arXiv:2512.16301v3 Announce Type: replace Abstract: Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents accumulate persistent memory and reusable skills. Yet the research landscape remains fragmented across post-training, retrieval, memory, and skill systems. This survey studies these developments under a single notion of \emph{adaptation}: improving an agent, its tools, or their interaction after pretraining. We organize the field with a four-paradigm framework spanning agent adaptation and tool adaptation. On the agent side, A1 (tool-execution-signaled) and A2 (agent-output-signaled) improve the agent itself through supervised fine-tuning, preference optimization, and reinforcement learning with verifiable rewards. On the tool side, T1 (agent-agnostic) provides reusable pre-trained modules any agent can call, while T2 (agent-supervised) uses the agent's outputs to train memory systems, skill libraries, or lightweight subagents. Using this framework, we review post-training methods, adaptive memory architectures, and agent skills; compare their trade-offs in cost, flexibility, and generalization; and summarize evaluation practices across deep research, software development, computer use, and drug discovery. We conclude by outlining open problems in agent-tool co-adaptation, continual learning, safety, and efficient deployment.

arXiv:2602.13810v2 Announce Type: replace-cross Abstract: Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling process, they still face a trade-off between expressiveness and computational burden, which is typically controlled by the number of flow steps. In this work, we propose mean velocity policy (MVP), a new generative policy function that models the mean velocity field to achieve the fastest one-step action generation. To ensure its high expressiveness, an instantaneous velocity constraint (IVC) is introduced on the mean velocity field during training. We theoretically prove that this design explicitly serves as a crucial boundary condition, thereby improving learning accuracy and enhancing policy expressiveness. Empirically, our MVP achieves state-of-the-art success rates across several challenging robotic manipulation tasks from Robomimic and OGBench. It also delivers substantial improvements in training and inference speed over existing flow-based policy baselines.

arXiv:2602.17911v2 Announce Type: replace-cross Abstract: Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is inherently conditional: nearly every decision depends on patient-specific factors such as comorbidities and contraindications. Existing benchmarks do not evaluate such conditional reasoning, and retrieval-augmented or graph-based methods lack explicit mechanisms to ensure that retrieved knowledge is applicable to given context. To address this gap, we propose CondMedQA, the first benchmark for conditional biomedical QA, consisting of multi-hop questions whose answers vary with patient conditions. Furthermore, we propose Condition-Gated Reasoning (CGR), a novel framework that constructs condition-aware knowledge graphs and selectively activates or prunes reasoning paths based on query conditions. Our findings show that CGR more reliably selects condition-appropriate answers while matching or exceeding state-of-the-art performance on biomedical QA benchmarks, highlighting the importance of explicitly modeling conditionality for robust medical reasoning.

arXiv:2603.03344v1 Announce Type: cross Abstract: Earthquake detection and seismic phase picking are fundamental yet challenging tasks in seismology due to low signal-to-noise ratios, waveform variability, and overlapping events. Recent deep-learning models achieve strong results but rely on large datasets and heavy backpropagation training, raising concerns over efficiency, interpretability, and sustainability. We propose GreenPhase, a multi-resolution, feed-forward, and mathematically interpretable model based on the Green Learning framework. GreenPhase comprises three resolution levels, each integrating unsupervised representation learning, supervised feature learning, and decision learning. Its feed-forward design eliminates backpropagation, enabling independent module optimization with stable training and clear interpretability. Predictions are refined from coarse to fine resolutions while computation is restricted to candidate regions. On the Stanford Earthquake Dataset (STEAD), GreenPhase achieves excellent performance with F1 scores of 1.0 for detection, 0.98 for P-wave picking, and 0.96 for S-wave picking. This is accomplished while reducing the computational cost (FLOPs) for inference by approximately 83% compared to state-of-the-art models. These results demonstrate that the proposed model provides an efficient, interpretable, and sustainable alternative for large-scale seismic monitoring.

