Large language model agents increasingly retrieve tools from large catalogs, yet most retrievers rank each tool independently by request similarity. For multi tool tasks, this recovers the goal matching tool while omitting prerequisite tools required by the workflow. We introduce LIBRA, a framework for Library Induction by Runtime Assembly that turns a flat tool catalog into an executable tool library. An LLM proposes per tool contracts of candidate invocations, reusable outputs and state changes, and success conditions; LIBRA then tests these compositions in a sandbox and retains the relations supported at runtime. Constructed before user queries, the library requires no dependency annotations, tool use trajectories, or task specific training, and supports both one-shot and agentic retrieval. On AppWorld, BFCL, and SciToolEval, LIBRA improves one-shot Recall and NDCG over the same dense retriever by 7.9 and 3.7 percentage points on average. Within ToolReAGt, it yields corresponding gains of 4.5 and 2.9 points after ten retrieval iterations.
Open-vocabulary detection (OVD) recognizes categories unseen during training through textual category queries, yet achieving strong generalization with real-time efficiency remains challenging. Beyond vocabulary scaling, zero-shot generalization may benefit from reusable visual--semantic cues learned from seen data, including attributes, actions, states, and contextual relations. Existing real-time OVD methods primarily emphasize vocabulary coverage and efficient region/query--text matching; under strict efficiency constraints, compact detectors may struggle to absorb rich instance semantics and scene context. We propose RT-DETR-World, a compact DETR-style detector that transfers the rich semantics conveyed by descriptions during training while retaining lightweight query--text matching at inference. We construct GroundingCapv2 with three levels of supervision: category names for standard OVD, object descriptions conveying instance-level semantics, and image descriptions conveying object relations and scene context. These descriptions serve only as training-time semantic supervision. To help the compact detector absorb these semantics, we propose Dual-Path Description Alignment (DDA), combining a deployment-consistent MiniLM pathway with a training-only LLM teacher. MiniLM provides query--category supervision and object-description alignment, while offline teacher features supervise matched queries and global visual representations at the object and image levels, respectively. All teacher features are precomputed, and the teacher-side modules are removed after training. We further propose Relation-Aware Negative Relaxation (RNR), which uses teacher-derived semantic similarities to relax related negatives while preserving exact positives. Experiments demonstrate competitive zero-shot accuracy and a favorable accuracy--efficiency trade-off. The code will be released.
Enzyme function annotation and the identification of candidate enzymes for a given reaction are essential steps in connecting genomic information to biochemical reaction networks. However, existing methods rely on sequence or structural similarity or on training with known enzyme--reaction pairs, making it difficult to integrate biochemical evidence across large candidate spaces; they also struggle with retrieval tasks involving enzyme families whose members are highly similar. Here, we introduce RIVER (Reaction--enzyme Inference via Evidence-guided Retrieval), a multi-agent framework for bidirectional enzyme--reaction retrieval that identifies potentially catalyzed reactions for a given enzyme and ranks candidate enzymes for a given reaction. RIVER coordinates large language models, specialized biochemical computational tools, and external knowledge resources to assemble evidence at multiple levels, including reaction chemistry, protein sequences and domains, catalytic mechanisms, and database annotations. Dedicated validation modules further examine evidence gaps and potential conflicts and rerank candidates using traceable evidence records. On public benchmarks, RIVER achieves the highest success rates in both enzyme retrieval and enzyme annotation. In family-specific enzyme retrieval, RIVER outperforms the evaluated baselines on the selected datasets and metrics. In Escherichia coli enzyme retrieval tasks constructed from recent literature, RIVER achieves the best retrieval results with closed-source and open-source model configurations, substantially outperforming closed-source general-purpose and biology-specialized multi-agent systems, including Claude Code, Codex, and Phylo Max. These results suggest that evidence-guided multi-agent retrieval can prioritize biochemically supported enzyme--reaction relationships, providing a basis for subsequent experimental validation.
Guanming Liu, Yuqi Ren, Hansu Gu, Peng Zhang, Weihang Wang, Jiahao Liu, Ning Gu, Tun Lu
A central role of personal-agent memory is to turn stored information and prior interactions into future-oriented assistance. In daily use, useful cues come from what the agent observes and how the user interacts with the agent, and the agent must carry them forward from the current request to similar future tasks. Existing memory benchmarks usually test dialogue recall or task improvement in isolation, leaving the trajectory from streaming observations to later assistance largely untested. We introduce StreamMemBench, a streaming benchmark that constructs a two-step task sequence around each evidence anchor from EgoLife egocentric streams. The initial task tests evidence use, while the follow-up task tests whether feedback and interaction experience are reused. Four metrics diagnose evidence recall, initial evidence use, feedback incorporation, and follow-up reuse. Experiments with eight memory systems across two backbones show that current systems often fail to use observed evidence or turn feedback into reliable follow-up behavior, even when evidence is stored or feedback is incorporated locally. StreamMemBench is publicly available at https://github.com/landian60/StreamMemBench.
