# Research Papers — 2026-05 · bundle page 269 of 326 > Full-text markdown of papers #13401–13450 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/269 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/268.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/270.md) ### A Linear-Transformer Hybrid for SNP-Based Genotype-to-Phenotype Prediction in Grapevine Authors: Yibin Wang, Murukarthick Jayakodi, Silvas Kirubakaran, Ambika Chandra, Azlan Zahid Published: 2026-05-07 Categories: q-bio.GN, cs.AI arXiv: https://arxiv.org/abs/2605.06762v1 Robust genotype-to-phenotype (G2P) prediction is essential for accelerating breeding decisions and genetic gain. However, it remains challenging to measure complex traits under variable field conditions and across years. In this study, we propose a linear-Transformer approach, LiT-G2P (Linear-Transformer Genotype-to-Phenotype), an automated predictive framework that integrates additive genetic variance effects with Transformer-based nonlinear interactions using genome-wide single-nucleotide polymorphisms (SNPs) data. We evaluated LiT-G2P on a panel of diverse grape accessions, genotyped with SNP markers and measured for phenotypes across two consecutive years. Target phenotypic traits include leaf hair density and trichome density of grapevines. Across both single-year and cross-year testing scenarios, LiT-G2P consistently improves prediction performance compared with baseline models. For hair density, LiT-G2P achieves the lowest error in both single-year and cross-year evaluations, with RMSEs of 0.469 and 0.454, respectively, while maintaining strong tolerance accuracies of 79.2% and 74.6%, respectively. For trichome density, LiT-G2P also presents the best overall G2P performance. In addition, we extract model-prioritized SNPs from attention weights and apply genotype-stratified analysis to provide interpretable candidate marker for downstream validation. These results demonstrate that integrating stable additive effects with learned interaction patterns can enhance cross-year robustness and support practical SNP-based predictive modeling for genomic selection. --- ### Weblica: Scalable and Reproducible Training Environments for Visual Web Agents Authors: Oğuzhan Fatih Kar, Roman Bachmann, Yuanzheng Gong, Anders Boesen Lindbo Larsen, Afshin Dehghan Published: 2026-05-07 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.06761v1 The web is complex, open-ended, and constantly changing, making it challenging to scale training data for visual web agents. Existing data collection attempts remain limited to offline trajectories for supervised fine-tuning or a handful of simulated environments for RL training, thus failing to capture web diversity. We propose Weblica (Web Replica), a framework for constructing reproducible and scalable web environments. Our framework leverages 1) HTTP-level caching to capture and replay stable visual states while preserving interactive behavior and 2) LLM-based environment synthesis grounded in real-world websites and core web navigation skills. Using this framework, we scale RL training to thousands of diverse environments and tasks. Our best model, Weblica-8B, outperforms open-weight baselines of similar size across multiple web navigation benchmarks while using fewer inference steps, scales favorably with additional test-time compute, and is competitive with API models. --- ### R$^3$L: Reasoning 3D Layouts from Relative Spatial Relations Authors: Zhifeng Gu, Yuqi Wang, Bing Wang Published: 2026-05-07 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2605.06758v2 Relative spatial relations provide a compact representation of spatial structure and are fundamental to relative spatial reasoning in 3D layout generation. Recent works leverage Multimodal Large Language Models (MLLMs) to infer such relations, but the inferred relations are often unreliable and are typically handled with post-hoc heuristics. In this paper, we propose R$^3$L, a general framework that improves the reliability and consistency of relative spatial reasoning for 3D layout generation. Our key motivation is that multi-hop reasoning requires repeated reference-frame transformations, which accumulate errors in inferred relations and lead to semantic and metric drift. To mitigate this, we propose invariant spatial decomposition to break coupled relation chains, and consistent spatial imagination to promote self-consistency through an imagine-and-revise loop. We further introduce supportive spatial optimization to ease pose optimization via global-to-local coordinate re-parameterization. Extensive experiments across diverse scene types and instructions demonstrate that R$^3$L produces more physically feasible and semantically consistent layouts. Notably, our analysis shows that resolving frame-induced inconsistencies is crucial for reliable multi-hop relative spatial reasoning. The code is available at https://github.com/Neal2020GitHub/R3L. --- ### Physics-based Digital Twins for Integrated Thermal Energy Systems Using Active Learning Authors: Umme Mahbuba Nabila, Paul Seurin, Linyu Lin, Majdi I. Radaideh Published: 2026-05-07 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2605.06756v1 Real-time supervisory control of thermal energy distribution systems requires digital twins that are accurate, interpretable, and uncertainty-aware, yet remain data and computationally efficient. High-fidelity simulations alone are costly, while purely data-driven surrogates often lack robustness. To address these challenges, this work proposes an active learning (AL) framework that couples system-level Modelica simulations with four simpler physics-informed and data-driven surrogate modeling approaches: deterministic Sparse Identification of Nonlinear Dynamics with Control (SINDyC), its probabilistic multivariate-Gaussian extension (MvG-SINDyC), feedforward neural network (FNN), and gated recurrent unit (GRU) network. Tailored to each surrogate, model-specific AL query strategies are employed, including Mahalanobis-distance sampling in coefficient space for MvG-SINDyC and error-based sampling in prediction space for SINDyC, FNN, and GRU, allowing the learning process to prioritize dynamically informative trajectories. The proposed approach is demonstrated on the glycol heat exchanger (GHX) subsystem of the Thermal Energy Distribution System (TEDS) at Idaho National Laboratory. Across key GHX outputs--the bypass mass flow rate $\dot{m}_{\mathrm{GHX}}$ and heat transfer rate $Q_{\mathrm{GHX}}$-the AL framework achieves comparable predictive accuracy using as few as one-fifth of the simulation trajectories required by random sampling. Among the evaluated surrogates, the GRU achieves the highest predictive fidelity, while SINDyC remains the most computationally efficient and interpretable. The probabilistic MvG-SINDyC surrogate further enables uncertainty quantification and exhibits the largest computational gains under AL. --- ### Skip What You Can Predict: Predictive Repositioning for Policy Optimization for Efficient LLM Training Authors: Ismam Nur Swapnil, Aranya Saha, Tasneea Zahra, Tanvir Ahmed Khan, Mohammad Ariful Haque, Ser-Nam Lim Published: 2026-05-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.06755v2 Reinforcement learning with verifiable rewards (RLVR) can improve the reasoning ability of large language models, but repeatedly updating a policy on the same rollout batch is expensive: every additional update requires another backward pass, and multi-step methods pay for all intermediate optimization steps. We introduce Predictive Repositioning for Policy Optimization (PrePO), which uses two observed optimizer transitions to estimate a farther point along the same-batch optimization trajectory, moves partway toward that point, evaluates the original objective there, and applies a corrective update. This gives PrePO a fixed active cost that does not grow with the virtual optimization depth. Our analysis gives finite-horizon error bounds for AdamW and Muon and shows that sufficiently accurate endpoint estimates preserve the usual descent and convergence behavior of smooth gradient descent. In RLVR experiments, PrePO reaches matched performance targets in fewer optimization steps and lower wall-clock time than the corresponding baselines. We further evaluate the same update mechanism in supervised fine-tuning on a different dataset, showing that its use is not restricted to the original RLVR setting. Together, these results suggest that PrePO provides a practical mechanism for approximating repeated same-batch optimization while avoiding the cost of explicitly executing every intermediate update. --- ### Gradient Extrapolation-Based Policy Optimization Authors: Ismam Nur Swapnil, Aranya Saha, Tanvir Ahmed Khan, Mohammad Ariful Haque, Ser-Nam Lim Published: 2026-05-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.06755v1 Reinforcement learning is widely used to improve the reasoning ability of large language models, especially when answers can be automatically checked. Standard GRPO-style training updates the model using only the current step, while full multi-step lookahead can give a better update direction but is too expensive because it needs many backward passes. We propose Gradient Extrapolation-Based Policy Optimization (GXPO), a plug-compatible policy-update rule for GRPO-style reasoning RL. GXPO approximates a longer local lookahead using only three backward passes during an active phase. It reuses the same batch of rollouts, rewards, advantages, and GRPO loss, so it does not require new rollouts or reward computation at the lookahead points. GXPO takes two fast optimizer steps, measures how the gradients change, predicts a virtual K-step lookahead point, moves the policy partway toward that point, and then applies a corrective update using the true gradient at the new position. When the lookahead signal becomes unstable, GXPO automatically switches back to standard single-pass GRPO. We also give a plain-gradient-descent surrogate analysis that explains when the extrapolation is exact and where its local errors come from. Across Qwen2.5 and Llama math-reasoning experiments, GXPO improves the average sampled pass@1 by +1.65 to +5.00 points over GRPO and by +0.14 to +1.28 points over the strongest SFPO setting, while keeping the active-phase cost fixed at three backward passes. It also achieves up to 4.00x step speedup, 2.33x wall-clock speedup, and 1.33x backward-pass speedup in reaching GRPO's peak accuracy. --- ### A Statistical Framework for Algorithmic Collective Action with Multiple Collectives Authors: Claudio Battiloro, Pietro Greiner, Dario Rancati, Bret Nestor, Oumaima Amezgar, Francesca Dominici Published: 2026-05-07 