on both Wan2.1-1.3B and Cosmos-Predict2.5-2B model, resolving the over-saturation artifacts with significantly better video dynamics and appearance, and even outperforms the teacher model.

03.
arXiv (CS.AI) 2026-06-18

Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards

arXiv:2606.18810v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradient on routine tokens while under-crediting pivotal reasoning steps. Existing token-level credit assignment methods require resources beyond the model's own rollouts. GRPO variants rely on process reward models or ground-truth answers. Knowledge distillation assigns credit through per-token divergence but requires external teachers (On-Policy Distillation) or privileged information (On-Policy Self Distillation). However, these dependencies limit applicability in the pure RLVR setting. We observe that conditioning the model on its own verified trajectories induces a measurable per-token KL divergence between the original and conditioned distributions, and prove that distilling from a self-teacher constructed by verified trajectories leads to infeasible weighted-average solutions when multiple verified trajectories exist. We propose SC-GRPO (Self-Conditioned GRPO), which uses KL divergence mentioned before as a multiplicative weight on GRPO gradients. Across five benchmarks spanning math, code, and agentic tasks, SC-GRPO consistently outperforms 8.1% over GRPO and 5.9% over DAPO with stronger OOD performance. Moreover, SC-GRPO achieves higher performance than OPD.

04.
arXiv (CS.AI) 2026-06-12

DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks

arXiv:2606.12871v1 Announce Type: new Abstract: Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-seeking tasks by autonomously exploring web sources and synthesizing information into comprehensive responses. For SAs evaluation, prior benchmarks mainly focus on specialized tasks that are unlikely to arise in real-world user scenarios. Moreover, their reliance on coarse task-level rubrics often limits evaluation interpretability. To bridge this gap, we introduce DailyReport, an open-ended benchmark to evaluate SA capabilities on daily search tasks. It contains 150 open-ended tasks with 3,546 associated rubrics, capturing widely discussed and timely information demands of real-world users. Each task is decomposed into subtasks and evaluated with cascade rubrics across disentangled dimensions. Through cascade performance attribution and user-centric aggregation, we derive highly interpretable scores for each dimension, along with a user preference score. Our results on 17 agentic systems show that current systems still fall short of users' expectations. To facilitate future research, our dataset and code are made publicly available at https://github.com/AGI-Eval-Official/DailyReport.

05.
arXiv (CS.AI) 2026-06-16

Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs

arXiv:2606.03489v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment techniques, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), typically apply coarse-grained optimization at the sequence level. This approach often fails to address the localized nature of security flaws, where a single incorrect token choice can compromise an entire program. To bridge this gap, we introduce Tree-like Self-Play (TSP), a framework that reframes secure code generation as a fine-grained sequential decision process. Unlike standard methods that blindly maximize likelihood, TSP constructs a decision tree where the model explores branching trajectories–generating both secure "golden paths" and vulnerable variants. By treating code generation as a self-play game, the model learns to strictly discriminate against its own localized errors. This provides a dense, on-policy learning signal that forces self-correction precisely at the critical decision nodes where vulnerabilities typically emerge. Our experiments demonstrate that TSP fundamentally enhances model reliability. In Python security benchmarks, TSP boosts CodeLlama-7B's pass rate (SPR@1) to 75.8%, significantly outperforming SFT (57.0%) and unstructured self-play baselines. Crucially, TSP induces robust out-of-distribution generalization: the model not only reduces vulnerabilities in unseen categories (CWEs) by 24.5% but also successfully transfers security principles learned from C/C++ to diverse languages, including Python, Go, and JavaScript. This suggests that TSP does not merely memorize patches, but internalizes abstract, language-agnostic security logic.