Reinforcement learning with verifiable rewards (RLVR) often adopts GRPO-style group-relative updates, sampling multiple rollouts per prompt to construct normalized learning signals. However, merely increasing the number of rollouts does not reliably strengthen learning: under GRPO-style group normalization, per-rollout policy-gradient features can concentrate into a low-rank, signed geometry, causing substantial cancellation during aggregation and weakening the effective update. We address this failure mode with SALT, a Subspace-Adaptive geometry pLug-in componenT that uses sample-wise gradient geometry to reweight the coefficients of group-relative updates. SALT estimates a dominant shared subspace from the mini-batch Gram geometry, decomposes group-relative coefficients into shared and residual channels, and adaptively amplifies the residual channel when signed cancellation is severe. Across diverse reasoning-oriented RLVR benchmarks and model scales, SALT improves effective update geometry and performance without modifying the reward model or the rollout sampling procedure.
Unified Multimodal Models (UMMs) aim to support visual understanding and generation within a single model. Existing post-training methods either use understanding as a fixed teacher to improve generation, or rely on ground-truth trajectories to supervise both understanding and generation. Prism instead derives bidirectional supervision from self-generated interleaved rollouts, constructing training targets according to the reliability of their text and image chains. We propose Prism, a bidirectional self-teaching post-training method for UMMs. Like a prism decomposing mixed light, Prism decouples a coupled interleaved trajectory into a text chain and an image chain, assesses the reliability of each chain, and constructs a corresponding training target from their reliability states. Experiments on both SenseNova-U1 and BAGEL show that Prism improves both understanding and generation. On the generation side, GenEval improves from 85.8 to 89.2 (+3.4), and DPG improves from 86.1 to 87.3 (+1.2) on SenseNova-U1. On the understanding side, the total MME score improves from 2282.6 to 2311.6, and MMVP improves from 58.0 to 62.0. Consistent improvements are observed on BAGEL. These results highlight that Prism enables coordinated improvements in generation and understanding by constructing reliability-guided self-training targets from self-generated trajectories, without relying on an external verifier or externally annotated corrected trajectories during target construction.
Multimodal Large Language Models have shown promising capabilities in bridging visual and textual reasoning, yet their reasoning capabilities in Open-Vocabulary Human-Object Interaction (OV-HOI) are limited by cross-modal hallucinations and limited viewpoints of images. To address this, we propose ImagineAgent, an agentic framework that integrates cognitive mapping, tool-augmented reinforcement learning (RL), and generative world modeling for robust OV-HOI understanding. Specifically, we first propose an innovative CoT dataset named hicodet-6K for supervised fine-tuning (SFT), which effectively bridges the perception-to-cognition gap by structuring perceived entities into interaction pairs for comprehensive predictions. Subsequently, we develop a multimodal tool library integrating online retrieval, image cropping, and generative modeling, enabling the agent to dynamically augment reasoning with domain-specific tools to resolve visual-semantic ambiguities and hallucinations during inference. Moreover, we incorporate a generative model to reconstruct alternative viewpoints, enabling the agent to 'imagine' under limited viewpoints. Finally, we propose a composite reward mechanism to jointly optimize prediction accuracy and tool efficiency. Evaluations on both SWIG-HOI and HICO-DET datasets demonstrate that our method achieves state-of-the-art performance while requiring merely 36.7% of the training data compared to existing methods, validating our robustness, empirical effectiveness and efficiency.
Language generation in the limit is a theoretical framework for studying how a generator can learn to produce new valid strings from a stream of positive examples. In this model, an adversary chooses an unknown language from a countable family and enumerates its elements in an arbitrary order, while the generator must eventually output only elements of the language that have not yet appeared in the enumeration. Reliable generation is thus formalized through two eventual guarantees: validity and novelty relative to the observed data. To further quantify the breadth of the generator's outputs, Kleinberg and Wei (FOCS 2025, STOC 2026) introduced lower density as a measure of output coverage. Given an order representing the importance or relevance of possible outputs, lower density is the asymptotic lower bound, as $n$ grows, on the fraction of the first $n$ elements of the target language that the generator outputs before they appear in the data. Kleinberg and Wei showed that $1/2$ is the optimal lower-density guarantee for deterministic algorithms. We develop a simple and unified framework for obtaining optimal lower-density guarantees. We first give a deterministic algorithm that recovers the optimal guarantee of $1/2$ with a significantly simpler analysis than prior work. We then demonstrate the flexibility of our framework through two extensions. First, against an oblivious adversary, randomization raises the optimal guarantee to $1-1/e$. Second, for any finite collection of orders, the optimal deterministic and randomized guarantees can be achieved simultaneously with respect to every order, so accommodating multiple notions of importance or relevance entails no loss in the optimal guarantee.