Categories: stat.ME, cs.AI arXiv: https://arxiv.org/abs/2605.06749v1 As learning systems increasingly shape everyday decisions, Algorithmic Collective Action (ACA), i.e., users coordinating changes to shared data to steer model behavior, offers a complement to regulator-side policy and corporate model design. Real-world collective actions have traditionally been decentralized and fragmented into multiple collectives, despite sharing overarching objectives, with each collective differing in size, strategy, and actionable goals. However, most of the ACA literature focuses on single collective settings. To address this, we propose the first comprehensive statistical framework for ACA with multiple collectives acting on the same system. In particular, we focus on collective action in classification, studying how multiple collectives can influence a classifier's behavior. We provide quantitative statistical bounds on the success of the collectives, considering the role and the interplay of the collectives' sizes and the alignment of their goals. We make such bounds computable by each collective with only partial knowledge of other collectives' sizes and strategies. Finally, we numerically illustrate our framework on simulations inspired by interventions for climate adaptation in smart cities, demonstrating the usefulness of our bounds. --- ### HumanNet: Scaling Human-centric Video Learning to One Million Hours Authors: Yufan Deng, Daquan Zhou Published: 2026-05-07 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2605.06747v1 Progress in embodied intelligence increasingly depends on scalable data infrastructure. While vision and language have scaled with internet corpora, learning physical interaction remains constrained by the lack of large, diverse, and richly annotated human activity data. We present HumanNet, a one-million-hour human-centric video corpus that captures how humans interact with the physical world at scale. HumanNet spans both first-person and third-person perspectives and covers fine-grained activities, human-object interactions, tool use, and long-horizon behaviors across diverse real-world environments. Beyond raw video, the dataset provides interaction-centric annotations, including captions, motion descriptions, and hand and body-related signals, enabling motion-aware and interaction-aware learning. Beyond scale, HumanNet introduces a systematic data curation paradigm for embodied learning, where human-centric filtering, temporal structuring, viewpoint diversity, and annotation enrichment are treated as first-class design principles. This design transforms unstructured internet video into a scalable substrate for representation learning, activity understanding, motion generation, and human-to-robot transfer. We conduct a first-step validation on the value of this design through controlled vision-language-action ablation: under a fixed set of validation data, continued training from the Qwen VLM model with 1000 hours of egocentric video drawn from HumanNet surpasses the continued training with 100 hours of real-robot data from Magic Cobot, indicating that egocentric human video could be a scalable and cost-effective substitute for robot data. By building this project, we aim to explore the opportunity to scale embodied foundation models using human-centric videos, rather than relying solely on robot-specific data. --- ### The Causally Emergent Alignment Hypothesis: Causal Emergence Aligns with and Predicts Final Reward in Reinforcement Learning Agents Authors: Federico Pigozzi, Michael Levin Published: 2026-05-07 Categories: cs.NE arXiv: https://arxiv.org/abs/2605.06746v1 A hallmark of life on Earth is the ability of agents to exert causal power and be drivers of subsequent events. This is key to cognition at all scales. Causal emergence, measuring the degree to which an agent exerts unique predictive power on its future, is one consequence of causal power. Indeed, recent discoveries have shown that biological agents, even minimal ones, increase their causal emergence after learning new memories. However, there is a major knowledge gap regarding how causally emergent artificial agents are. We focused on Reinforcement Learning (RL) of neural-network agents across an array of environmental conditions, encompassing different algorithms, agent architectures, and six environments arranged on a complexity spectrum. For consistency, we computed the causal emergence of their latent-space representations over their lifetimes. We used the recently proposed ΦID to estimate causal emergence and tested how it related to learning performance. Our results suggested a Causally Emergent Alignment Hypothesis: successful agents exhibited causal emergence that was consistently predictive of final reward early in training and whose representational dynamics aligned with reward improvement in most tasks. This idea suggests that causal emergence may be a previously undisclosed axis of reorganization of neural representations in RL agents, with the potential to establish causal relationships and interventions that will lead to better RL agents. Our work also highlights the alignment between causal emergence and learning as another way biological and artificial creatures compare. --- ### A Closed-Form Upper Bound for Admissible Learning-Rate Steps in Belief-Space Dynamics Authors: Zixi Li, Youzhen Li Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06741v1 Learning-rate steps are usually treated as hyperparameters. This paper isolates a local beliefspace calculation: when an update is modeled as a projected forward step on the probability simplex, admissibility means contractivity in the natural KL/Bregman geometry. Under this model, the upper bound of an admissible step is not a tuning slogan but a formula. --- ### Geometric Kolmogorov--Arnold Network (GeoKAN) Authors: Abhijit Sen, Bikram Keshari Parida, Giridas Maiti, Mahima Arya, Denys I. Bondar Published: 2026-05-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.06740v1 We introduce Geometric Kolmogorov--Arnold Networks (GeoKANs), a family of geometry-aware KAN-type models in which approximation is carried out in learned, geometry-adapted coordinates rather than in fixed Euclidean input coordinates. GeoKAN achieves this by learning a diagonal Riemannian metric that warps the input before basis expansion and feature mixing. The learned metric provides a geometric inductive bias through local length scaling and volume distortion, and in physics-informed settings it also affects the differential structure seen by the model. Within this framework, we develop three main variants, namely GeoKAN-NNMetric, GeoKAN-$γ$, and LM-KAN. For LM-KAN, we further consider three basis-specific versions, LM-KAN-RBF, LM-KAN-Wav, and LM-KAN-Fourier. These variants allow us to study geometry-aware KAN models both as general function approximators and as surrogates in physics-informed learning. By stretching regions with rapid variation and compressing smoother regions, GeoKAN reallocates representational resolution in a task-dependent manner, allowing the model to place capacity where it is most needed. As a result, GeoKAN is well suited to sharp, stiff, localized, and strongly non-uniform regimes arising in scientific machine learning and differential-equation problems. --- ### Trust Without Trusting: A Recomputable Trust Protocol for Autonomous Agents Authors: Lars Kersten Kroehl Published: 2026-05-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2605.06738v2 Autonomous AI agents already transact at production scale -- 69,000 bots, 165 million transactions, $50 million in volume on a single marketplace -- and any party can verify a signed credential without a central service. In an open agent world that covers most of what trust requires: there are no universal borders, and each party chooses for itself whom to deal with. Borders appear only where a closed space draws one -- a marketplace, a platform, or a consortium sets house rules. Whoever draws the border holds the authority to apply it, and may apply it as they choose, behind closed doors. This paper addresses the gap that opens there: when you rely on someone else's border, how do you check that they applied their own published rules -- taking no one's word for it, and handing the check to no new trusted party? Our answer is the Combined Evidence Protocol (CEP): a five-condition predicate any party recomputes from anchored data, turning "did the boundary-owner follow its own admission rules" into a fact anyone verifies rather than a claim anyone believes. The move that secures optimistic rollups secures this -- correctness rests on recomputation, so the measurement belongs to everyone and the oracle problem dissolves. Its load-bearing setting is a consortium of co-equal, mutually distrusting peers under a shared charter, each able to verify, independently, that the rules they jointly agreed are the rules being applied. CEP belongs to the family of trustless systems -- optimistic and zero-knowledge rollups, verifiable ML, self-sovereign-identity predicates. The infrastructure beneath it is live: a W3C VC + DID trust layer running since March 2026, anchored on Base L2, continuing arXiv:2605.06738 and standing on its own. --- ### A Self-Healing Framework for Reliable LLM-Based Autonomous Agents Authors: Cheonsu Jeong, Younggun Shin Published: 2026-05-07 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.06737v1 Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution errors, and inconsistent reasoning. This paper proposes a reliability-aware self-healing framework for LLM-based software agents. The framework integrates failure detection, reliability assessment, and automated recovery mechanisms. First, we define a taxonomy of failure types and introduce a quantitative reliability assessment model. Next, we propose a failure detection method that identifies abnormal agent behavior based on execution patterns and output consistency. Finally, we design a self-healing mechanism that dynamically recovers from failures through adaptive replanning and corrective prompting strategies. The proposed framework was implemented in a multi-agent workflow environment and evaluated using real-world task scenarios. Experimental results demonstrate that our approach significantly increases task success rates, reduces failure propagation, and enhances overall system robustness compared to existing methods. In particular, this study distinguishes itself by establishing an integrated monitoring system that combines the agent's internal reasoning process with external execution results. These findings are expected to contribute to securing the stability of advanced autonomous systems and lowering