arXiv:2510.18573v2 Announce Type: replace-cross Abstract: We present Kaleido, a subject-to-video~(S2V) generation framework, which aims to synthesize subject-consistent videos conditioned on multiple reference images of target subjects. Despite recent progress in S2V generation models, existing approaches remain inadequate at maintaining multi-subject consistency and at handling background disentanglement, often resulting in lower reference fidelity and semantic drift under multi-image conditioning. These shortcomings can be attributed to several factors. Primarily, the training dataset suffers from a lack of diversity and high-quality samples, as well as cross-paired data, i.e., paired samples whose components originate from different instances. In addition, the current mechanism for integrating multiple reference images is suboptimal, potentially resulting in the confusion of multiple subjects. To overcome these limitations, we propose a dedicated data construction pipeline, incorporating low-quality sample filtering and diverse data synthesis, to produce consistency-preserving training data. Moreover, we introduce Reference Rotary Positional Encoding (R-RoPE) to process reference images, enabling stable and precise multi-image integration. Extensive experiments across numerous benchmarks demonstrate that Kaleido significantly outperforms previous methods in consistency, fidelity, and generalization, marking an advance in S2V generation.

arXiv:2505.02156v5 Announce Type: replace-cross Abstract: Effective social intelligence simulation requires language agents to dynamically adjust reasoning depth, a capability notably absent in current studies. Existing methods either lack explicit reasoning or employ lengthy Chain-of-Thought reasoning uniformly across all scenarios, resulting in excessive token usage and inflexible social behaviors in tasks such as negotiation or collaboration. To address this, we propose an $\textbf{A}$daptive $\textbf{S}$ocial $\textbf{L}$earning ($\textbf{ASL}$) framework in this paper, aiming to improve the adaptive reasoning ability of language agents in dynamic social interactions. To this end, we first identify the hierarchical reasoning modes under such context, ranging from intuitive response to deep deliberation based on the cognitive control theory. We then develop the $\textbf{A}$daptive $\textbf{M}$ode $\textbf{P}$olicy $\textbf{O}$ptimization ($\textbf{AMPO}$) algorithm to learn the context-aware mode adaptation and reasoning. Our framework advances existing research in three key aspects: (1) Multi-granular reasoning mode design, (2) Context-aware mode switching in rich social interaction, and (3) Token-efficient reasoning with depth adaptation. Extensive experiments on the benchmark social intelligence environment verify that ASL achieves 15.6% higher task performance than GPT-4o. Notably, our AMPO outperforms GRPO by 7.0% with 32.8% shorter thinking chains, demonstrating the advantages of our AMPO and the learned adaptive reasoning ability over GRPO's solution.

arXiv:2509.11663v2 Announce Type: replace-cross Abstract: This paper formulates the Embodied Questions Answering (EQsA) problem, introduces a corresponding benchmark, and proposes an agentic system to tackle the problem. Classical Embodied Question Answering (EQA) is typically formulated as answering one single question by actively exploring a 3D environment. Real deployments, however, often demand handling multiple questions that may arrive asynchronously and carry different urgencies. We formalize this setting as Embodied Questions Answering (EQsA) and present ConEQsA, an agentic framework for concurrent, urgency-aware scheduling and answering. ConEQsA leverages shared group memory to reduce redundant exploration, and a priority-planning method to dynamically schedule questions. To evaluate the EQsA setting fairly, we contribute the Concurrent Asynchronous Embodied Questions (CAEQs) benchmark containing 40 indoor scenes and five questions per scene (200 in total), featuring asynchronous follow-up questions and human-annotated urgency labels. We further propose metrics for EQsA performance: Direct Answer Rate (DAR), and Normalized Urgency-Weighted Latency (NUWL), which serve as a fair evaluation protocol for EQsA. Empirical evaluations demonstrate that ConEQsA consistently outperforms strong sequential baselines, and show that urgency-aware, concurrent scheduling is key to making embodied agents responsive and efficient under realistic, multi-question workloads. Code is available on https://anonymous.4open.science/r/ConEQsA.