Real-world forgery is inherently heterogeneous: it manifests not only as digital manipulation but also as physical spoofing, and is carried not only by images but also by videos. Despite substantial progress, a unified anti-forgery foundation model covering such a broad threat spectrum remains absent. In this paper, we present Venus-DefakerOne2, which substantially extends the forensic capability boundary along both the forgery-form and media-type dimensions. Trained on tens of millions of open-source and in-house samples, it incorporates two key designs. Tide-Style-Tuning alternates LoRA and full-parameter fine-tuning to balance computational efficiency, generalization, and hard-sample fitting while mitigating catastrophic forgetting. Entropy-based Test Adaptation determines the optimal prediction modality by analyzing prediction entropy. Venus-DefakerOne2 achieves new state-of-the-art performance across a comprehensive suite of benchmarks, including DeepFake faces (96.7%), AI-generated images (93.3%), tampered documents (87.6%), manipulated natural images (89.6%), physical spoofs (93.1%), and AI-generated videos (96.0%). It significantly outperforms both specialized expert models and its predecessor, DefakerOne, establishing itself as a powerful and versatile foundation model for binary-decision forensic tasks.
Xiaopeng Zhang, Yongjin Mu, Yueyang Weng, Chengzhi Zhao, Yanjie Li
World Action Models (WAMs) have recently shown great promise in robotic control, benefiting from the future imagination capability of large-scale pretrained video models. However, most existing WAMs require explicitly imagining future states at test time, incurring substantial computational overhead and latency that make them unsuitable for real-time robotic control. In this paper, we propose W2A, a two-stage distillation framework for real-time robotic manipulation that distills intermediate denoising representations from a video diffusion model into an action model during training, while entirely discarding the video model at test time. We hypothesize that although video latent representations are high-dimensional, a compressed low-dimensional subspace is sufficient to provide effective supervision for action generation. This makes it possible to transfer such information effectively into an action model. Extensive experiments in both simulation and real-world settings demonstrate competitive success rates while significantly improving inference efficiency. On LIBERO, W2A achieves a 95.9% average success rate. More importantly, W2A achieves about 21x faster inference than the representative WAM baseline.
Video-conditioned audio generation, including Video-to-Sound (V2S) and Visual Text-to-Speech (VisualTTS), has traditionally been studied as two separate tasks despite their shared objective of generating audio conditioned on visual content. Existing methods rely on task-specific architectures and training paradigms, while the possibility of a unified generative framework remains largely unexplored due to heterogeneous conditioning signals and limited joint training data. In this paper, we propose ViSSFlow, a unified flow-matching framework for both V2S and VisualTTS. To effectively integrate diverse conditioning modalities within a Diffusion Transformer (DiT), we introduce a disentangled condition aggregation mechanism that exploits the complementary roles of attention layers, using cross-attention to model semantic conditions and self-attention to capture temporally dense visual cues. Furthermore, contrary to the common assumption that joint optimization of V2S and VisualTTS causes task interference, we show that a single model can be trained end-to-end without sacrificing task-specific performance. To address the scarcity of paired training data covering both sound and speech generation, we further propose a simple yet effective feature-level data synthesis strategy that enables robust joint learning. Extensive experiments on V2S, VisualTTS, and joint generation benchmarks demonstrate that ViSSFlow consistently outperforms state-of-the-art task-specific baselines while providing a unified solution for video-conditioned audio generation. Code and demos are provided in Supplementary Material.
Jindou Jia, Jingliang Li, Kuangji Zuo, Tuo An, Yuxuan Hu, Mengfei Zhao, Bofan Lyu, Jiaqi Bai 等 12 位作者
Most robot policies, whether trained by imitation learning (IL) or reinforcement learning (RL), map observations to action values at discrete control steps and leave the continuity of physical motion to be learned implicitly. We propose ODE policy, which learns the dynamics of the action rather than the action itself. A neural ordinary differential equation (ODE) learns the vector field of the action by matching the integrated actions to the targets over short action chunks in IL and single control steps in RL. A lightweight diversity head captures multi-modal behavior by randomizing the direction of the field. At deployment, each action is integrated from the previous one, so the executed trajectory is continuous by construction. We evaluate it as a visuomotor policy, as the action head of vision-language-action (VLA) and world action models (WAMs), and as the actor of model-based RL against 14 baselines on unimanual, bimanual, dexterous, locomotion, and loco-manipulation tasks. In IL, against flow matching, it reaches 5.9$\times$ the success, 5.4$\times$ the generalization, and 3.9$\times$ the mode balance after one epoch, and generates actions 10.8$\times$ faster. It mostly moves more smoothly than human demonstrations. On 14 real-world tasks across single-arm, dual-arm, dexterous, and humanoid robots, it achieves the highest success rate. In RL, it further speeds up SuperMimic for humanoid motion tracking and smooths its actions. Efficient in learning, data, parameters, and execution, ODE policy offers a promising path to scaling robot learning.
GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling
Kang He, Wenshuo Peng, Chuanhao Li, Zihui Gao, Xiaojie Xu, Zhengyuan Lin, Yuzhe Ding, Donghong Ji 等 10 位作者
AI 速览：作者构建了包含69.7K片段、1,655小时、约3.5亿帧的分钟级游戏视频数据集GameVerse，用于支撑长时程交互式世界模型训练。
Recent advances in interactive world models have made it possible to generate controllable, dynamic environments from action inputs. Yet current models struggle to maintain coherence beyond roughly one minute of rollout, a limitation rooted not in model capacity but in the scarcity of long-horizon training data. Existing gameplay video datasets typically consist of clips under ten seconds, with captions that describe whole clips in coarse and undifferentiated text, which is insufficient for controllable long-horizon generation. We address this with GameVerse, a minute-scale gameplay video dataset purpose-built for long-horizon interactive world modeling. GameVerse contains 69.7K clips spanning 1,655 hours and 349.6 million frames across diverse first- and third-person gameplay, including 1,358 hours of continuous two-minute sequences, an order of magnitude longer than prior datasets. Clips pass through a unified pipeline of scene-consistent segmentation, quality filtering, camera pose estimation, and event-based caption annotation. Each clip is paired with a temporally stable camera trajectory that remains coherent across minutes, together with captions that separate static scene context from dynamic foreground events and align to event boundaries rather than fixed time windows. Comprehensive analysis shows that GameVerse surpasses existing public datasets in scale, diversity, and annotation quality. Experiments further demonstrate that training on GameVerse substantially extends the temporal horizon of interactive world models.
Understanding how humans interact with the world requires a representation of physical interactions at the hand surface. Tactile sensing captures these interactions, but collecting tactile data at scale requires specialized hardware. We introduce TactoHand, a model that predicts three dense hand-surface interaction fields---contact, proximity, and 3D force---from monocular video. We derive geometry-based contact and proximity labels and motion-derived force labels from eligible training data within a curated collection spanning approximately 50 million source frames. TactoHand uses a temporal transformer to aggregate visual evidence across frames, while three learned queries decode the corresponding hand-surface fields. A differentiable physics layer further constrains force predictions using observed object motion. Across in-domain and out-of-domain benchmarks, TactoHand improves contact and proximity estimation over prior methods. In addition, physics supervision reduces position and rotation errors in motion rollouts, and the predicted contact and proximity fields improve downstream hand-object reconstruction. Together, these results show a scalable, low-cost path to learning hand-surface interaction fields without collecting tactile measurements. Code will be released at https://github.com/zhenqis123/Tactohand.
AI coding agents can now build small playable games in minutes, but the results usually look like programmer art: gray blockouts, colored geometric primitives, and flat semantic blobs. We present AnyGameRenderer, a video-to-video generative renderer that turns such footage into high-quality visuals with characters, motion detail, and effects. Throughout, it keeps the layout, camera, and every entity's position and timing intact. Our AnyGameRenderer generalizes across a wide range of genres that agents build, such as tower defense, auto-battlers, top-down survivors, turn-based battles, kart racing, and crowd runners. AnyGameRenderer takes plain video as its game-state input, with no complex representations such as engine G-buffers, per-object class labels, or low-poly proxies. Gray blockouts, colored primitives, semantic maps, and wireframes all work as input. It also preserves entity correspondence: group counts stay correct, and entities appear and disappear on the right frame. We implement AnyGameRenderer by LoRA fine-tuning MiniMax-H3 ref2va, a 33B reference-video-conditioned video generation model. Training uses ~10k paired clips from three sources: (i) multi-stream rendering data from 38 agent-made games; (ii) two-stream rendering data from Unreal Engine, with programmatically controlled crowds, count changes, and entity scales; and (iii) real gameplay recordings, with pairs reconstructed via 3D-box detection. To evaluate the entity correspondence, we propose an entity-level benchmark of 59 held-out cases with 753 entities, scored against ground-truth boxes. Compared with the base model, AnyGameRenderer better preserves entity correspondence: temporal match rises from 50.9% to 62.9%, missed count changes fall from 34.7% to 21.3%, and fewer entities are hallucinated or left unrendered. Project page: https://alaya-lab.github.io/AnyGameRenderer.