the barriers to LLM adoption in production environments. --- ### STDA-Net: Spectrogram-Based Domain Adaptation for cross-dataset Sleep Stage Classification Authors: Unaza Tallal, Shruti Kshirsagar, Ankita Shukla Published: 2026-05-07 Categories: cs.LG, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2605.06736v1 Accurate sleep stage classification across datasets remains challenging due to variability in EEG channel montages, sampling rates, recording environments, and subject populations. Although deep learning has shown considerable promise for automated sleep staging, most existing cross-dataset methods rely on one-dimensional EEG signal representations, whereas the use of two-dimensional spectrogram-based inputs within an unsupervised domain adaptation framework has remained largely unexplored. Here, we propose STDA-Net (Spectrogram-based Temporal Domain Adaptation Network), a framework that combines a convolutional neural network (CNN) for spectrogram-based feature extraction, a bidirectional long short-term memory (BiLSTM) module for temporal modeling of sleep dynamics, and a domain-adversarial neural network (DANN) for source-to-target feature alignment without requiring any labeled target-domain data during training. Experiments are conducted on three publicly available datasets Sleep-EDF, SHHS-1, and SHHS-2 under six cross-dataset transfer settings. Results show that the proposed framework achieves an average accuracy of 89.03% and an average macro F1-score of 87.64%, consistently outperforming existing 1D baseline methods in terms of balanced classification performance, with substantially lower variance across five independent runs, indicating improved stability and reproducibility. Overall, these findings demonstrate that 2D spectrogram-based representations, combined with temporal modeling and adversarial domain adaptation, provide a robust and competitive alternative to conventional 1D EEG inputs for cross-dataset sleep staging. --- ### Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning Authors: Kuo-Chung Peng, Samuel Yen-Chi Chen, Jiun-Cheng Jiang, Chen-Yu Liu, En-Jui Kuo, Yun-Yuan Wang, Prayag Tiwari, Andrea Ceschini, Chi-Sheng Chen, Yu-Chao Hsu, Chun-Hua Lin, Tai-Yue Li et al. Published: 2026-05-07 Categories: cs.LG, cs.AI, quant-ph arXiv: https://arxiv.org/abs/2605.06734v2 Fast Weight Programmers (FWPs) encode temporal dependencies through dynamically updated parameters rather than recurrent hidden states. Quantum FWPs (QFWPs) extend this idea with variational quantum circuits (VQCs), but existing implementations rely on multi-qubit architectures that are difficult to scale on noisy intermediate-scale quantum (NISQ) devices and expensive to simulate classically. We propose gated QKAN-FWP, a fast-weight framework that integrates FWP with Quantum-inspired Kolmogorov-Arnold Network (QKAN) using single-qubit data re-uploading circuits as learnable nonlinear activation, known as DatA Re-Uploading ActivatioN (DARUAN). We further introduce a scalar-gated fast-weight update rule that stabilizes parameter evolution, supported by a theoretical analysis of its adaptive memory kernel, geometric boundedness, and parallelizable gradient paths. We evaluate the framework across time-series benchmarks, MiniGrid reinforcement learning, and highlight real-world solar cycle forecasting as our main practical result. In the long-horizon setting with 528-month input window and 132-month forecast horizon, our 12.5k-parameter model achieves lower scaled Mean Square Error (MSE), peak amplitude error, and peak timing error than a suite of classical recurrent baselines with up to 13x more parameters, including Long Short-Term Memory (LSTM) networks (25.9k-89.1k parameters), WaveNet-LSTM (167k), Vanilla recurrent neural network (11.5k), and a Modified Echo State Network (132k). To validate NISQ compatibility, we further deploy the trained fast programmer on IonQ and IBM Quantum processors, recovering forecasting accuracy within 0.1% relative MSE of the noiseless simulator at 1024 shots. These results position gated QKAN-FWP as a scalable, parameter-efficient, and NISQ-compatible approach to quantum-inspired sequence modeling. --- ### Beyond Factor Aggregation: Gauge-Aware Low-Rank Server Representations for Federated LoRA Authors: Jinqian Chen, Chang Liu, Jihua Zhu Published: 2026-05-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.06733v1 Federated LoRA enables parameter-efficient adaptation of large language models under decentralized data and limited client resources.However, directly averaging LoRA factors is representation-dependent: the same intrinsic update admits infinitely many gauge-equivalent factorizations, so factor-level aggregation can change under arbitrary coordinate choices while the underlying update remains unchanged. This reveals a semantic mismatch in existing federated LoRA aggregation rules. We propose \textbf{GLoRA}, a gauge-aware server representation for federated LoRA.Instead of aggregating raw factors, GLoRA estimates a consensus update subspace from client projectors and aggregates client updates in shared reference coordinates, thereby representing semantic update aggregation entirely in low-rank form. To support heterogeneous client capacities, GLoRA further provides a rank-compatible readout that instantiates adapters of different ranks from the same server state without dense update reconstruction. Experiments on GLUE and SuperNI show that GLoRA consistently outperforms federated LoRA baselines under data, resource, and task heterogeneity, including heterogeneous client ranks, sparse participation, larger backbones, and unseen-task evaluation. GLoRA also achieves a favorable efficiency--performance trade-off, suggesting that effective federated LoRA requires not merely averaging low-rank factors, but defining a semantically meaningful server-side representation for aggregation. --- ### On Training in Imagination Authors: Nadav Timor, Ravid Shwartz-Ziv, Micah Goldblum, Yann LeCun, David Harel Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06732v2 State-of-the-art model-based reinforcement learning methods train policies on imagined rollouts. These rollouts are trajectories generated by a learned dynamics model and are scored by a learned reward model, but without querying the true environment during policy updates. We study this training paradigm by quantifying how errors in learned dynamics and reward models affect returns and policy optimization. First, we extend the analysis of Asadi et al. (2018) to MDPs with learned reward models, and derive the optimal sample allocation--the ratio of dynamics samples to reward samples that minimizes a bound on return error under power-law scaling assumptions. We identify lower Lipschitz constants of the learned dynamics, reward, and policy as a representation desideratum that tightens this bound, and we connect this perspective to the temporal-straightening objective of Wang et al. (2026). Second, we examine how policy optimization with REINFORCE tolerates noisy rewards, which are often cheaper to obtain. We show that zero-mean reward noise leaves the gradient estimator unbiased and adds at most a variance term that decreases with the number of rollouts. This introduces a practical tradeoff: given a fixed budget, should one buy more rollouts with cheaper but noisier rewards, or fewer rollouts with more expensive but less noisy rewards? We reduce this choice to a one-dimensional optimization problem and characterize the optimum. --- ### When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents Authors: Xiaoyu Xu, Minxin Du, Qipeng Xie, Haobin Ke, Qingqing Ye, Haibo Hu Published: 2026-05-07 Categories: cs.CR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.06731v1 Personalized LLM agents maintain persistent cross-session state to support long-horizon collaboration. Yet, this persistence introduces a subtle but critical security vulnerability: routine user-agent interactions can gradually reshape an agent's long-term state, inadvertently weakening future confirmation boundaries, expanding tool-use defaults, and escalating autonomous behavior over time. We formalize this risk as \textbf{unintended long-term state poisoning}. To systematically study it, we introduce the \textbf{Unintended Long-Term State Poisoning Bench (ULSPB)}, a bilingual benchmark comprising $350$ settings spanning five assistance categories, seven interaction patterns, 24-turn routine interactions, and matched single-injection counterparts. Furthermore, we define the \emph{Harm Score} (HS), a state-centric metric that quantifies \emph{authorization drift}, \emph{tool-use escalation}, and \emph{unchecked autonomy}. Experiments on OpenClaw with four backbone LLMs demonstrate that, while single-injection is generally effective, routine conversations alone can substantially poison long-term state, primarily corrupting memory-centric artifacts. Evaluations seeded with real-world user interactions confirm that this risk is not a mere artifact of synthetic prompts. To mitigate this threat, we propose \textbf{StateGuard}, a lightweight, post-execution defense that audits state diffs at the writeback boundary and selectively rolls back dangerous edits. Across all evaluated models, StateGuard reduces HS to near zero and lowers false-negative rates, with acceptable high false-positive rates under a safety-first writeback defense and minimal overhead. --- ### Semantic State Abstraction Interfaces for LLM-Augmented Portfolio Decisions: Multi-Axis News Decomposition and RL Diagnostics Authors: Likhita Yerra, Remi Uttejitha Allam Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06730v1 We introduce Semantic State Abstraction Interfaces (SSAI): a methodological template for mapping sparse unstructured text into $K$ auditable, named coordinates with neutral defaults on no-news days, designed to separate representation hypotheses from optimisation variance in sequential decision systems. Our contribution is the framework and its evaluation protocol, not a claim that SSAI outperforms denser alternatives. We instantiate SSAI with $K=4$ axes (sentiment, risk, confidence, volatility forecast) on a US-equity panel (30 NASDAQ-100 names, FNSPID news, 2019--2023 test), and evaluate it across direct factor portfolios, supervised ridge forecasters, and RL agents (DP-PPO, SAC) that share the same fixed $φ$. The four-factor factor portfolio reaches 307.2% cumulative return and Sharpe 1.067, but apparent gains versus buy-and-hold (243.6%) fail coverage-stratified controls, reverse at $\geq 0.2$% costs, and are statistically fragile versus a sentiment-only baseline; a PC1 composite and a FinBERT portfolio baseline are stronger ranking signals in