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

Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models

Foundation models in language and multimodality achieve strong generalization by aligning heterogeneous data under a unified formulation and training at scale. In this report, we investigate whether this scaling recipe can be applied to robotic manipulation to achieve genuine generalization. This is challenging because, unlike text, manipulation data is heterogeneous by nature, expensive to collect, and narrow in diversity, making alignment and scale simultaneously difficult. We present Qwen-RobotManip, a generalizable Vision-Language-Action foundation model built on Qwen-VL. Qwen-RobotManip introduces a unified alignment framework across the representation, motion, and behavioral dimensions of manipulation, making large-scale multi-source training coherent rather than conflicting. This alignment capability in turn enables Qwen-RobotManip to absorb manipulation data at a scale that prior training regimes could not sustain. A human-to-robot synthesis pipeline converts egocentric hand demonstrations into robot trajectories across 15 platforms, and a rigorous curation pipeline harmonizes heterogeneous datasets. Using only open-source datasets and human videos without proprietary data collection, Qwen-RobotManip constructs a ~38,100-hour pretraining corpus and exhibits emergent generalization capabilities, including zero-shot instruction following, robustness to perturbations, reactive error recovery, and cross-embodiment transfer. We find that standard benchmarks fail to capture pretraining quality and instead adopt OOD settings including RoboCasa365, LIBERO-Plus, EBench, RoboTwin-Clean2Rand, RoboTwin-IF, and RoboTwin-XE. Qwen-RobotManip substantially outperforms prior state-of-the-art models, including $\pi$0.5, across all OOD settings, ranks 1st in RoboChallenge with a 20% relative improvement, and is validated on real-robot platforms including AgileX ALOHA, Franka, UR, and ARX.

07.
arXiv (CS.CV) 2026-06-19

JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising

Creating 3D visual illusions, a single 3D mesh that reveals entirely different semantics from various viewing angles, is a fascinating but tough challenge. Existing optimization-based methods are slow and can produce oversaturated colors. In contrast, naive stitching approaches fail to produce geometrically coherent objects. This results in visible unnatural seams and semantic leaks. In this paper, we present a fast and training-free framework for generating text-driven 3D visual illusions. Our approach decouples the generation into two stages. First, we propose a cross-space dual-branch denoising process. This process dynamically decodes 3D latents into voxel space for CLIP-guided orientation alignment and Signed Distance Field (SDF) blending, which ensures seamless geometric fusion. Second, we introduce a view-conditioned texture synthesis module that projects and aggregates view-specific 2D diffusion priors onto the fused geometry. Extensive experiments demonstrate that our method generates highly realistic, dual-semantic 3D illusions in just 3-5 minutes. It significantly outperforms existing methods in geometric integrity, semantic recognizability, and efficiency. Project page: https://siang1105.github.io/JanusMesh.github.io/

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

JE-IRT: A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory

Standard LLM evaluation practices compress diverse abilities into single scores, obscuring their inherently multidimensional nature. We present JE-IRT, a geometric item-response framework that embeds both LLMs and questions in a shared space. For question embeddings, the direction encodes semantics and the norm encodes difficulty, while correctness on each question is determined by the geometric interaction between the model and question embeddings. This geometry replaces a global ranking of LLMs with topical specialization and enables smooth variation across related questions. Building on this framework, our experimental results reveal that out-of-distribution behavior can be explained through directional alignment, and that larger norms consistently indicate harder questions. Moreover, JE-IRT naturally supports generalization: once the space is learned, new LLMs are added by fitting a single embedding. The learned space further reveals an LLM-internal taxonomy that only partially aligns with human-defined subject categories. We also show that simple linear probes of the embedding space recover cross-subject ability directions, such as an arithmetic axis that highlights quantitatively demanding questions in seemingly distant subjects like virology and global facts. JE-IRT thus establishes a unified and interpretable geometric lens that connects LLM abilities with the structure of questions, offering a distinctive perspective on model evaluation and generalization.

09.
arXiv (CS.AI) 2026-06-11

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

arXiv:2606.11324v1 Announce Type: cross Abstract: We introduce Embodied-R1.5, a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied reasoning capabilities, spanning embodied cognition, task planning, correction, and pointing, within a single architecture toward general physical intelligence. Leveraging three automated data construction pipelines to significantly expand the data coverage of critical capabilities, we build a large-scale data system of over 15B tokens, and design a multi-task balanced RL recipe to alleviate heterogeneous task conflicts. We further introduce a Planner-Grounder-Corrector (PGC) closed-loop framework that enables a single model to autonomously execute and self-correct over long-horizon tasks. With only 8B parameters, Embodied-R1.5 achieves SOTA on 16 out of 24 embodied VLM benchmarks, surpassing leading models like Gemini-Robotics-ER-1.5 and GPT-5.4. Benefiting from the internalized embodied capabilities, Embodied-R1.5 can be fine-tuned into a VLA with only a small amount of data, outperforming leading VLA models like $\pi_{0.5}$ across 4 popular manipulation benchmark suites. We further conduct extensive zero-shot real-robot experiments, validating performance in instruction following, affordance grounding, articulated object manipulation, and long-horizon complex tasks, demonstrating strong generalization to the physical world. We open-source model weights, datasets, training code, and EmbodiedEvalKit, an evaluation framework tailored for embodied tasks, to facilitate future research in EFMs.