Stable training is often treated as evidence that learning is succeeding, but stability characterizes optimization behavior rather than correctness relative to an external objective. We study what happens when the signal being optimized remains persistently biased. We define Stable but Wrong (SBW) as a learning state in which optimization remains active or stabilizes while the learned outcome stays systematically displaced from an independently defined objective. A minimal theoretical model shows that persistent systematic bias can separate a stable convergence point from the true objective even under standard conditions for stable convergence. We then introduce static and dynamic bias in reinforcement learning, supervised learning, and continual fine-tuning of large language models. Across these settings, optimization of the current learning signal continues or stabilizes while correctness relative to the external objective declines or remains displaced. Finally, two controlled challenge-correction experiments with external ground truth test whether a prespecified error can be exposed and changed. In controlled scientific discovery and CIFAR-10, targeted evidence corrects or reduces established errors more effectively than equal-budget general evidence, with no evident harm to paired correct states under the tested protocols. These experiments do not provide a general method for automatically discovering unknown errors. Overall, SBW identifies a basic limit of convergence and other internal optimization metrics as evidence of correctness in systems that learn through persistent bias and feedback.
Embodied systems can update policies, world models, skills, and executable programs from deployment experience, allowing one interaction to benefit later tasks. When a system also revises and reuses its data-acquisition, feedback, or learning procedures, experience changes the process that produces capability, introducing recursive self-improvement. This paper surveys research in physical AI through the connection between persistent capability and its improvement process. We first explain the functional distinction between learner updates and improvers, then compare policy learning, imagined experience, memory and skill accumulation, and executable harnesses. These approaches connect to revisions of curricula, rewards, and research programs in different ways. Contact validity, recovery, retention, and resource costs determine whether the resulting gains accumulate during continued deployment. An L0-L3 rubric distinguishes task-local adaptation, persistent capability gain, inherited process revision, and verified improver gain. Representative benchmarks and within-study contrasts relate these distinctions to existing results. We further propose common-data and interactive comparisons that evaluate reference and revised improvers from shared learner starts, separating the use of experience from its acquisition. This perspective connects the diverse methods, physical operating conditions, and evaluation evidence, underpinning embodied RSI. A comprehensive list of studies in this survey is available at https://github.com/nkd-lkz/physical-ai-rsi-survey.
Modern automatic speech recognition (ASR) systems have achieved remarkable accuracy by scaling model depth and capacity, but at the cost of increased memory, energy, and computational demands. On edge devices where ASR is often most needed, such as watches and glasses, deploying such large models is infeasible due to extremely constrained resources. This raises a fundamental question: can we achieve high representational power in deep ASR models without scaling up parameterization? In this work, we revisit the role of depth and identify layer wise representational dynamics, in which most layers learn functionally similar transformations. Motivated by this insight, we propose a block-recurrent ASR architecture that replaces parameterized depth with a small set of recurrent blocks, each consisting of weight-shared layers, thereby preserving effective depth while drastically reducing model size. Through representation-guided grouping and knowledge distillation, block-recurrent models retain the accuracy of large reference models while using an order of magnitude fewer parameters. Across Open ASR Leaderboard benchmarks, a model with only two shared blocks recovers 97.4% of the accuracy of large models on average. The compact backbone further enables efficient on-device personalization through lightweight MoE-LoRA adaptation, allowing user-specific models to match or surpass the accuracy of general-purpose ASR systems with significantly lower inference cost. By reusing weights across recurrent steps, the proposed architecture reduces memory-access overhead and inference energy consumption. Together, these results show that high quality ASR can be achieved without large parameterization, and that structured recurrence provides a principled path towards ultra-compressed, energy-efficient, and personalized speech recognition on the edge.
Recently, Group Relative Policy Optimization (GRPO) and its variants have been developed for policy optimization and demonstrated notable performance gains. However, these methods usually incur substantial computational overhead due to per-question multi-rollout sampling and repeated per-token probability evaluation across rollouts. Furthermore, low-information or highly homogeneous trajectories can degrade downstream learning signal efficiency, hindering model optimization and limiting final performance. To address these issues, we propose FastRL, a novel plug-and-play reinforcement learning framework that simultaneously improves training efficiency and the effectiveness of policy learning. Specifically, 1) We introduce an advantage-aware pruning strategy to selectively preserve high-advantage trajectories while maximizing inter-trajectory gradient diversity. 2) Then, we design an adaptive rollout sampling mechanism to dynamically adjust the sampling scale across different training stages based on historical pruning distributions, balancing exploration adequacy and computational efficiency. Experiments demonstrate that FastRL can be seamlessly integrated into GRPO, DAPO, and GSPO variants, achieving an average 2.07$\times$ training speedup on Geometry3K and GeoQA8K-R1V, along with an approximately 1.64\% improvement in average accuracy on visual reasoning benchmarks. Source codes will be available at https://github.com/Nicozwy/FastRL.
