Artificial Intelligence
Learning in Dreams, Winning in Reality: A Continuous Dyna Loop for a Ten-Hero MOBA
Jordy Kieto
World models are usually judged from the inside: by prediction loss, by the return a policy earns in imagination, or by how convincing their frames look. We judge one from the outside. We learn a structured, multi-
agent world model of a complete ten-hero MOBA (206 units, every hero acting every tick, games of up to 6,000 ticks), train a policy only inside it with 1,400-tick free-running imagined episodes, and measure that policy in the real game against the opponent the game ships with. The real game never provides a gradient; it provides the policy's own games as training data for the world model, and an online evaluation that selects and anchors the policy. Run as a continuous asynchronous Dyna loop, the policy wins 70.2% of real games as radiant (421 of 600; 95% CI 66.4-73.7) on seeds never used for any decision, up from 0% for dream training alone and 33.7% before the loop. It wins none as dire, and neither does the shipped opponent when it plays itself. Four findings explain the result. Model exploitation is invisible from inside the dream: every unanchored run collapsed within a few updates while no in-dream metric tracked the collapse. A world model that is accurate on its training corpus is badly wrong on the policy's own games, and Dyna repairs it there, which is worth +9.2 points of real win rate with the policy recipe held fixed. Finally, the policy inherits its world model's fidelity profile mechanic by mechanic: the model represents the macro game but not crowd control, cast timing or lethality, and the policy wins by map-wide pressure with almost no coordinated fighting. We release the world model, the dream-PPO harness, a world-model debugger, the evaluation protocol, and every policy and log.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
TICDA: Tabular In-Context Data Attribution
Yacine Benihaddadene, Milan Bhan, Eliot Dugelay et al. (+4 more)
Tabular foundation models (TFMs) achieve strong predictive performance by conditioning on labeled demonstrations provided in context, without any parameter update. Yet how individual demonstrations shape a given prediction remains poorly understood. This gap matters in practice: the context is often assembled from whatever labeled data is available, potentially leading to the inclusion of mislabeled, redundant, or low-quality examples that degrade performance. Standard data attribution methods do not transfer to the TFM setting: resampling-based approaches such as DemoShapley require a combinatorial number of forward passes, and gradient-based
estimators such as influence functions require computing training point's effect on the model parameters, which in-context learning never updates. We introduce TICDA, a method that measures the influence of every demonstration in the context directly from linear surrogates trained on TFM latent
embeddings, in a single forward pass and at negligible cost. We show that TICDA offers the best compromise against competitors across four tasks: detecting labeling errors, curating context to preserve predictive accuracy while lowering inference cost, producing attribution scores that transfer across TFMs, and supporting an acquisition strategy for efficient active learning.
Read the full abstract ▾
All authors Yacine Benihaddadene, Milan Bhan, Eliot Dugelay, Mohammed Jawhar, Benjamin Wong, Nicolas Chesneau, Duong Nguyen
Artificial Intelligence · Cross-listed from cs.CV
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs
Yuan Feng, Qize Yang, Ruizhe Chen et al. (+9 more)
Multimodal large
language models have become the dominant paradigm for visual understanding, but incur substantial costs by encoding inputs into dense, fixed-size patch
tokens. However, visual information is unevenly distributed: some regions require fine-grained detail, while others admit compact representations. Downsampling sacrifices this detail, while existing
token pruning and adaptive approaches remain limited in content-adaptive granularity, task generalization, and integration with modern MLLMs and serving infrastructure. Overcoming these limitations calls for foundation models that learn, end to end, where-and at what granularity-to allocate visual representations, a native capability we term elastic visual representation weaving. We introduce VisionWeave, establishing this capability in frontier-level MLLMs through large-scale training. It combines two components: a gated spatial pooler constructs coarse-grained representations alongside native fine-grained representations within a shared MRoPE coordinate, while a granularity router learns their content-adaptive allocation. Through self-
distillation alone, we validate this capability on Qwen3.5-4B and scale to Qwen3.8-27B with over 30K A100 GPU-hours. Based on Qwen3.8-27B, VisionWeave adaptively adjusts
token savings to visual content, saving 43.0%
tokens on average while retaining 98.9% native performance across eight
benchmarks, versus only 88% performance preserved for
token pruning baselines with a fixed 50% savings target. Extensive evaluations confirm robust efficiency-quality trade-offs across diverse tasks, resolutions and
video frames. When deployed on SGLang serving engine, our method achieves a 2.3x throughput gain while reducing mean TTFT by 54.4% and mean TPOT by 60.6%. Together, we believe these results position elastic visual weaving as a promising capability for next-generation
multimodal models.