10.
arXiv (CS.LG) 2026-06-12

FedBiCross: Personalized One-Shot Federated Learning on Medical Images

arXiv:2601.01901v4 Announce Type: replace Abstract: Data-free knowledge distillation-based one-shot federated learning (OSFL) trains a model in a single communication round without sharing raw data, making OSFL attractive for privacy-sensitive medical applications. However, existing methods aggregate predictions from all clients to form a global teacher. Under non-IID data, conflicting predictions dilute each other during averaging, yielding less informative soft labels that weaken distillation. We propose FedBiCross, a personalized OSFL framework with three stages: (1) clustering clients by model output similarity to form coherent sub-ensembles, (2) bi-level cross-cluster optimization that learns adaptive weights to selectively leverage beneficial cross-cluster knowledge while suppressing negative transfer, and (3) personalized distillation for client-specific adaptation. Experiments on four medical image datasets demonstrate that FedBiCross consistently outperforms state-of-the-art baselines across different non-IID degrees.

11.
arXiv (CS.AI) 2026-06-16

Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call

arXiv:2606.15225v1 Announce Type: cross Abstract: Large-scale learner-task interaction data are crucial for intelligent educational systems but are costly to collect and constrained by privacy and learner engagement. Learner simulators play a critical role in simulating scalable learner behavior without the need for continuous involvement of real learners. However, existing methods are predominantly individual-centric, pairing a simulator with each learner to iteratively infer latent knowledge states from dense interaction histories, which is both data- and computation-intensive, and fragile in cold-start scenarios. We propose a cohort-aware roll-call simulation paradigm that first constructs cohort-level proficiency priors and refines individual learner states through a small number of targeted diagnostic queries. Based on this paradigm, we introduce Edu-Theater, an LLM-powered agent system that performs cohort-aware learner simulation via a teacher agent and retrospective roll-call probing over learner logs. Edu-Theater enables scalable future behavior simulation without the need for dense per-learner histories. Experiments on two real-world datasets demonstrate that Edu-Theater achieves higher simulation accuracy with significantly fewer LLM calls, producing synthetic data that enhances downstream applications such as adaptive testing.

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

Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models

arXiv:2509.22020v2 Announce Type: replace Abstract: While recent advances in machine learning have equipped Weather Foundation Models (WFMs) with substantial generalization capabilities across diverse downstream tasks, the escalating computational requirements associated with their expanding scale increasingly hinder practical deployment. Current Parameter-Efficient Fine-Tuning (PEFT) methods, designed for vision or language tasks, fail to address the unique challenges of weather downstream tasks, such as variable heterogeneity, resolution diversity, and spatiotemporal coverage variations, leading to suboptimal performance when applied to WFMs. To bridge this gap, we introduce WeatherPEFT, a novel PEFT framework for WFMs incorporating two synergistic innovations. First, during the forward pass, Task-Adaptive Dynamic Prompting (TADP) dynamically injects the embedding weights within the encoder to the input tokens of the pre-trained backbone via internal and external pattern extraction, enabling context-aware feature recalibration for specific downstream tasks. Furthermore, during backpropagation, Stochastic Fisher-Guided Adaptive Selection (SFAS) not only leverages Fisher information to identify and update the most task-critical parameters, thereby preserving invariant pre-trained knowledge, but also introduces randomness to stabilize the selection. We demonstrate the effectiveness and efficiency of WeatherPEFT on three downstream tasks, where existing PEFT methods show significant gaps versus Full-Tuning, and WeatherPEFT achieves performance parity with Full-Tuning using fewer trainable parameters. The code of this work is available at https://github.com/ShileiCao/WeatherPEFT.

13.
arXiv (CS.LG) 2026-06-15

Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models

arXiv:2606.14222v1 Announce Type: new Abstract: The rapid evolution of Time Series Foundation Models (TSFMs) has advanced zero-shot forecasting across diverse domains. Inspired by the current form of Large Language Models, future TSFMs may be offered as commercialized, closed-source API services. However, many existing online adaptation methods still rely on white-box access for parameter fine-tuning or gradient backpropagation. This paradigm mismatch raises a question: In black-box online adaptation for TSFMs, what should we learn? We answer this with an insight: the predictive errors of the base model are conditioned on both the input and output of the base model (i.e., the context of errors). To validate this insight, we propose ORCA (Online Residual Contextual Adaptation). We conduct extensive experiments across 5 state-of-the-art TSFMs and 8 datasets to demonstrate the effectiveness of our approach. Furthermore, through ablation studies, we quantitatively analyze the impact of different adapter learning hypotheses on the final adaptation performance in black-box online adaptation. Code available at https://github.com/Fifthky/ORCA.