this setting. Ridge and RL blocks diagnose representation versus optimiser effects. We position SSAI as an interpretability-performance diagnostic and reusable protocol for sparse-text decision systems. --- ### The E$Δ$-MHC-Geo Transformer: Adaptive Geodesic Operations with Guaranteed Orthogonality Authors: Arash Shahmansoori Published: 2026-05-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.06729v1 We present the E$Δ$-MHC-Geo Transformer, a novel architecture that unifies Manifold-Constrained Hyper-Connections (mHC), Deep Delta Learning (DDL), and the Cayley transform to obtain input-adaptive, unconditionally orthogonal residual connections. Unlike DDL, whose Householder operator is orthogonal only at $β\in \{0,2\}$, our Data-Dependent Cayley rotation $Q(x)=(I+(β/2)A(x))^{-1}(I-(β/2)A(x))$ preserves orthogonality for all $β$ and all inputs. To handle negation, an eigenvalue $-1$ case that Cayley provably excludes, we introduce the E$Δ$-MHC-Geo Hybrid, which combines Cayley rotation with Householder reflection via a learned operator-selection gate $X'=γ(X)Q(X)X+(1-γ(X))H_2(X)X$. A midpoint-collapse regularizer, $4γ(1-γ)$, encourages boundary gate decisions, where each selected component is orthogonal. In matched-parameter comparisons, with approximately 1.79M parameters per model and mean +/- standard deviation over 3 seeds, against four baselines including the concurrent JPmHC, E$Δ$-MHC-Geo achieves the best long-horizon stability, 1.9x over JPmHC and 3.8x over GPT; the best near-$π$ rotation loss, 4.5x over JPmHC on single-plane; strong norm preservation, with 0.001 mean deviation; and 0.96 negation cosine alignment in a diagnostic reflection probe, all with 33% fewer layers. While JPmHC's wider representation excels on pure rotation, its finite Cayley residual mixer excludes an exact $λ=-1$ operator and has no reflection branch, motivating our hybrid approach for accessing both connected components of $O(n)$. --- ### OmicsLM: A Multimodal Large Language Model for Multi-Sample Omics Reasoning Authors: Maciej Sypetkowski, Joanna Krawczyk, Łukasz Smoliński, Remigiusz Kinas, Przemysław Pietrzak, Tomasz Jetka, Rafał Powalski Published: 2026-05-07 Categories: q-bio.GN, cs.AI, q-bio.CB arXiv: https://arxiv.org/abs/2605.06728v1 Interpreting transcriptomic data is one of the most common analytical tasks in modern biology. Yet most current models either consume expression profiles without producing natural-language biological explanations, or reason in language without direct access to quantitative omics measurements. We introduce OmicsLM, a multimodal LLM that connects quantitative omics profiles with natural-language biological tasks. OmicsLM represents each transcriptomic profile as a compact continuous representation within the LLM context. This interface preserves quantitative expression signal while allowing natural-language instructions, explicit gene mentions, and multiple interleaved biological samples to be processed together in one model context. We train OmicsLM on more than 5.5 million instruction-following examples spanning over 70 task types, combining continuous transcriptomic inputs, experimental data rendered through diverse language templates, and free-text biological knowledge and question-answering data. This mixture covers cell type annotation, perturbation prediction, clinical prediction, pathway reasoning, and open-ended biological question answering. Existing benchmarks evaluate either profile-level prediction or text-only biological QA, leaving language-guided, multi-sample reasoning over real expression profiles unmeasured. To close this gap, we introduce GEO-OmicsQA, a benchmark for multi-sample biological question answering built from real Gene Expression Omnibus (GEO) studies. We demonstrate that OmicsLM can use expression profiles directly and perform comparably to specialized omics models on profile-level tasks, while outperforming both omics-specialized models and general LLMs on language-guided biological reasoning over expression data. --- ### Medical Imaging Classification with Cold-Atom Reservoir Computing using Auto-Encoders and Surrogate-Driven Training Authors: Nuno Batista, Ana Morgado, Oscar Ferraz, Sagar Silva Pratapsi, Jorge Lobo, Gabriel Falcao Published: 2026-05-07 Categories: cs.LG, cs.ET, eess.IV arXiv: https://arxiv.org/abs/2605.06727v1 We introduce a hybrid quantum-classical pipeline, based on neutral-atom reservoir computing, for medical image classification, focusing on the binary classification task of polyp detection. To deal effectively with the high dimensionality, we integrate a guided auto-encoder. This pipeline learns compact and discriminative representations of image data that are also well-suited for quantum reservoir computing. A key challenge in such systems is the non-differentiable nature of quantum measurements, which creates a 'gradient barrier' for standard training. We overcome this barrier by incorporating a differentiable surrogate model that emulates the quantum layer, enabling end-to-end backpropagation through the entire system. This guided training process is jointly optimized for classification accuracy and for faithful image recovery from the auto-encoder. The learned latent representations are encoded as pulse detuning parameters within a Rydberg Hamiltonian, and quantum embeddings are subsequently obtained through expectation values. These embeddings are then passed to a linear classifier. Our simulations show that this method outperforms some traditional approaches that use PCA or unguided autoencoders. We also conduct ablation studies to assess the impact of various quantum and training parameters, demonstrating the robustness and flexibility of our proposed pipeline for real-world medical imaging applications, even in the current NISQ era. --- ### Transformer-Based Wildlife Species Classification from Daily Movement Trajectories Authors: Obed Irakoze, Prasenjit Mitra Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06726v1 Inferring the identity of wildlife species from daily movement data alone is a challenging task. We train sequence models on large-scale, 7-species GPS trajectories from the Movebank platform. Trajectories models are evaluated using a protocol in which entire telemetry studies or regions are heldout during testing. We compare Transformer-based sequence models to LSTM, CNN, and Temporal Convolutional Networks, and find that Transformers consistently achieve higher balanced accuracy with gains of approximately 8 to 22 percentage points, depending on the species and experimental setting. In an elephant binary classification task with 1-hour resolution, the Transformer achieves a balanced accuracy of 0.83 and an AUC of 0.92, substantially outperforming all baseline models. We examine, under data-limited conditions, feature representations by analyzing the differences between a basic displacement-based encoding and an expanded range of movement descriptors that include speed, direction, and turning behavior. With feature augmentation, we see clear performance gains, especially for underrepresented and sparsely represented species, such as large carnivores, lions, and Zebras. Finally, experiments comparing 1-hour and 30-minutetemporal resolutions show that while finer sampling can capture short-term movement patterns for some species, a unified 1-hour resolution yields more promising performance across studies by reducing missing data and ensuring consistent temporal coverage. --- ### Enabling Unsupervised Training of Deep EEG Denoisers With Intelligent Partitioning Authors: Qiyu Rao, Haozhe Tian, Homayoun Hamedmoghadam, Danilo Mandic Published: 2026-05-07 Categories: cs.LG, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2605.06724v1 Denoising wearable electroencephalogram (EEG) is inherently challenging since neural activity is not only subtle but also inseparable from spectrally overlapping noise artifacts. Classical signal processing methods, relying on fixed or heuristic rules, cannot handle the time-varying pervasive artifacts in wearable EEGs. Deep learning methods, on the other hand, show promise in decomposition-free EEG denoising using highly expressive neural networks, but the training requires artifact-free EEG, which is inherently unobtainable. To address this, we propose Intelligent Partitioning for Self-supervised Denoising (iPSD). Our method eliminates the need for clean references by learning to partition an input EEG segment into independent noisy realizations with the same underlying signal. This enables self-supervision of deep learning denoisers, even in zero-shot settings where only a single EEG segment to be denoised is available. We validate iPSD through extensive experiments, including validations on wearable EEG from in-ear sensors. The results show that iPSD achieves state-of-the-art performance, most notably under extremely low signal-to-noise ratios (down to -10 dB) and challenging artifacts (e.g., EMG), with spectral fidelity orders of magnitude higher than competitive baselines. --- ### When Does a Language Model Commit? A Finite-Answer Theory of Pre-Verbalization Commitment Authors: Long Zhang, Wei-neng Chen, Feng-feng Wei, Zi-bo Qin Published: 2026-05-07 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.06723v1 Language models often generate reasoning before giving a final answer, but the visible answer does not reveal when the model's answer preference became stable. We study this question through a narrow computable object: \emph{finite-answer preference stabilization}. For a model state and specified answer verbalizers, we project the model's own continuation probabilities onto a finite answer set; in binary tasks this yields an exact log-odds code, $δ(ξ)=S_θ(\mathrm{yes}\midξ)-S_θ(\mathrm{no}\midξ)$. This target defines parser-based answer onset, retrospective stabilization time, and lead without relying on greedy rollouts or learned probes. In controlled delayed-verdict tasks with Qwen3-4B-Instruct, the contextual finite-answer projection stabilizes before the answer is parseable, with 17--31 token mean lead in the main templates and positive, shorter lead in a parser-clean replication. The signal tracks the model's eventual output rather than truth, is linearly recoverable from compact hidden summaries, is partly separable from cursor progress, and transfers as shared information without a single invariant coordinate. Diagnostics separate the measurement from online stopping, verbalizer-free belief, and causal answer control; exact steering shows local sensitivity of $δ$ but not reliable generation control. --- ### Conditional generation of antibody sequences with classifier-guided germline-absorbing discrete diffusion Authors: Justin Sanders, Luca Giancardo, Lan Guo, Yue Zhao, Kemal Sonmez, Nina Cheng, Melih Yilmaz Published: 2026-05-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.06720v1 Antibody therapeutics are among the most successful modern medicines, yet computationally designing antibodies with desirable binding and developability properties remains challenging. While protein language models (pLMs) have emerged as powerful tools for antibody sequence design, existing approaches largely suffer from two key limitations: they predominantly memorize germline sequences rather than modeling biologically meaningful somatic variation, and they offer limited support for flexible classifier-guided conditional generation. We address these challenges through two primary contributions. First, we demonstrate that discrete diffusion fine-tuning achieves strong language modeling performance on antibody sequences while allowing for generation conditioned on any off-the-shelf classifier. Second, we introduce germline absorbing diffusion, a novel modification of the discrete diffusion noise process in which the germline sequence - rather than a masked sequence - serves as the absorbing state. This biologically motivated inductive bias restricts the model to learning the trajectory from germline to observed sequence, effectively excluding genetic variation and V(D)J recombination statistics from the learned distribution and dramatically mitigating germline bias. We show that germline diffusion improves non-germline residue prediction accuracy from 26 percent to 46 percent, approaching the theoretical upper bound set by true biological variability. We then demonstrate the utility of our germline diffusion model on the conditional generation tasks of sampling antibodies with improved hydrophobicity and predicted binding affinity. On both tasks our model shows an improved tradeoff between class adherence and sample quality, significantly outperforming EvoProtGrad, a popular strategy to sample from pLMs with gradient-based discrete Markov Chain Monte Carlo. --- ### TUANDROMD-X: Advanced Entropy and Visual Analytics Dataset for Enhanced Malware Detection and Classification Authors: Parthajit Borah, Upasana Sarmah, D. K. Bhattacharyya, J. K. Kalita Published: 2026-05-07 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2605.06718v1 Malware and malware-based attacks are becoming more prevalent and complex. Attackers regularly come up with new techniques that have the ability to evade conventional and signature-based malware defense. In order to address such threats, there is an increasing demand for advanced and better defense solutions. Machine learning-based techniques are efficiently capable of defending against malware and malware-based attacks. Nevertheless, creating and efficiently testing such techniques demand high-quality datasets having samples of various malware families as well as goodware. The lack of such datasets continues to be a major bottleneck in malware research. In this paper, we introduce TUANDROMD-X, a multiclass malware dataset with visual and entropy-based features of each sample, distinctly identifying malware from goodware. The dataset is created based on static analysis, lowering the overhead that comes with high feature engineering and dynamic analysis. As a result, TUANDROMD-X facilitates researchers and cyber-security experts to design faster and better malware detection systems. --- ### Agentic Coding Needs Proactivity, Not Just Autonomy Authors: Nghi D. Q. Bui, Georgios Evangelopoulos Published: 2026-05-07 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.06717v1 Coding agents are rapidly changing the landscape of software development, moving from inline completion to autonomous systems that edit repositories, open pull requests, respond to issues, and run scheduled or webhook triggered routines across the development life cycle. The next generation is increasingly described as proactive and long-horizon: agents should notice relevant changes before the developer asks, connect signals across tools, decide when to interrupt, and carry preferences across sessions. Yet the field still lacks a clear account of what proactivity means for software development, how it differs from autonomy, what acceptance criteria proactive long-horizon tasks should satisfy, and which metrics determine whether unsolicited agent behavior is useful rather than merely active. Proactive coding agents should be evaluated by the quality and improvement of their insight policy: the policy that decides what matters next, what evidence supports it, whether to show it, and how to adapt after feedback. This view is grounded in the principles of mixed initiative interaction. We propose a three level taxonomy of proactivity (Reactive, Scheduled, and Situation Aware), compare contemporary coding agents against five practical criteria, and sketch an active user simulation protocol with three evaluation targets: Insight Decision Quality (IDQ), Context Grounding Score (CGS), and Learning Lift --- ### From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms Authors: Jinghao Luo, Yuchen Tian, Chuxue Cao, Ziyang Luo, Hongzhan Lin, Kaixin Li, Chuyi Kong, Ruichao Yang, Jing Ma Published: 2026-05-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.06716v1 Large Language Model (LLM)-based agents have fundamentally reshaped artificial intelligence by integrating external tools and planning capabilities. While memory mechanisms have emerged as the architectural cornerstone of these systems, current research remains fragmented, oscillating between operating system engineering and cognitive science. This theoretical divide prevents a unified view of technological synthesis and a coherent evolutionary perspective. To bridge this gap, this survey proposes a novel evolutionary framework for LLM agent memory mechanisms, formalizing the development process into three stages: Storage (trajectory preservation), Reflection (trajectory refinement), and Experience (trajectory abstraction). We first formally define these three stages before analyzing the three core drivers of this evolution: the necessity for long-range consistency, the challenges in dynamic environments, and the ultimate goal of continual learning. Furthermore, we specifically explore two transformative mechanisms in the frontier Experience stage: proactive exploration and cross-trajectory abstraction. By synthesizing these disparate views, this work offers robust design principles and a clear roadmap for the development of next-generation LLM agents. --- ### Edge Deep Learning in Computer Vision and Medical Diagnostics: A Comprehensive Survey Authors: Yiwen Xu, Tariq M. Khan, Yang Song, Erik Meijering Published: 2026-05-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.06714v1 Edge deep learning, a paradigm change reconciling edge computing and deep learning, facilitates real-time decision making attuned to environmental factors through the close integration of computational resources and data sources. Here we provide a comprehensive review of the current state of the art in edge deep learning, focusing on computer vision applications, in particular medical diagnostics. An overview of the foundational principles and technical advantages of edge deep learning is presented, emphasising the capacity of this technology to revolutionise a wide range of domains. Furthermore, we present a novel categorisation of edge hardware platforms based on performance and usage scenarios, facilitating platform selection and operational effectiveness. Following this, we dive into approaches to effectively implement deep neural networks on edge devices, encompassing methods such as lightweight design and model compression. Reviewing practical applications in the fields of computer vision in general and medical diagnostics in particular, we demonstrate the profound impact edge-deployed deep learning models can have in real-life situations. Finally, we provide an analysis of potential future directions and obstacles to the adoption of edge deep learning, with the intention to stimulate further investigations and advancements of intelligent edge deep learning solutions. This survey provides researchers and practitioners with a comprehensive reference shedding light on the critical role deep learning plays in the advancement of edge computing applications. --- ### ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation Authors: Omar El Khalifi, Thomas Rossi, Oscar Fossey, Thibault Fouque, Ulysse Mizrahi, Philip Torr, Ivan Laptev, Fabio Pizzati, Baptiste Bellot-Gurlet Published: 2026-05-07 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.06667v1 For artistic applications, video generation requires fine-grained control over both performance and cinematography, i.e., the actor's motion and the camera trajectory. We present ActCam, a zero-shot method for video generation that jointly transfers character motion from a driving video into a new scene and enables per-frame control of intrinsic and extrinsic camera parameters. ActCam builds on any pretrained image-to-video diffusion model that accepts conditioning in terms of scene depth and character pose. Given a source video with a moving character and a target camera motion, ActCam generates pose and depth conditions that remain geometrically consistent across frames. We then run a single sampling process with a two-phase conditioning schedule: early denoising steps condition on both pose and sparse depth to enforce scene structure, after which depth is dropped and pose-only guidance refines high-frequency details without over-constraining the generation. We evaluate ActCam on multiple benchmarks spanning diverse character motions and challenging viewpoint changes. We find that, compared to pose-only control and other pose and camera methods, ActCam improves camera adherence and motion fidelity, and is preferred in human evaluations, especially under large viewpoint changes. Our results highlight that careful camera-consistent conditioning and staged guidance can enable strong joint camera and motion control without training. Project page: https://elkhomar.github.io/actcam/. --- ### UniPool: Learning Expert-to-Layer Ownership from Brief Global Access Authors: Minbin Huang, Han Shi, Chuanyang Zheng, Yimeng Wu, Guoxuan Chen, Xintong Yu, Yichun Yin, Hong Cheng Published: 2026-05-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.06665v2 Most Mixture-of-Experts (MoE) transformers preassign each expert to one layer for the whole of training. We study whether a brief global-access phase can learn a compatible expert-to-layer allocation that is then executed privately. UniPool-Lock gives every layer its own router over one global