Read the full abstract ▾
All authors Yuan Feng, Qize Yang, Ruizhe Chen, Sibo Song, Haolin He, Muzhi Zhu, Zihan Liu, Yunfei Chu, Xize Cheng, Yuxuan Wang, Jin Xu, Xike Xie
Artificial Intelligence · Cross-listed from cs.CV
Decide Before You Look: Learning Which Retrieved Memories Deserve Pixels
Youxing LI
Multimodal assistants answer questions from long-term
memories that contain images. After
retrieval, each retrieved image reaches the answering model either as pixels, at about a thousand visual
tokens per image, or as a stored text proxy that often misses the detail the question asks about. We find that the benefit of pixels usually comes from one or two retrieved
memories, and that it can be predicted before the answering model runs, without reading any full-resolution image. In PixelTriage, a plug-in placed after
retrieval, a small model that does not generate text reads the dialogue, a short note and a thumbnail of each retrieved
memory and predicts how much its pixels would add. It is trained on synthetic
memory episodes labeled by a frozen 27B model that answers each question with and without each
memory's pixels. With a 7B answering model, PixelTriage lies on the accuracy–cost frontier of M$^3$Exam, DMV and MemEye and uses 11–23% of the visual
tokens without a significant loss of accuracy. On DMV it answers 2.9 times faster than opening all images. It outperforms
retrieval order and uniform down-sizing at equal budgets and transfers to other
memory systems and to a 397B answering model.
Read the full abstract ▾
Artificial Intelligence
Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents
Qianhan Feng, Zhongzhen Huang, Yakun Zhu et al. (+2 more)
As
agents continuously improve by generating and revising Skills, the process that discovers and refines those Skills becomes a learnable object in its own right. Task-Skills directly act on task execution, whereas Meta-Skills govern how
agents discover and improve future Skills; their value therefore emerges through the subsequent search processes they induce. Existing approaches improve Meta-Skills from observed raw Skill-search trajectories and branch outcomes. However, branch performance entangles the effects of the initial discovery state and the Meta-Skill revision that generated the search process, making it difficult to characterize what a particular revision actually changed, and pushing updates toward revisions that benefit from favorable states rather than those that improve the process. We introduce HMED (Hindsight Meta-Experience
Distillation), a mechanism for constructing Meta-Experience for self-improving
agents. HMED revisits the completed event from which a revision originates and re-executes the incumbent and revised Meta-Skills from the same restored discovery state, so that the changes associated with the revision can be observed under a shared condition. Each comparison is distilled into a Meta-Experience, a structured record that can be reused by future updates, so that even revisions that are not ultimately retained still contribute a learning signal. Across three interactive
agent benchmarks and both open-source and closed-source models, HMED consistently improves Skill discovery performance over strong baselines, shifting Meta-Skill learning beyond branch outcomes toward the consequences of changing the improvement process.
Read the full abstract ▾
All authors Qianhan Feng, Zhongzhen Huang, Yakun Zhu, Xiaofan Zhang, Qi Dou
Artificial Intelligence
Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces
Yeji Park, Jaeyun Shim and Taesik Gong
Mobile GUI
agents increasingly operate on interfaces influenced by users' histories and preferences, but their reliability across different users remains underexplored. We introduce PAIR (Personalized Application-state Instantiation and Rendering), a pipeline for constructing user-conditioned application states that enables controlled evaluation of the same task across different users. We further introduce RePAIR (Reinforcement learning with Personalization-Aware Interaction Rewards), a training approach that learns from cross-user differences in subgoal outcomes to improve reliability across user-conditioned mobile environments. Across six
agents, we find substantial variation in task success across users and consistently lower subgoal achievement in user-conditioned UI contexts (6.98 to 15.4 pp). This gap further increases for personal targets drawn from each user's own content (8.77 to 22.0 pp). Failures in these contexts frequently involve selecting another item instead of the intended target, particularly before target exposure. Finally, RePAIR improves user-conditioned SAR (+5.87 pp), all-success (+7.50 pp), and overall Task SR (+9.42 pp) over its supervised fine-tuning parent on unseen users, providing initial evidence that explicitly learning from cross-user variation can improve GUI-
agent reliability.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.NE
ReGraph: A Computational Account of Emergent Generalization in the "what" and "where" Dual Visual Streams
Hyewon Kang, Jungmin Lee, Ilgyu Lee et al. (+1 more)