Self-disclosures on the Web support diverse psychological analyses, from recognizing expressed experiences to identifying symptom-relevant information. We study a shared, question-conditioned decision interface for this heterogeneous problem in content analysis. We organize PsyJudgeBench, comprising 13 annotated datasets and 82 questions across six psychological areas, while preserving source-specific criteria and masks for unobserved labels. We introduce PsyJev, a System-1 model that directly produces distributions over answers specified in each request. Joint supervised training establishes the shared judgment function, followed by Judgment-Anchored RLCD (JA-RLCD), which adapts logit-space reward optimization to heterogeneous psychological judgments through balanced supervision, selective retention of correct SFT predictions, and question-group reward optimization. The Qwen3.5-based 2B, 4B, and 9B models achieve 64.33, 66.21, and 67.56 average test F1, respectively. The 9B model exceeds the strongest external comparison by 2.54 points. Controlled 2B comparisons examine the training stages and anchored refinement. Further analyses examine question-conditioned judgment, inference cost, and probability quality, complemented by qualitative comparisons across models.
Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity. A key insight is that tasks with different modalities and surface forms can share the same underlying capability requirements. We therefore introduce The Trinity, a recursive self-improvement framework coupling world generation with Harness evolution through three roles: Creator, Explorer, and Evolver. Drawing on verified execution trajectories, Evolver shifts the basis of task organization from surface categories to shared requirements, reorganizing the original task tree into a hierarchical capability tree. We introduce Capability-Driven Real2Sim2Real: for heterogeneous tasks at the same node, Creator abstracts their common requirements into simplified, verifiable simulated worlds for capability learning, while evaluation on original tasks measures transfer. Along this capability tree, Explorer progressively evolves reusable capability modules through selective inheritance, forming a Harness tree whose validated updates accumulate across iterations within a fixed topology. The resulting Harnesses specialize in different capabilities, motivating a Capability-Aware Harness Router that uses public task information to select compatible module configurations from the tree. Our evolved Harnesses improve mean performance by 34 points across 28 training benchmarks and 26 points across 18 unseen benchmarks, including two real-world embodied tasks.
Zhenzhen Ren, Xiaoqing Zhang, GuoBiao Li, Bowen Fang, Yanxi Wang, Xinpeng Zhang, Ke Han
Trajectory-based confidence estimation has shown promising performance for large language models (LLMs) by leveraging rich signals from their reasoning processes. However, we find that such confidence estimators can degrade substantially after agentic reinforcement learning (Agentic RL) as it induces substantial shifts in the reasoning trajectories. More importantly, despite these shifts, we uncover a reliability structure that is largely preserved across Base and RL models: $\textbf{more}$ $\textbf{stable}$ $\textbf{trajectories}$ $\textbf{remain}$ $\textbf{more}$ $\textbf{likely}$ $\textbf{to}$ $\textbf{produce}$ $\textbf{correct}$ $\textbf{answers}$. This preserved relationship provides a transferable, label-free reliability signal for post-RL confidence adaptation. Building on this finding, we propose $\textbf{StaR-TTA}$, a stability-guided framework for label-free test-time confidence adaptation. StaR-TTA jointly learns from correctness supervision and stability-derived reliability supervision on labeled Base trajectories, establishing the connection between trajectory stability and answer reliability. At test time, it reuses stability-induced reliability rankings from unlabeled RL trajectories to adapt confidence scores to the shifted trajectory distribution, without requiring target correctness labels. Across four QA benchmarks, StaR-TTA achieves an average AUROC of \(0.721\), with consistent improvements across unseen datasets, model families and scales, and different Agentic RL algorithms.
Large language models incur substantial training and inference costs in personalized search and recommendation, as growing interaction histories lengthen request inputs and repeatedly expose the same item text to the model. We propose \textbf{C}omposable and \textbf{R}eusable \textbf{I}tem \textbf{M}emory (CRIM), a framework that separates item-level semantic encoding from request-level history modeling. A small set of learnable summary tokens compresses each item into compact continuous memories, while segment-level readout tokens (REC tokens) introduce predictive supervision within the interaction history. These memories are independent of users and queries and can therefore be reused across requests. At inference time, CRIM composes cached memories in interaction order and incorporates an optional query to produce a personalized retrieval representation, reducing repeated item-text encoding while retaining request-dependent contextual modeling. We further introduce a joint training mechanism that combines cached memories with sampled live re-encoding. Re-encoding only a few history items per request allows the retrieval objective to jointly optimize the item and request encoders at limited computational cost, while periodic cache refreshes maintain consistency. Extensive evaluation and cost analysis on MovieLens-1M, Qilin, and our new LazSeq dataset show that CRIM achieves state-of-the-art retrieval performance with substantially lower inference costs at the same backbone scale, while limiting item re-encoding during joint training. We will publicly release our code and dataset.