pool, balances aggregate pool usage, and scores experts with a scale-stable NormRouter. After the short ownership-learning phase, it assigns each expert to one layer, locks the disjoint allocation, and continues training as a layer-private MoE. With the same expert-FFN budget and routed expert FLOPs, this recipe lowers held-out loss relative to vanilla MoE by 0.024-0.037 across five dense-equivalent scales from 182M to 1.5B, including -0.0247 at 1.5B after 60B tokens. The ownership-learning phase lasts 2K steps, about 3.3% of training, and post-lock step time is within -0.7% to +2.8% of vanilla MoE in our throughput measurements. Controls locate the gain in full-pool training and in the allocation it produces: a random disjoint allocation fixed at initialization, trained with the same router and losses, matches vanilla, whereas locking the allocation learned during the full-pool phase recovers nearly all of the persistent full-pool gain, and substituting a random allocation at the lock forfeits about half of it. Keeping full-pool access throughout training (UniPool-Full) also improves over vanilla MoE at four scales and outperforms it with only 66.7% (182M) to 50% (469M and 650M) of its expert parameters. --- ### UniPool: A Globally Shared Expert Pool for Mixture-of-Experts Authors: Minbin Huang, Han Shi, Chuanyang Zheng, Yimeng Wu, Guoxuan Chen, Xintong Yu, Yichun Yin, Hong Cheng Published: 2026-05-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.06665v1 Modern Mixture-of-Experts (MoE) architectures allocate expert capacity through a rigid per-layer rule: each transformer layer owns a separate expert set. This convention couples depth scaling with linear expert-parameter growth and assumes that every layer needs isolated expert capacity. However, recent analyses and our routing probe challenge this allocation rule: replacing a deeper layer's learned top-k router with uniform random routing drops downstream accuracy by only 1.0-1.6 points across multiple production MoE models. Motivated by this redundancy, we propose UniPool, an MoE architecture that treats expert capacity as a global architectural budget by replacing per-layer expert ownership with a single shared pool accessed by independent per-layer routers. To enable stable and balanced training under sharing, we introduce a pool-level auxiliary loss that balances expert utilization across the entire pool, and adopt NormRouter to provide sparse and scale-stable routing into the shared expert pool. Across five LLaMA-architecture model scales (182M, 469M, 650M, 830M, and 978M parameters) trained on 30B tokens from the Pile, UniPool consistently improves validation loss and perplexity over the matched vanilla MoE baselines. Across these scales, UniPool reduces validation loss by up to 0.0386 relative to vanilla MoE. Beyond raw loss improvement, our results identify pool size as an explicit depth-scaling hyperparameter: reduced-pool UniPool variants using only 41.6%-66.7% of the vanilla expert-parameter budget match or outperform layer-wise MoE at the tested scales. This shows that, under a shared-pool design, expert parameters need not grow linearly with depth; they can grow sublinearly while remaining more efficient and effective than vanilla MoE. Further analysis shows that UniPool's benefits compose with finer-grained expert decomposition. --- ### BAMI: Training-Free Bias Mitigation in GUI Grounding Authors: Borui Zhang, Bo Zhang, Bo Wang, Wenzhao Zheng, Yuhao Cheng, Liang Tang, Yiqiang Yan, Jie Zhou, Jiwen Lu Published: 2026-05-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.06664v1 GUI grounding is a critical capability for enabling GUI agents to execute tasks such as clicking and dragging. However, in complex scenarios like the ScreenSpot-Pro benchmark, existing models often suffer from suboptimal performance. Utilizing the proposed \textbf{Masked Prediction Distribution (MPD)} attribution method, we identify that the primary sources of errors are twofold: high image resolution (leading to precision bias) and intricate interface elements (resulting in ambiguity bias). To address these challenges, we introduce \textbf{Bias-Aware Manipulation Inference (BAMI)}, which incorporates two key manipulations, coarse-to-fine focus and candidate selection, to effectively mitigate these biases. Our extensive experimental results demonstrate that BAMI significantly enhances the accuracy of various GUI grounding models in a training-free setting. For instance, applying our method to the TianXi-Action-7B model boosts its accuracy on the ScreenSpot-Pro benchmark from 51.9\% to 57.8\%. Furthermore, ablation studies confirm the robustness of the BAMI approach across diverse parameter configurations, highlighting its stability and effectiveness. Code is available at https://github.com/Neur-IO/BAMI. --- ### EMO: Pretraining Mixture of Experts for Emergent Modularity Authors: Ryan Wang, Akshita Bhagia, Sewon Min Published: 2026-05-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.06663v2 Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain-specific knowledge. Mixture-of-Experts (MoEs) seemingly offer a potential alternative by activating only a subset of experts per input, but in practice, restricting inference to a subset of experts for a given domain leads to severe performance degradation. This limits their practicality in memory-constrained settings, especially as models grow larger and sparser. We introduce EMO, an MoE designed for modularity-the independent use and composition of expert subsets-without requiring human-defined priors. Our key idea is to encourage tokens from similar domains to rely on similar experts. Since tokens within a document often share a domain, EMO restricts them to select experts from a shared pool, while allowing different documents to use different pools. This simple constraint enables coherent expert groupings to emerge during pretraining using document boundaries alone. We pretrain a 1B-active, 14B-total EMO on 1T tokens. As a full model, it matches standard MoE performance. Crucially, it enables selective expert use: retaining only 25% (12.5%) of experts incurs just a 1% (3%) absolute drop, whereas standard MoEs break under the same setting. We further find that expert subsets in EMO specialize at semantic levels (e.g., domains such as math or code), in contrast to the low-level syntactic specialization observed in standard MoEs. Altogether, our results demonstrate a path toward modular, memory-efficient deployment of large, sparse models and open new opportunities for composable architectures. --- ### Verifier-Backed Hard Problem Generation for Mathematical Reasoning Authors: Yuhang Lai, Jiazhan Feng, Yee Whye Teh, Ning Miao Published: 2026-05-07 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.06660v1 Large Language Models (LLMs) demonstrate strong capabilities for solving scientific and mathematical problems, yet they struggle to produce valid, challenging, and novel problems - an essential component for advancing LLM training and enabling autonomous scientific research. Existing problem generation approaches either depend on expensive human expert involvement or adopt naive self-play paradigms, which frequently yield invalid problems due to reward hacking. This work introduces VHG, a verifier-enhanced hard problem generation framework built upon three-party self-play. By integrating an independent verifier into the conventional setter-solver duality, our design constrains the setter's reward to be jointly determined by problem validity (evaluated by the verifier) and difficulty (assessed by the solver). We instantiate two verifier variants: a Hard symbolic verifier and a Soft LLM-based verifier, with evaluations conducted on indefinite integral tasks and general mathematical reasoning tasks. Experimental results show that VHG substantially outperforms all baseline methods by a clear margin. --- ### Relit-LiVE: Relight Video by Jointly Learning Environment Video Authors: Weiqing Xiao, Hong Li, Xiuyu Yang, Houyuan Chen, Wenyi Li, Tianqi Liu, Shaocong Xu, Chongjie Ye, Hao Zhao, Beibei Wang Published: 2026-05-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.06658v1 Recent advances have shown that large-scale video diffusion models can be repurposed as neural renderers by first decomposing videos into intrinsic scene representations and then performing forward rendering under novel illumination. While promising, this paradigm fundamentally relies on accurate intrinsic decomposition, which remains highly unreliable for real-world videos and often leads to distorted appearances, broken materials, and accumulated temporal artifacts during relighting. In this work, we present Relit-LiVE, a novel video relighting framework that produces physically consistent, temporally stable results without requiring prior knowledge of camera pose. Our key insight is to explicitly introduce raw reference images into the rendering process, enabling the model to recover critical scene cues that are inevitably lost or corrupted in intrinsic representations. Furthermore, we propose a novel environment video prediction formulation that simultaneously generates relit videos and per-frame environment maps aligned with each camera viewpoint in a single diffusion process. This joint prediction enforces strong geometric-illumination alignment and naturally supports dynamic lighting and camera motion, significantly improving physical consistency in video relighting while easing the requirement of known per-frame camera pose. Extensive experiments demonstrate that Relit-LiVE consistently outperforms state-of-the-art video relighting and neural rendering methods across synthetic and real-world benchmarks. Beyond relighting, our framework naturally supports a wide range of downstream applications, including scene-level rendering, material editing, object insertion, and streaming video relighting. The Project is available at https://github.com/zhuxing0/Relit-LiVE. --- ### Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML Authors: Jai Moondra, Ayela Chughtai, Bhargavi Lanka, Swati Gupta Published: 2026-05-07 Categories: cs.LG, cs.DM, cs.ET, math.OC arXiv: https://arxiv.org/abs/2605.06656v1 Ranking LLMs via pairwise human feedback underpins current leaderboards for open-ended tasks, such as creative writing and problem-solving. We analyze ~89K comparisons in 116 languages from 52 LLMs from Arena, and show that the best-fit global Bradley-Terry (BT) ranking is misleading. Nearly 2/3 of the decisive votes cancel out, and even the top 50 models according to the global BT ranking are statistically indistinguishable (pairwise win probabilities are at most 0.53 within the top 50 models). We trace this failure