Where generalization capacity–the ability to extract context-invariant relational structures–first emerges remains a central question in AI and neuroscience. The foundation for this capacity lies upstream of the hippocampus, within the entorhinal cortex, where parallel pathways dissociate relational structure in the medial entorhinal cortex (MEC) from sensory content in the lateral entorhinal cortex. However, as Eichenbaum argued, such factorization likely originates earlier, driven by the segregation of the dorsal ('where') and ventral ('what') visual streams. Supporting this, grid-like firing patterns–a signature of MEC (context-invariant codes)–also appear in preceding neocortical regions along the dorsal pathway. Yet, how such representations are computationally formed along upstream pathways remains unknown. To investigate this in silico, we developed ReGraph, a recurrent dual-stream graph model with biological inductive biases, including retina-driven stream-specialized encoding, dorsal-to-ventral modulation, and dynamic lateral connectivity. Trained on the action
benchmark Something-Something V2, ReGraph revealed a pathway-specific emergence of relational mapping: context-invariant codes and grid-like spatial bases uniquely co-emerged along the extended dorsal stream. In contrast, their absence in single-stream, unmodulated variants, and standard baselines implies that these inductive biases are prerequisites for relational structures. Crucially, our post-hoc analyses demonstrated that these grid-like bases serve as reusable routing templates for information processing via lateral connectivity. Together, our findings provide a computational account that generalization may not be a faculty that emerges abruptly within a dedicated region, but a property that already takes shape as sensory information is parsed into factorized streams of hierarchical visual processing.
Read the full abstract ▾
All authors Hyewon Kang, Jungmin Lee, Ilgyu Lee, Seok-Jun Hong
Artificial Intelligence
Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents
Brendan King, Farima Fatahi Bayat, Jean-Flavien Bussotti et al. (+2 more)
When using an LLM
agent in a consequential domain, making an informed decision about whether to trust its output or intervene requires calibrated confidence in the
agent's success. Confidence estimation for
agents is difficult because evidence about success is distributed across heterogeneous, interdependent steps of an
agent's trajectory. Practical agentic deployments introduce further challenges: frontier LLMs often provide limited access to internal signals,
agent roll-outs are costly, and training data may be unavailable or quickly become outdated. To address these challenges, we introduce Confidence
Reasoning Graphs (CRGs), an inference-time framework that estimates the probability an
agent accomplished its task from a single trajectory, without privileged model access or training data. Rather than compressing an execution into a single holistic judgment, a CRG begins with the claim that the
agent accomplished its task, decomposes it into contextualized sub-claims grounded in trajectory evidence, estimates confidence for each terminal claim, and finally aggregates these into an overall confidence estimate. Across three agentic
benchmarks, three backbone models, and three
agent frameworks, CRGs yield better-calibrated confidence and stronger risk-aware decision making than verbalized, sampling-based, and white-box surrogate baselines. We further find that calibration error alone can be misleading: a white-box surrogate baseline appears well calibrated while providing near-chance discrimination. Ablations attribute CRG's improvements to claim-level confidence estimation and aggregation rather than graph construction alone. Finally, a CRG exposes the claims and trajectory evidence underlying each confidence estimate, enabling it to be audited at decision time.
Read the full abstract ▾
All authors Brendan King, Farima Fatahi Bayat, Jean-Flavien Bussotti, Pouya Pezeshkpour, Estevam Hruschka
Artificial Intelligence · Cross-listed from cs.RO
Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution
Ahin Lee, Jinwoo Seo, Youngsoo Jang et al. (+1 more)
Visual disruptions can arise while a
robot is executing a task, leaving a
vision-
language-action (VLA) policy to respond without knowing the disruption type or timing. We introduce Self-supervised Adaptation from Leftover Trajectories (SALT), which uses the leftover trajectory, the unexecuted part of the previous action chunk, as self-supervision for test-time adaptation. Because consecutive chunks overlap in time, the leftover provides a temporally aligned target for the current prediction over the same future control interval. At the onset of a visual shift, the leftover can retain a plan formed before the corruption, so updating the policy toward it anchors the adaptation across the shift (Transition Anchoring). SALT keeps the adapted policy and regenerates the current chunk, whose leftover becomes the target at the next replan, carrying the correction forward along the execution trajectory (Sequential Correction Propagation). Supervision comes entirely from the policy's own predictions, requiring no disruption annotations, expert actions, or target-domain demonstrations, and a lightweight adaptation gate calibrated only on nominal trajectories decides when updates begin. On LIBERO-10, SALT increases average success across five persistent visual corruptions from 43.9% to 53.2% with SmolVLA and from 58.7% to 66.0% with GR00T N1.7, while largely preserving nominal performance. On a real
robot, it raises task progress averaged over digital and physical disruptions from 0.49 to 0.61.