arXiv:2602.18473v1 Announce Type: cross Abstract: Accurate analysis of medical time series (MedTS) data, such as electroencephalography (EEG) and electrocardiography (ECG), plays a pivotal role in healthcare applications, including the diagnosis of brain and heart diseases. MedTS data typically exhibit two critical patterns: temporal dependencies within individual channels and channel dependencies across multiple channels. While recent advances in deep learning have leveraged Transformer-based models to effectively capture temporal dependencies, they often struggle with modeling channel dependencies. This limitation stems from a structural mismatch: MedTS signals are inherently centralized, whereas the Transformer's attention mechanism is decentralized, making it less effective at capturing global synchronization and unified waveform patterns. To address this mismatch, we propose CoTAR (Core Token Aggregation-Redistribution), a centralized MLP-based module designed to replace decentralized attention. Instead of allowing all tokens to interact directly, as in standard attention, CoTAR introduces a global core token that serves as a proxy to facilitate inter-token interactions, thereby enforcing a centralized aggregation and redistribution strategy. This design not only better aligns with the centralized nature of MedTS signals but also reduces computational complexity from quadratic to linear. Experiments on five benchmarks validate the superiority of our method in both effectiveness and efficiency, achieving up to a 12.13% improvement on the APAVA dataset, while using only 33% of the memory and 20% of the inference time compared to the previous state of the art. Code and all training scripts are available at https://github.com/Levi-Ackman/TeCh.

arXiv:2602.07883v2 Announce Type: replace Abstract: Agentic systems powered by Large Language Models (LLMs) have demonstrated remarkable potential in tackling complex, long-horizon tasks. However, their efficacy is fundamentally constrained by static configurations governing agent behaviors, which are fixed prior to execution and fail to adapt to evolving task dynamics. Existing approaches, relying on manual orchestration or heuristic-based patches, often struggle with poor generalization and fragmented optimization. To transcend these limitations, we propose ToolSelf, a novel paradigm enabling tool-driven runtime self-reconfiguration. By abstracting configuration updates as a callable tool, ToolSelf unifies task execution and self-adjustment into a single action space, achieving a phase transition from external rules to intrinsic parameters. Agents can thereby autonomously update their sub-goals and context based on task progression, and correspondingly adapt their strategy and toolbox, transforming from passive executors into dual managers of both task and self. We further devise Configuration-Aware Two-stage Training (CAT), combining rejection sampling fine-tuning with trajectory-level reinforcement learning to internalize this meta-capability. Extensive experiments across diverse benchmarks demonstrate that ToolSelf rivals specialized workflows while generalizing to novel tasks, achieving a 24.1% average performance gain and illuminating a path toward truly self-adaptive agents.

arXiv:2602.10604v2 Announce Type: replace-cross Abstract: We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/full attention and Multi-Token Prediction (MTP-3) to reduce the latency and cost of multi-round agentic interactions. To reach frontier-level intelligence, we design a scalable reinforcement learning framework that combines verifiable signals with preference feedback, while remaining stable under large-scale off-policy training, enabling consistent self-improvement across mathematics, code, and tool use. Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and 51.0% on Terminal-Bench 2.0, comparable to frontier models such as GPT-5.2 xHigh and Gemini 3.0 Pro. By redefining the efficiency frontier, Step 3.5 Flash provides a high-density foundation for deploying sophisticated agents in real-world industrial environments.