to strong, structured heterogeneity of opinions across language, task, and time. Moreover, we find an important characteristic - *language* plays a key role. Grouping by language (and families) increases the agreement of votes massively, resulting in two orders of magnitude higher spread in the ELO scores (i.e., very consistent rankings). What appears as global noise is in fact a mixture of coherent but conflicting subpopulations. To address such heterogeneity in supervised machine learning, we introduce the framework of $(λ, ν)$-portfolios, which are small sets of models that achieve a prediction error at most $λ$, "covering" at least a $ν$ fraction of users. We formulate this as a variant of the set cover problem and provide guarantees using the VC dimension of the underlying set system. On the Arena data, our algorithms recover just 5 distinct BT rankings that cover over 96% of votes at a modest $λ$, compared to the 21% coverage by the global ranking. We also provide a portfolio of 6 LLMs that cover twice as many votes as the top-6 LLMs from a global ranking. We further construct portfolios for a classification problem on the COMPAS dataset using an ensemble of fairness-regularized classification models and show that these portfolios can be used to detect blind spots in the data, which might be of independent interest to policymakers. --- ### Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less Authors: Yuxing Liu, Jianyu Wang, Tong Zhang Published: 2026-05-07 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2605.06654v1 Optimizers play an important role in both pretraining and finetuning stages when training large language models (LLMs). In this paper, we present an observation that full finetuning with the same optimizer as in pretraining achieves a better learning-forgetting tradeoff, i.e., forgetting less while achieving the same or better performance on the new task, than other optimizers and, possibly surprisingly, LoRA, during the supervised finetuning (SFT) stage. We term this phenomenon optimizer-model consistency. To better understand it, through controlled experiments and theoretical analysis, we show that: 1) optimizers can shape the models by having regularization effects on the activations, leading to different landscapes around the pretrained checkpoints; 2) in response to this regularization effect, the weight update in SFT should follow some specific structures to lower forgetting of the knowledge learned in pretraining, which can be obtained by using the same optimizer. Moreover, we specifically compare Muon and AdamW when they are employed throughout the pretraining and SFT stages and find that Muon performs worse when finetuned for reasoning tasks. With a synthetic language modeling experiment, we demonstrate that this can come from Muon's strong tendency towards rote memorization, which may hurt pattern acquisition with a small amount of data, as for SFT. --- ### When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels Authors: Sushant Gautam, Finn Schwall, Annika Willoch Olstad, Fernando Vallecillos Ruiz, Birk Torpmann-Hagen, Sunniva Maria Stordal Bjørklund, Leon Moonen, Klas Pettersen, Michael A. Riegler Published: 2026-05-07 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.06652v1 Many deployments must compare candidate language models for safety before a labeled benchmark exists for the relevant language, sector, or regulatory regime. We formalize this setting as benchmarkless comparative safety scoring and specify the contract under which a scenario-based audit can be interpreted as deployment evidence. Scores are valid only under a fixed scenario pack, rubric, auditor, judge, sampling configuration, and rerun budget. Because no labels are available, we replace ground-truth agreement with an instrumental-validity chain: responsiveness to a controlled safe-versus-abliterated contrast, dominance of target-driven variance over auditor and judge artifacts, and stability across reruns. We instantiate the chain in SimpleAudit, a local-first scoring instrument, and validate it on a Norwegian safety pack. Safe and abliterated targets separate with AUROC values between 0.89 and 1.00, target identity is the dominant variance component ($η^2 \approx 0.52$), and severity profiles stabilize by ten reruns. Applying the same chain to Petri shows that it admits both tools. The substantial differences arise upstream of the chain, in claim-contract enforcement and deployment fit. A Norwegian public-sector procurement case comparing Borealis and Gemma 3 demonstrates the resulting evidence in practice: the safer model depends on scenario category and risk measure. Consequently, scores, matched deltas, critical rates, uncertainty, and the auditor and judge used must be reported together rather than collapsed into a single ranking. --- ### AI co-mathematician: Accelerating mathematicians with agentic AI Authors: Daniel Zheng, Ingrid von Glehn, Yori Zwols, Iuliya Beloshapka, Lars Buesing, Daniel M. Roy, Martin Wattenberg, Bogdan Georgiev, Tatiana Schmidt, Andrew Cowie, Fernanda Viegas, Dimitri Kanevsky et al. Published: 2026-05-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.06651v2 We introduce the AI co-mathematician, a workbench for mathematicians to interactively leverage AI agents to pursue open-ended research. The AI co-mathematician is optimized to provide holistic support for the exploratory and iterative reality of mathematical workflows, including ideation, literature search, computational exploration, theorem proving and theory building. By providing an asynchronous, stateful workspace that manages uncertainty, refines user intent, tracks failed hypotheses, and outputs native mathematical artifacts, the system mirrors human collaborative workflows. In early tests, the AI co-mathematician helped researchers solve open problems, identify new research directions, and uncover overlooked literature references. Besides demonstrating a highly interactive paradigm for AI-assisted mathematical discovery, the AI co-mathematician also achieves state of the art results on hard problem-solving benchmarks, including scoring 48% on FrontierMath Tier 4, a new high score among all AI systems evaluated. --- ### Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients Authors: Mingwei Xu, Hao Fang Published: 2026-05-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.06650v1 Reinforcement learning with verifiable rewards (RLVR), due to the deterministic verification, becomes a dominant paradigm for enhancing the reasoning ability of large language models (LLMs). The community witnesses the rapid change from the Proximal Policy Optimization (PPO) to Group Relative Policy Optimization (GRPO), in which GRPO reduces the complicated advantage estimation with simple estimation over grouped positive and negative rollouts. However, we note that negative rollouts may admit no gradation of failure severity, and the combinatorial vastness makes penalizing a few sampled negatives unlikely to cover a meaningful reward signal under sparse binary rewards. In this work, we propose Positive-Only Policy Optimization (POPO), a novel RLVR framework in which learning can occur exclusively via online positive rollouts. Specifically, POPO utilizes bounded importance sampling over the positive rollout set. Thus, no disjoint negative rollouts are used for the gradient guidance. We show that implicit negative gradients can emerge naturally through reinforcing the positive probability via rollouts redistribution. Next, POPO stabilizes the policy optimization through two mechanisms. First, it applies a siamese policy network with a momentum-based adaptation law for stabilized policy evolution. Second, we replace the KL-divergence with a bounded similarity penalty term in the siamese representation space. We conduct extensive experiments using publicly available, well-established text-LLM models, e.g., the Qwen family, across all-level mathematical benchmarks. Our experiment demonstrates that POPO achieves performance comparable to, or even superior to GRPO. Notably, we show that POPO can achieve 36.67% in AIME 2025 with Qwen-Math-7B, outperforming GRPO 30.00%. Our ablation and sweep studies further illustrate the necessity and robustness of POPO components. --- ### Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval Authors: Zeyu Yang, Xu Han, Qi Ma, Jason Chen, Anshumali Shrivastava Published: 2026-05-07 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.06647v3 Retrieval-augmented agents are increasingly the interface to large knowledge bases, yet most treat retrieval as a black box: they issue exploratory queries, inspect snippets, and reformulate until evidence emerges. This resembles how a newcomer searches an unfamiliar database rather than how an expert navigates it with strong priors about terminology and likely evidence, causing extra retrieval rounds, latency, and poor recall. We introduce \textit{Superintelligent Retrieval Agent} (SIRA), which casts \emph{superintelligence} in retrieval as compressing multi-round exploratory search into a single corpus-discriminative retrieval action. SIRA does not merely ask which terms are relevant; it asks which terms separate the desired evidence from corpus-level confusers. Offline, an LLM enriches each document with missing search vocabulary; at query time, it predicts evidence vocabulary the query omits; and corpus statistics serve as tool calls that filter terms that are absent, overly common, or unlikely to create retrieval margin. The final step is a single weighted BM25 call combining the query with the validated expansion. Across ten BEIR benchmarks, SIRA achieves the strongest average retrieval performance in our comparison, beating dense retrievers, learned sparse retrievers, and LLM search-agent baselines while using no relevance labels or retriever fine-tuning. On downstream QA, its retrieval-only answer coverage exceeds recent RL-trained agentic QA systems on NQ and HotpotQA. We also introduce \textbf{BrowseComp-Wikipedia}, a hard-search benchmark of 232 BrowseComp-derived queries over a 25,587,229-document Wikipedia index. Even without index-time enrichment, using only grounded Wikipedia categories, SIRA outperforms multi-round Perplexity agents at every budget, reaching 9.70% Recall@1, 15.27% Recall@10, and 36.14% Recall@100. --- ### Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval Authors: Zeyu Yang, Qi Ma, Jason Chen, Anshumali Shrivastava Published: 2026-05-07 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.06647v2 Retrieval-augmented agents are increasingly the interface to large knowledge bases, yet most treat retrieval as a black box: they issue exploratory queries, inspect snippets, and