14.
arXiv (CS.CL) 2026-06-12

Agents' Last Exam

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long horizon, economically valuable, real world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 sub fields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is below 1%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP relevant impact.

15.
arXiv (CS.CV) 2026-06-11

Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-ID

In cloth-changing person re-identification (CCReID), it is critical to learn clothes-invariant feature, which can provide discriminative ID features that remain robust against clothing changes. However, a spurious correlation currently limits existing ReID methods from effectively extracting these clothing-invariant features. This spurious correlation arises from clothing ownership: clothing is rarely shared across different identities, so models tend to memorize clothing cues for identity recognition, and this strategy generalizes poorly to unseen clothing. In this paper, we propose Causal Clothes-Invariant Learning (CCIL), which explicitly shifts CC-ReID from likelihood learning P (Y|X) to causal intervention learning P (Y|do(X)) to block the clothing shortcut. CCIL realizes this intervention through three modules: a Confounder Dictionary, an Intervention Module, and Disentangle Regularization. The causality-based modeling makes the entire model naturally clothes-invariant, effectively preventing the capture of spurious correlations in feature learning. Extensive experiments validate the effectiveness of CCIL. On PRCC and DeepChange datasets, CCIL achieves Rank-1 accuracies of 66.4% and 59.2%, outperforming state-of-the-art methods by 1.4 and 4.1 percentage points, respectively.

16.
arXiv (CS.CV) 2026-06-11

EventRadar: Long-Range Visual UAV Discovery through Spatiotemporal Event Sensing

Unauthorized unmanned aerial vehicle (UAV) activity around airports, public venues, and other sensitive sites has made protected-airspace monitoring increasingly important. A practical sensing system must search a wide angular region, find small long-range targets, and return both bearing support and UAV-specific evidence before a restricted perimeter is breached. Existing UAV detection paths often rely on spatially organized evidence, such as body extent, silhouette, or track continuity. At long range, however, these cues become difficult to preserve and verify as the target footprint weakens and its image-plane support shrinks. EventRadar follows a complementary cue: propeller-induced temporal periodicity, which recent event-camera sensing studies have shown can reveal UAV-specific motion after appearance becomes weak. We extend this cue to kilometer-scale active sensing with an event-camera prototype. Scene-Anchored Geometry Evidence (SAGE) fuses scanning events with IMU pose to maintain a bearing-indexed scene memory, separating transient candidate support from persistent background clutter. Comb-guided Harmonic-Group Learned Iterative Shrinkage and Thresholding Algorithm (CHG) then treats each candidate as a weak high-rate timing signal and recovers phase-insensitive harmonic evidence with fixed compute. Compared with related event-camera baselines on 700-1500 m UAV event recordings, EventRadar achieves 0.990 mAP$_{.3}$ and 0.949 F1$_{.3}$, reduces FN$_{.3}$ to 0.009, and shows real-time feasibility in prototype profiling.

17.
arXiv (CS.AI) 2026-06-11

Harness In-Context Operator Learning with Chain of Operators

arXiv:2606.12318v1 Announce Type: cross Abstract: Neural operators approximate mappings between function spaces, but often generalize poorly to other operators and usually require fine-tuning or retraining. In-Context Operator Networks (ICON) addresses this issue by prompting the model with numerical context so that the model learns specific operators from prompts and adapt to different operators without fine-tuning. However, ICON may still fail to generalize to out-of-distribution (OOD) operator tasks. Inpired by the success of harness engineering of Large Language models (LLMs), we introduce Chain of Operators (CHOP), a framework that harness a frozen ICON to OOD operator tasks without updating its parameters. Specifically, CHOP constructs a chain of operators consisting of explicit elementary transformations and the frozen ICON. Experiments on a scalar conservation law and a mean-field control problem show that CHOP reduces relative inference error over direct ICON evaluation, while each operator in the chain remains interpretable and in closed form. A chain constructed on one PDE family further generalizes to a different family, indicating shared mechanisms across harness systems.