Bo Liu, Tong Li, Jiapeng Zhang, Zhu Xiao, Zhuo Tang, Kenli Li
Human mobility data are fundamental to Web-based location services and broader urban applications, and mobility generation provides synthetic trajectories when real data are costly or inaccessible. Although recent mobility generators have incorporated collective mobility patterns, they primarily focus on individual trajectories and aggregate population dynamics, leaving evolving community structures formed by user-location interactions insufficiently modeled. In this paper, we study community-consistent human mobility generation. To this end, we formulate mobility generation as the generation of dynamic user-location graphs to model community structures and propose MOTION, a Multi-agent framework for cOmmuniTy-consIstent human mObility geNeration. MOTION consists of user agents, location agents, and a global manager agent. MOTION first detects coherent communities from historical mobility using the Leiden algorithm and extracts community-conditioned interaction priors to guide the generation process. Guided by these priors, the user agents plan mobility, search destination candidates, and infer user movements from the individual view. In parallel, selectively activated location agents infer likely user arrivals from the community view. The manager coordinates both views, diagnoses interactions causing deviations, and attributes targeted reflection signals to revise user decisions, location attraction, and source-user selection. Experiments on two real-world datasets show that MOTION outperforms baselines by at least 4.05% across reported metrics of individual trajectories, population and flow distributions, and community and graph structures. Further analyses confirm its robustness, privacy preservation, and downstream utility. The code is available at https://anonymous.4open.science/r/MOTION-04C4.
Haiyong Tang, Hanzhou Wu, Xinpeng Zhang, Athanasios V. Vasilakos
Large language models (LLMs) are valuable digital assets, yet their weights can be easily modified after unauthorized acquisition, making model provenance difficult to verify. Model fingerprinting provides a promising solution for model ownership protection without modifying the model or embedding ownership information. However, parameter-based fingerprints can be sensitive to model transformations, limiting their robustness, while representation-based fingerprints may assign high similarity to unrelated models, limiting their uniqueness. To address these limitations, we propose TrFP, an intrinsic fingerprinting method based on computational trajectories. Instead of comparing model parameters or representations, TrFP captures how representations evolve across network depth and constructs compact fingerprints using permutation-invariant trajectory descriptors. Experiments across multiple LLM families show that TrFP reliably distinguishes related and unrelated models. It also remains robust under fine-tuning, pruning, quantization, model merging, parameter permutation, and adaptive attacks, while requiring less than 0.3 MiB of fingerprint storage. Overall, TrFP provides stronger provenance discrimination than several existing state-of-the-art methods, demonstrating the effectiveness of computational trajectories for reliable LLM provenance verification.
Junhan Liu, Zhenke Liu Brown University, Yongcheng Shi, Peilin Yu Apple, Minxing Zhang, Jiapeng Zhang University of Southern California
Gardener is an interactive agentic system for single-cell RNA-seq (scRNA-seq) analysis that enables expert-steered, iterative workflows under strict data-residency requirements. Existing large language model (LLM)-based analysis agents commonly encode workflow progress as implicit conversational state and rely on cloud-centric execution, which hinders traceability and auditability and complicates keeping sensitive expression data on-device. Gardener grounds cloud-side reasoning in a local, on-device scientific engine and an Experiment Management Kernel (EMK) that externalizes analysis progress as persistent, immutable snapshots linked by lineage. This explicit state representation supports rollback, branching, and comparison of alternative analysis paths while reusing prior computation. Gardener enforces data isolation by design: cloud-hosted LLMs operate only on snapshot identifiers and sanitized summaries, while raw expression matrices and local artifacts remain on the user’s device. A local graphical user interface (GUI) provides human-in-the-loop steering and inspection of workflow state and outputs. Gardener is released as an open-source desktop application for macOS and Windows under the Apache License 2.0.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表
Haojin Yang, Ai Jian, Yiwei Wang, Xinyue Huang, Weipeng Zhang, Ke Zeng, Xunliang Cai, Jingqing Ruan