arXiv:2602.12691v2 Announce Type: replace-cross Abstract: We study how to improve large foundation vision-language-action (VLA) systems through online reinforcement learning (RL) in real-world settings. Central to this process is the value function, which provides learning signals to guide VLA learning from experience. In practice, the value function is estimated from trajectory fragments collected from different data sources, including historical policies and intermittent human interventions. Estimating the value function of current behavior quality from the mixture data is inherently an off-policy evaluation problem. However, prior work often adopts conservative on-policy estimation for stability, which avoids direct evaluation of the current high-capacity policy and limits learning effectiveness. In this paper, we propose ALOE, an action-level off-policy evaluation framework for VLA post-training. ALOE applies chunking-based temporal-difference bootstrapping to evaluate individual action sequences instead of predicting final task outcomes. This design improves effective credit assignment to critical action chunks under sparse rewards and supports stable policy improvement. We evaluate our method on three real-world manipulation tasks, including smartphone packing as a high-precision task, laundry folding as a long-horizon deformable-object task, and bimanual pick-and-place involving multi-object perception. Across all tasks, ALOE improves learning efficiency without compromising execution speed, showing that off-policy RL can be reintroduced in a reliable manner for real-world VLA post-training. Videos and additional materials are available at our project website.

arXiv:2602.13562v1 Announce Type: cross Abstract: While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures. For safety alignment, the core challenge lies in the inherent trade-off between safety and utility. However, prevailing alignment strategies typically construct CoT training data with explicit safety rules via context distillation. This approach inadvertently limits reasoning capabilities by creating a rigid association between rule memorization and refusal. To mitigate the safety-utility trade-off, we propose the Adaptive Safe Context Learning (ASCL) framework to improve the reasoning given proper context. ASCL formulates safety alignment as a multi-turn tool-use process, empowering the model to autonomously decide when to consult safety rules and how to generate the ongoing reasoning. Furthermore, to counteract the preference for rule consultation during RL, we introduce Inverse Frequency Policy Optimization (IFPO) to rebalance advantage estimates. By decoupling rule retrieval and subsequent reasoning, our method achieves higher overall performance compared to baselines.

arXiv:2602.13671v1 Announce Type: cross Abstract: Large Language Model (LLM)-based multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. However, existing works often rely on manual designs or "one-size-fits-all" automation, lacking dynamic adaptability after deployment. Inspired by how biological systems adapt, we introduce MASFly, a novel multi-agent framework enabling dynamic adaptation at test time. To adapt system generation, MASFly employs a retrieval-augmented SOP instantiation mechanism that leverages a self-constructed repository of successful collaboration patterns, enabling the LLM to assemble customized MASs for new queries. For adaptive execution, MASFly incorporates an experience-guided supervision mechanism, where a dedicated Watcher agent monitors system behaviors with reference to a personalized experience pool and provides real-time interventions. Extensive experiments demonstrate that MASFly achieves state-of-the-art performance, most notably a 61.7% success rate on the TravelPlanner benchmark, while exhibiting strong task adaptability and robustness.

arXiv:2602.13704v1 Announce Type: cross Abstract: In this work, we presented Pailitao-VL, a comprehensive multi-modal retrieval system engineered for high-precision, real-time industrial search. We here address three critical challenges in the current SOTA solution: insufficient retrieval granularity, vulnerability to environmental noise, and prohibitive efficiency-performance gap. Our primary contribution lies in two fundamental paradigm shifts. First, we transitioned the embedding paradigm from traditional contrastive learning to an absolute ID-recognition task. Through anchoring instances to a globally consistent latent space defined by billions of semantic prototypes, we successfully overcome the stochasticity and granularity bottlenecks inherent in existing embedding solutions. Second, we evolved the generative reranker from isolated pointwise evaluation to the compare-and-calibrate listwise policy. By synergizing chunk-based comparative reasoning with calibrated absolute relevance scoring, the system achieves nuanced discriminative resolution while circumventing the prohibitive latency typically associated with conventional reranking methods. Extensive offline benchmarks and online A/B tests on Alibaba e-commerce platform confirm that Pailitao-VL achieves state-of-the-art performance and delivers substantial business impact. This work demonstrates a robust and scalable path for deploying advanced MLLM-based retrieval architectures in demanding, large-scale production environments.