Read the full abstract ▾
All authors Ahin Lee, Jinwoo Seo, Youngsoo Jang, Taesik Gong
Artificial Intelligence · Cross-listed from cs.CL
Yuhan Chen, Siyuan Zhang, Nan Wang et al. (+2 more)
Looped
language models apply the same stack of layers T times to each
token, which deepens the model without adding parameters but multiplies its key-value (KV) cache by T. The larger cache limits how many sequences a GPU can decode at once and slows each decoding step, which reads the whole cache. We propose Hybrid Latent
Attention (HLA), which keeps exact keys and values within a sliding window of W recent
tokens and stores each older
token as a compact latent that the query of each loop reads directly, without reconstructing keys and values. We uptrain HLA on Ouro looped models (T=4) with 1.4B and 2.6B parameters, keeping the pretrained weights frozen and training only the added parameters to reproduce the original
attention. The cache shrinks by 10.7x per
token, fitting 4.0-8.8x as many concurrent sequences per GPU, and decoding throughput improves by 2.5x at 1K-
token contexts and by up to 7.4x at 16K. HLA retains over 97% of the original accuracy on math, knowledge and
reasoning benchmarks, and 96-100% on long-context
retrieval up to 16K
tokens. After supervised fine-tuning, it performs on par with the fine-tuned original model on competition-level math.
Read the full abstract ▾
All authors Yuhan Chen, Siyuan Zhang, Nan Wang, Feiyang Kang, Ruoxi Jia
Artificial Intelligence
SIGMA: Self-Improving Alignment Generalization from a Model Spec
Jingyu Zhang, Shruti Palaskar, Daniel Khashabi et al. (+3 more)
LLM
agents are increasingly capable of executing complex tasks and of recursively improving themselves on easy-to-verify objectives such as software engineering and mathematics. Since
alignment is much harder to verify, this creates a growing risk of capabilities increasing without appropriate safety
alignment, especially as capabilities expand to auto-research and cybersecurity. Existing approaches focus on capability self-improvement using verifiable feedback or on
alignment training with supervision from stronger models or curated data, creating an external supervision bottleneck for
alignment. We ask whether current models can improve their own safety
alignment, and propose SIGMA, a data generation and training pipeline enabling
alignment self-improvement that generalizes to out-of-distribution settings. Given only a "Model Spec" stating the model's desired behavior, SIGMA leverages a model's
reasoning capabilities to strengthen its own safety
reasoning. SIGMA first performs spec-guided task synthesis, using the candidate model as a task designer
agent to generate diverse
alignment dilemma scenarios and convert them into training tasks that stress-test its understanding of the Model Spec. Next, SIGMA conducts self-judged
alignment training through supervised fine-tuning and rubric-based reinforcement learning with the model itself as the reward model. Despite training only on single-turn chat data, SIGMA improves safety
alignment in multi-turn agentic environments (AgentHarm harmfulness decreases from 22.6 to 14.8; Agentic Misalignment decreases from 79.1 to 3.8), outperforms Deliberative
Alignment and Constitutional AI baselines, and retains general capability. Analyses show that a Model Spec balancing harmlessness and helpfulness, test-time
reasoning for safety deliberation, and high-quality rubrics from SIGMA's task designer
agent are crucial for effective self-improvement.
Read the full abstract ▾
All authors Jingyu Zhang, Shruti Palaskar, Daniel Khashabi, Benjamin Van Durme, Leon A. Gatys, Joseph Yitan Cheng
Artificial Intelligence · Cross-listed from cs.CV
Jinghao Xu, Zhenhua Guo, Xiaofeng Zhu et al. (+1 more)
Dynamic
multimodal learning aims to learn robust representations by adaptively modeling information discrepancies across modalities. However, existing methods still suffer from two limitations: (i) static cross-modal
alignment strategies usually impose uniform constraints on all samples while overlooking sample-wise variations, potentially leading to unreasonable over-
alignment; and (ii) confidence- or uncertainty-aware fusion methods often fail to adequately account for feature magnitude and confidence differences across modalities. For modality pairs with significant feature magnitude differences or small confidence gaps, it might be unreliable to strictly align fusion weights according to confidence. To address these issues, we propose an
Alignment- and Calibration-driven
Multimodal Learning framework (ACML). Specifically, ACML incorporates a dynamic cross-modal triplet
alignment module, which enforces strong semantic consistency for high-confidence positive pairs while encouraging diverse representation learning between high- and low-confidence positive pairs according to their confidence gaps. Additionally, ACML introduces a difference-aware
attention calibration strategy that adaptively adjusts
attention regularization based on feature magnitude and confidence differences across modalities, thereby mitigating biases caused by unreasonable fusion constraints. Extensive experiments on multiple
multimodal benchmark datasets demonstrate that ACML consistently achieves superior performance and robustness over recent state-of-the-art methods.