Optimizing large language models for industrial sales requires balancing long-term commercial objectives (e.g., conversion rate) with immediate linguistic constraints such as fluency and compliance. Conventional reinforcement learning often merges these heterogeneous goals into a single reward, causing high-magnitude session-level rewards to overwhelm subtler turn-level signals, which leads to unstable training or reward hacking.To address this issue, we propose Dual-Horizon Credit Assignment (DuCA), a framework that disentangles optimization across time scales. Its core, Horizon-Independent Advantage Normalization (HIAN), separately normalizes advantages from turn-level and session-level rewards before fusion, ensuring balanced gradient contributions from both immediate and long-term objectives to the policy update.Extensive experiments with a high-fidelity user simulator show DuCA outperforms the state-of-the-art GRPO baseline, achieving a 6.82% relative improvement in conversion rate, reducing inter-sentence repetition by 82.28%, and lowering identity detection rate by 27.35%, indicating a substantial improvement for an industrial sales scenario that effectively balances the dual demands of strategic performance and naturalistic language generation.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表
Feiyu Zhao, Yiming Chen, Wenhuan Lu Tianjin University, China, Daipeng Zhang, Xianghu Yue, Jianguo Wei Tianjin University
Large Audio-Language Models (LALMs) have recently achieved strong performance across various audio-centric tasks. However, hallucination, where models generate responses that are semantically incorrect or acoustically unsupported, remains largely underexplored in the audio domain. Existing hallucination benchmarks mainly focus on text or vision, while the few audio-oriented studies are limited in scale, modality coverage, and diagnostic depth. We therefore introduce HalluAudio, the first large-scale benchmark for evaluating hallucinations across speech, environmental sound, and music. HalluAudio comprises over 5K human-verified QA pairs and spans diverse task types, including binary judgments, multi-choice reasoning, attribute verification, and open-ended QA. To systematically induce hallucinations, we design adversarial prompts and mixed-audio conditions. Beyond accuracy, our evaluation protocol measures hallucination rate, yes/no bias, error-type analysis, and refusal rate, enabling a fine-grained analysis of LALM failure modes. We benchmark a broad range of open-source and proprietary models, providing the first large-scale comparison across speech, sound, and music. Our results reveal significant deficiencies in acoustic grounding, temporal reasoning, and music attribute understanding, underscoring the need for reliable and robust LALMs.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zhuo Li The Chinese University of Hong Kong, Shenzhen, Yupeng Zhang Alibaba Group, Pengyu Cheng Alibaba Group, Jiajun Song Beijing Institute for General Artificial Intelligence, Mengyu Zhou Alibaba Group, Hao Li, Shujie Hu, Yu Qin 等 11 位作者
Hallucination remains a critical bottleneck for large language models (LLMs), undermining their reliability in real-world applications, especially in Retrieval-Augmented Generation (RAG) systems. While existing hallucination detection methods employ LLM-as-a-judge to verify LLM outputs against retrieved evidence, they suffer from inherent confirmation bias, where the verifier inadvertently reproduces the errors of the original generation. To address this, we introduce Multi-Agent Reinforced self-Check for Hallucination (MARCH), a framework that enforces rigorous factual alignment by leveraging deliberate information asymmetry. MARCH orchestrates a collaborative pipeline of three specialized agents: a Solver, a Proposer, and a Checker. The Solver generates an initial RAG response, which the Proposer decomposes into claim-level verifiable atomic propositions. Crucially, the Checker validates these propositions against retrieved evidence in isolation, deprived of the Solver’s original output. This well-crafted information asymmetry scheme breaks the cycle of self-confirmation bias. By training this pipeline with multi-agent reinforcement learning (MARL), we enable the agents to co-evolve and optimize factual adherence. Extensive experiments across hallucination benchmarks demonstrate that MARCH substantially reduces hallucination rates. Notably, an 8B-parameter LLM equipped with MARCH achieves performance competitive with powerful closed-source models. MARCH paves a scalable path for factual self-improvement of LLMs through co-evolution. The code is at https://github.com/Qwen-Applications/MARCH.
尚无 AI 解读，展示原文摘要
cs.CL · cs.MA
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Runtao Liu, Ziyi Liu Beijing University of Posts and Telecommunications, Jiaqi Tang, Yue Ma, Renjie Pi, Jipeng Zhang Microsoft, Qifeng Chen Hong Kong University of Science and Technology
Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets, weakening temporal grounding and missing fine-grained cues. We propose a multi-agent framework in which a master LLM coordinates a grounding agent to localize question-relevant segments and a vision agent to extract targeted textual observations. The master agent plans with a step limit, and is trained with reinforcement learning to encourage concise, correct, and efficient multi-agent cooperation. This design helps the master agent focus on relevant clips via grounding, complements subtitles with visual detail, and yields interpretable trajectories. On our proposed LongTVQA and LongTVQA+ which are episode-level datasets aggregated from TVQA/TVQA+, our multi-agent system significantly outperforms strong non-agent baselines. Experiments also show reinforcement learning further strengthens reasoning and planning for the trained agent.
尚无 AI 解读，展示原文摘要
cs.CL · cs.MA · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表