arXiv:2602.13810v1 Announce Type: cross Abstract: Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling process, they still face a trade-off between expressiveness and computational burden, which is typically controlled by the number of flow steps. In this work, we propose mean velocity policy (MVP), a new generative policy function that models the mean velocity field to achieve the fastest one-step action generation. To ensure its high expressiveness, an instantaneous velocity constraint (IVC) is introduced on the mean velocity field during training. We theoretically prove that this design explicitly serves as a crucial boundary condition, thereby improving learning accuracy and enhancing policy expressiveness. Empirically, our MVP achieves state-of-the-art success rates across several challenging robotic manipulation tasks from Robomimic and OGBench. It also delivers substantial improvements in training and inference speed over existing flow-based policy baselines.

arXiv:2602.13891v1 Announce Type: cross Abstract: Recent advances in speech language models, such as GPT-4o Voice Mode and Gemini Live, have demonstrated promising speech generation capabilities. Nevertheless, the aesthetic naturalness of the synthesized audio still lags behind that of human speech. Enhancing generation quality requires a reliable evaluator of speech naturalness. However, existing naturalness evaluators typically regress raw audio to scalar scores, offering limited interpretability of the evaluation and moreover fail to generalize to speech across different taxonomies. Inspired by recent advances in generative reward modeling, we propose the Generative Speech Reward Model (GSRM), a reasoning-centric reward model tailored for speech. The GSRM is trained to decompose speech naturalness evaluation into an interpretable acoustic feature extraction stage followed by feature-grounded chain-of-thought reasoning, enabling explainable judgments. To achieve this, we curated a large-scale human feedback dataset comprising 31k expert ratings and an out-of-domain benchmark of real-world user-assistant speech interactions. Experiments show that GSRM substantially outperforms existing speech naturalness predictors, achieving model-human correlation of naturalness score prediction that approaches human inter-rater consistency. We further show how GSRM can improve the naturalness of speech LLM generations by serving as an effective verifier for online RLHF.

arXiv:2602.14879v1 Announce Type: cross Abstract: Artificial intelligence (AI) can automatically delineate lesions on computed tomography (CT) and generate radiology report content, yet progress is limited by the scarcity of publicly available CT datasets with lesion-level annotations. To bridge this gap, we introduce CT-Bench, a first-of-its-kind benchmark dataset comprising two components: a Lesion Image and Metadata Set containing 20,335 lesions from 7,795 CT studies with bounding boxes, descriptions, and size information, and a multitask visual question answering benchmark with 2,850 QA pairs covering lesion localization, description, size estimation, and attribute categorization. Hard negative examples are included to reflect real-world diagnostic challenges. We evaluate multiple state-of-the-art multimodal models, including vision-language and medical CLIP variants, by comparing their performance to radiologist assessments, demonstrating the value of CT-Bench as a comprehensive benchmark for lesion analysis. Moreover, fine-tuning models on the Lesion Image and Metadata Set yields significant performance gains across both components, underscoring the clinical utility of CT-Bench.

arXiv:2502.14560v4 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a promising approach for aligning large language models with human preferences. While prior work mainly extends DPO from the aspect of the objective function, we instead improve DPO from the largely overlooked but critical aspect of data selection. Specifically, we address the issue of parameter shrinkage caused by noisy data by proposing a novel margin-maximization principle for dataset curation in DPO training. To further mitigate the noise in different reward models, we propose a Bayesian Aggregation approach that unifies multiple margin sources (external and implicit) into a single preference probability. Extensive experiments in diverse settings demonstrate the consistently high data efficiency of our approach. Remarkably, by using just 10\% of the Ultrafeedback dataset, our approach achieves 3\% to 8\% improvements across various Llama, Mistral, and Qwen models on the AlpacaEval2 benchmark. Furthermore, our approach seamlessly extends to iterative DPO, yielding a roughly 3\% improvement with 25\% online data, revealing the high redundancy in this presumed high-quality data construction manner. These results highlight the potential of data selection strategies for advancing preference optimization.