18.
arXiv (CS.LG) 2026-06-11

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning

arXiv:2606.12372v1 Announce Type: cross Abstract: Human-in-the-loop reinforcement learning (HiL-RL) has emerged as an effective paradigm for real-world robotic manipulation, enabling online policy improvement with human guidance. However, current HiL-RL frameworks remain intervention-intensive, relying on frequent human corrections to redirect the policy out of unproductive exploration, which incurs high labor cost and limits real-world scalability. To address this, we propose UniIntervene, an agentic intervention model that detects unproductive exploration and autonomously recovers the policy toward high-value states, taking over the bulk of interventions from human operators. Specifically, UniIntervene first performs future-conditioned action-value estimation, predicting the latent consequence of the current action and evaluating its induced value, which provides a more stable progress signal. Building on this, a temporal value-risk critic aggregates recent value dynamics and triggers intervention when the estimated value exhibits sustained stagnation or degradation. When intervention is required, UniIntervene retrieves a high-value recovery target from a memory of past intervention episodes and produces executable corrective actions through a goal-conditioned recovery policy. In this way, UniIntervene turns intervention from passive human correction into a value-aware recovery process for efficient real-world RL. Extensive experiments on diverse real-world manipulation tasks demonstrate that UniIntervene improves the average success rate by 8.6% while reducing human interventions by 57% relative to state-of-the-art HiL-RL baselines.

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

Vero: An Open RL Recipe for General Visual Reasoning

What does it take to build a visual reasoner that works across charts, science, spatial understanding, and open-ended tasks? The strongest vision-language models (VLMs) suggest that broad visual reasoning is within reach, yet their closed data and reinforcement learning (RL) pipelines make their gains difficult to study, reproduce, or extend. We introduce Vero, a family of fully open VLMs that match or exceed existing open-weight models across diverse visual reasoning tasks. We scale RL data and rewards across six broad task categories, constructing Vero-600K, a 600K-sample dataset from 59 datasets, and designing task-routed rewards that handle heterogeneous answers. Across VeroEval, our 30-benchmark suite, Vero-600K outperforms existing RL datasets under controlled comparisons. Applied to five starting models, Vero variants gain 2.9-5.4 points on average over their initial models. Notably, Vero-Qwen3I-8B, trained on the Instruct model, surpasses Qwen3-VL-8B-Thinking by 3.8 points on average without additional distillation. Systematic ablations reveal that different task categories elicit distinct reasoning patterns and that broad gains depend on learning them jointly rather than in isolation. All data, code, and models are publicly available.

20.
arXiv (CS.AI) 2026-06-15

StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents

arXiv:2606.07027v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has become a promising approach for improving GUI Agents in long-horizon, stochastic digital environments, but trajectory-level success feedback is too sparse to provide reliable credit assignment for intermediate exploration steps. To mitigate this issue, recent studies introduce Process Reward Models (PRMs), which provide finer-grained training feedback through global milestone verification or local step-level evaluation. However, these methods still suffer from two level-specific limitations: global milestone decomposition is subjective and singular, making it difficult to accommodate the multiple valid execution paths in real GUI tasks, while fixed local judging windows may miss long-range key evidence or dilute the decision signal with irrelevant frames. Inspired by stain-tracing mechanisms in network flow analysis, we propose StainFlow, an entity-stain-flow process reward model for GUI Agents. To reduce the subjectivity of global partitioning, we introduce the Global Entity Stain Tracking module, which extracts visually verifiable task entities and tracks how their stain concentrations and states evolve along the trajectory, allowing task phases to be objectively separated by changes in the entity evidence flow. To improve the accuracy of local verification, we introduce the Local Stain Evidence Linking module. Centered on the triggering entities of each candidate key node, it retrieves relevant steps based on their stain concentrations and state changes, and dynamically constructs high-density evidence windows for verifying true key nodes. Extensive experiments on AndroidWorld and OGRBench show that StainFlow relatively improves online RL success by 3.2% and trajectory completion judgment accuracy by 1.8%.

21.
arXiv (CS.CL) 2026-06-11

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the evidence, and carry the resulting lessons into later attempts. We study how an AI agent can run this loop autonomously over long horizons. We introduce Arbor, a general framework for autonomous research that combines a long-lived coordinator, short-lived executors, and Hypothesis Tree Refinement (HTR), a persistent tree that links hypotheses, artifacts, evidence, and distilled insights across time. The coordinator manages global research strategy over the tree, while executors implement and test individual hypotheses in isolated worktrees. As results return, Arbor updates the tree, propagates reusable lessons, refines the search frontier, and admits verified improvements. This design turns autonomous research from a sequence of local attempts into a cumulative process in which strategy, execution, and evidence are carried across time. We evaluate Arbor under Autonomous Optimization (AO), an operational setting where an agent improves an initial research artifact through iterative experimentation without step-level human supervision. Across six real research tasks in model training, harness engineering, and data synthesis, Arbor achieves the best held-out result on all six tasks, attaining more than 2.5x the average relative held-out gain of Codex and Claude Code under the same task interface and resource budget. On MLE-Bench Lite, Arbor reaches 86.36% Any Medal with GPT-5.5, the strongest result in our comparison.