reformulate until evidence emerges. This resembles how a newcomer searches an unfamiliar database rather than how an expert navigates it with strong priors about terminology and likely evidence, causing extra retrieval rounds, latency, and poor recall. We introduce \textit{Superintelligent Retrieval Agent} (SIRA), which casts \emph{superintelligence} in retrieval as compressing multi-round exploratory search into a single corpus-discriminative retrieval action. SIRA does not merely ask which terms are relevant; it asks which terms separate the desired evidence from corpus-level confusers. Offline, an LLM enriches each document with missing search vocabulary; at query time, it predicts evidence vocabulary the query omits; and corpus statistics serve as tool calls that filter terms that are absent, overly common, or unlikely to create retrieval margin. The final step is a single weighted BM25 call combining the query with the validated expansion. Across ten BEIR benchmarks, SIRA achieves the strongest average retrieval performance in our comparison, beating dense retrievers, learned sparse retrievers, and LLM search-agent baselines while using no relevance labels or retriever fine-tuning. On downstream QA, its retrieval-only answer coverage exceeds recent RL-trained agentic QA systems on NQ and HotpotQA. We also introduce \textbf{BrowseComp-Wikipedia}, a hard-search benchmark of 232 BrowseComp-derived queries over a 25,587,229-document Wikipedia index. Even without index-time enrichment, using only grounded Wikipedia categories, SIRA outperforms multi-round Perplexity agents at every budget, reaching 9.70% Recall@1, 15.27% Recall@10, and 36.14% Recall@100. --- ### Inductive Venn-Abers and related regressors Authors: Ivan Petej, Vladimir Vovk Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06646v2 Venn-Abers predictors are probabilistic predictors that enjoy appealing properties of validity, but their major limitation is that they have been applicable only to binary classification, apart from a recent extension to bounded regression. We generalize them to the case of unbounded regression, which requires adding an element of conformal prediction. In our simulation and empirical studies we investigate the predictive efficiency of point regressors derived from Venn-Abers regressors and argue that they somewhat improve the predictive efficiency of standard regressors for larger training sets. --- ### Inductive Venn-Abers and related regressors Authors: Ivan Petej, Vladimir Vovk Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06646v1 Venn-Abers predictors are probabilistic predictors that enjoy appealing properties of validity, but their major limitation is that they are applicable only to the case of binary classification, with a recent extension to bounded regression. We generalize them to the case of unbounded regression, which requires adding an element of conformal prediction. In our simulation and empirical studies we investigate the predictive efficiency of point regressors derived from Venn-Abers regressors and argue that they somewhat improve the predictive efficiency of standard regressors for larger training sets. --- ### Edge-specific signal propagation on mature chromophore-region 3D mechanism graphs for fluorescent protein quantum-yield prediction Authors: Yuchen Xiong, Swee Keong Yeap, Steven Aw Yoong Kit Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06644v2 Fluorescent protein quantum yield (QY) is governed by the mature chromophore and its three-dimensional microenvironment rather than sequence identity alone. Protein language models and emission-band averages capture global trends, but do not model how local physical signals act on specific chromophore regions. We present a chromophore-centred mechanism graph algorithm for QY prediction. Each PDB structure is converted into a typed 3D residue graph, registered to a mature-CRO state, partitioned into phenolate, bridge and imidazolinone regions, and transformed by channel-signal-region propagation. The representation contains 121 enrichment features; after removing identity shortcuts, 52 non-identity features are used for band-specific ExtraTrees regression. Because each feature encodes a contact channel, seed signal and target CRO region, interpretation is intrinsic rather than post hoc. On a 531-protein benchmark, the method achieved the best random-CV performance among model-based baselines (R = 0.772 +/- 0.008, MAE = 0.131 +/- 0.002), exceeding Band mean (R = 0.632), ESM-C (R = 0.734) and SaProt (R = 0.731), and ranked first in bright screening (Bright P@5 = 0.704). Under homology control, the advantage was clearest in the remote bucket (<50% similarity; R = 0.697 versus 0.633, 0.575 and 0.408), with the strongest overall bright/dark Top-K screening. Stable selected features recovered band-specific mechanisms: aromatic packing and clamp asymmetry in GFP-like proteins, charge/clamp balance in Red proteins, and flexibility-risk/bulky-contact features in Far-red proteins. Source code, feature tables and evaluation scripts are available from the first author upon request. Contact: yuchenak05@gmail.com --- ### Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study Authors: Hao Dong, Hongzhao Li, Shupan Li, Muhammad Haris Khan, Eleni Chatzi, Olga Fink Published: 2026-05-07 Categories: cs.CV, cs.AI, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2605.06643v2 Despite the growing popularity of Multimodal Domain Generalization (MMDG) for enhancing model robustness, it remains unclear whether reported performance gains reflect genuine algorithmic progress or are artifacts of inconsistent evaluation protocols. Current research is fragmented, with studies varying significantly across datasets, modality configurations, and experimental settings. Furthermore, existing benchmarks focus predominantly on action recognition, often neglecting critical real-world challenges such as input corruptions, missing modalities, and model trustworthiness. This lack of standardization obscures a reliable assessment of the field's advancement. To address this issue, we introduce MMDG-Bench, the first unified and comprehensive benchmark for MMDG, which standardizes evaluation across six datasets spanning three diverse tasks: action recognition, mechanical fault diagnosis, and sentiment analysis. MMDG-Bench encompasses six modality combinations, nine representative methods, and multiple evaluation settings. Beyond standard accuracy, it systematically assesses corruption robustness, missing-modality generalization, misclassification detection, and out-of-distribution detection. With 7, 402 neural networks trained in total across 95 unique cross-domain tasks, MMDG-Bench yields five key findings: (1) under fair comparisons, recent specialized MMDG methods offer only marginal improvements over ERM baseline; (2) no single method consistently outperforms others across datasets or modality combinations; (3) a substantial gap to upper-bound performance persists, indicating that MMDG remains far from solved; (4) trimodal fusion does not consistently outperform the strongest bimodal configurations; and (5) all evaluated methods exhibit significant degradation under corruption and missing-modality scenarios, with some methods further compromising model trustworthiness. --- ### Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study Authors: Hao Dong, Hongzhao Li, Shupan Li, Muhammad Haris Khan, Eleni Chatzi, Olga Fink Published: 2026-05-07 Categories: cs.CV, cs.AI, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2605.06643v1 Despite the growing popularity of Multimodal Domain Generalization (MMDG) for enhancing model robustness, it remains unclear whether reported performance gains reflect genuine algorithmic progress or are artifacts of inconsistent evaluation protocols. Current research is fragmented, with studies varying significantly across datasets, modality configurations, and experimental settings. Furthermore, existing benchmarks focus predominantly on action recognition, often neglecting critical real-world challenges such as input corruptions, missing modalities, and model trustworthiness. This lack of standardization obscures a reliable assessment of the field's advancement. To address this issue, we introduce MMDG-Bench, the first unified and comprehensive benchmark for MMDG, which standardizes evaluation across six datasets spanning three diverse tasks: action recognition, mechanical fault diagnosis, and sentiment analysis. MMDG-Bench encompasses six modality combinations, nine representative methods, and multiple evaluation settings. Beyond standard accuracy, it systematically assesses corruption robustness, missing-modality generalization, misclassification detection, and out-of-distribution detection. With 7, 402 neural networks trained in total across 95 unique cross-domain tasks, MMDG-Bench yields five key findings: (1) under fair comparisons, recent specialized MMDG methods offer only marginal improvements over ERM baseline; (2) no single method consistently outperforms others across datasets or modality combinations; (3) a substantial gap to upper-bound performance persists, indicating that MMDG remains far from solved; (4) trimodal fusion does not consistently outperform the strongest bimodal configurations; and (5) all evaluated methods exhibit significant degradation under corruption and missing-modality scenarios, with some methods further compromising model trustworthiness. --- ### StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction Authors: Xiangyuan Xue, Yifan Zhou, Zidong Wang, Shengji Tang, Philip Torr, Wanli Ouyang, Lei Bai, Zhenfei Yin Published: 2026-05-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.06642v2 Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficult because current methods are largely purely reactive, which weakens both exploration and credit assignment over extended trajectories. In this work, we present Strategic Trajectory Abstraction (StraTA), a simple framework that introduces an explicit trajectory-level strategy into agentic reinforcement learning (RL). StraTA samples a compact strategy from the initial task state, conditions subsequent actions on that strategy, and trains strategy generation and action execution jointly with a hierarchical GRPO-style rollout design, further enhanced by diverse strategy rollout and critical self-judgment. Experiments on ALFWorld, WebShop, and SciWorld show that StraTA consistently improves both sample efficiency and final performance over strong baselines. StraTA reaches success rates of 93.1% on ALFWorld and 84.2% on WebShop. On SciWorld, StraTA attains a 63.5% overall score, outperforming frontier closed-source models. ---