22.
arXiv (CS.CL) 2026-06-11

Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization

Reinforcement Learning (RL) with verifiable environments has emerged as a powerful approach for enhancing the reasoning capabilities of Large Language Models (LLMs). While prior research demonstrates that scaling environment quantity improves RL performance, existing manual or individual construction methods suffer from linear scaling limits, thereby hindering scalable reasoning generalization. This paper introduces RACES (Recursive Automated Composition for Environment Scaling), a framework that conceptualizes verifiable environments as composable building blocks that can be recursively assembled. The key insight is that when the codomain (output type) of one environment matches the domain (input type) of another, they can be automatically fused into a new verifiable environment, enabling recursive composition. RACES is implemented with 300 individual environments and defines a set of composition operators (\textsc{SEQUENTIAL}, \textsc{PARALLEL}, \textsc{SORT}, and \textsc{SELECT}) that induce diverse reasoning patterns. Extensive experiments show that RL training on these composite environments consistently enhances reasoning generalization. Specifically, RACES improves DeepSeek-R1-Distill-Qwen-14B by an average of 3.1 points (from 48.2 to 51.3) and boosts Qwen3-14B performance from 58.8 to 61.1 on six benchmarks, which are unseen during the construction of training environments. Moreover, RACES achieves performance comparable to training on 300 individual environments using only 50 base environments, demonstrating significant efficiency in environment utilization.

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

Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs

arXiv:2606.15258v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly capable of mathematical problem solving and can even assist with research-level proofs, yet we still lack a scalable and reproducible way to measure step-level reasoning in long proofs across diverse sources. This evaluation gap limits trustworthy AI assistance in proof-certified scientific progress. Existing evaluations often emphasize final answers or rely on costly expert grading, while end-to-end proof generation remains open-ended and hard to verify automatically. We introduce Mask-Proof, a pipeline that turns real proofs into automatically checkable masked-step tasks. It masks key formula steps, provides the necessary surrounding context, and evaluates model reconstructions with an LLM-based equivalence judge using repeated votes for stability. The resulting Mask-ProofBench contains 292 curated problems across diverse research areas. Experiments with 17 models show that reasoning-enhanced models outperform standard models by 12% to 27%. Our evaluator achieves 96.8% agreement with expert annotators, enabling faithful, reproducible, and comparable measurement of step-level mathematical reasoning. Benchmark, annotations, and code are available at https://github.com/weating/Mask-Proof.

24.
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.

25.
arXiv (CS.CV) 2026-06-18

APT: Atomic Physical Transitions for Causal Video-Language Understanding

Physical events are not understood by their names alone, but by the causal state changes that compose them. A clip-level label such as "bounce" can be correct while hiding the process that makes the event physically valid, from support loss and contact onset to rebound and settling. To make this hidden process explicit, we introduce Atomic Physical Transitions (APTs): minimal, temporally localized state changes that bind a visible cue to an active physical mechanism and before/after dynamical regimes. An APT chain represents a video as an ordered causal transition sequence rather than a single aggregate event label: event labels tell what happened; APT chains explain why it happened. To make APTs learnable by VLMs, we construct mixed-source APT data from human annotations and simulator ground truth, covering 14 transition types across contact, gravity, friction, and rotation/stability, with 27,303 timed instances over 1,246 trials. Using this data, we find that current VLMs miss transition-level physics, with zero-shot recall at most 14% and errors dominated by missed transitions. Direct fine-tuning on APT chains improves transition detection but causes event-level forgetting, indicating that the model learns a specialized answer format rather than a reusable physical representation. We therefore propose APT-Tune, a parameter-efficient recipe that teaches VLMs to use causal transitions without forgetting how to answer video questions. It combines image-pad-aware supervision, format-conditional co-training, and mechanism-conditioned domain-to-type decoding to make APT learning format-robust and physically grounded. With only 11 M LoRA parameters on Qwen3-VL-2B, APT-Tune substantially improves APT recall while also improving event-level video transfer. These results show that APTs are not a new answer format, but a human-aligned causal supervision signal for physical video understanding.