Read the full abstract ▾
All authors Jinghao Xu, Zhenhua Guo, Xiaofeng Zhu, Xiaoshuang Shi
Artificial Intelligence · Cross-listed from cs.CV
Multimodal Knowledge Distillation for Gastric Adenocarcinoma Classification from Whole-Slide Images
Shrihari Dumbre and Bikash Santra
Gastric adenocarcinoma (GA) is a leading cause of cancer-related mortality worldwide, and accurate histopathological subtype classification from whole-slide images (WSIs) is essential for effective treatment planning. While
multimodal approaches that integrate pathology report text with WSIs can improve classification, existing methods often depend on computationally expensive
transformer architectures and large
language models. We propose a
multimodal knowledge
distillation (MKD) framework that combines a pretrained WSI image encoder and a clinical text encoder using Low-Rank
Multimodal Fusion (LMF) to efficiently model cross-modal interactions during training. Each WSI is represented as a bag of patches paired with a slide-level diagnostic caption. The teacher model learns fused image-text representations for subtype classification, while the student model distills this knowledge to enable accurate image-only inference. We evaluate our method on the PatchGastric
benchmark dataset and achieve at least 3.35% higher mean accuracy than state-of-the-art approaches, without relying on
transformer-based fusion, multi-task learning, or large
language models. The source code is available at https://github.com/helomelo1/MKD-LMF.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Diverse Motion Customization via Control-based Dynamic Optimization
Youngyoon Choi, Kihyun Kim, Jeongwoo Shin et al. (+1 more)
Despite recent advances in
video generation, motion customization remains challenging due to content leakage, where appearance attributes from the reference
video unintentionally propagate into the generated output. We identify this issue as a consequence of the generative process collapsing toward the reference
video, which arises from formulating the learning objective as a direct regression on the reference. To address this, we propose Control-based Motion Customization (CMC), a principled training framework that is structurally robust to content leakage. Our key idea is to steer generative dynamics toward desired motion while avoiding collapse toward the reference
video, which we formalize using
Stochastic Optimal Control (SOC). Under this formulation, customized
videos acquire the target motion yet remain within the pre-trained model's
prompt-conditional distribution, where appearance is determined by the text
prompt rather than the reference
video. Furthermore, to improve efficiency, we tailor the SOC formulation to motion customization by eliminating the need for an explicit reward and introducing a timestep-adaptive motion cost that focuses only on early generative stages, accelerating training by 2.5 times. Extensive experiments demonstrate that CMC effectively mitigates content leakage and achieves competitive motion fidelity while preserving the diversity of the base model across diverse scenarios.
Read the full abstract ▾
All authors Youngyoon Choi, Kihyun Kim, Jeongwoo Shin, Joonseok Lee
Artificial Intelligence
Continuous Memory Machines
Ciaran Regan, Kai Arulkumaran, Luke Darlow et al. (+3 more)
Recurrent neural networks typically compress information into a single vector-valued recurrent state, forcing short-term computation and long-term retention to share the same representation. Past extensions alleviate this bottleneck by increasing the
memory capacity or separating timescales, but lack the combination of rapid
neuron-level processing and longer-term retention found in biology. To that end, we introduce the Continuous
Memory Machine (CMM), a recurrent architecture with
matrix-valued short- and long-term
memory states serving distinct functional roles. Building on the Continuous Thought Machine (CTM), the CMM's short-term
memory tracks recent neural activity, with uniquely parameterized
neuron-level models learning to use these activity patterns for computation. A persistent long-term
memory stores information for later use, with a
Transformer jointly updating both
memory stores, providing an expressive bidirectional read–write mechanism such that each store can reorganize its own contents and both read from and write to the other. Across algorithmic, in-context learning, and recurrent
reasoning tasks, the CMM outperforms a broad suite of baselines, exhibiting stronger generalization than prior
memory-augmented networks while preserving the CTM's interpretable
attention patterns. Code is available at https://github.com/SakanaAI/continuous-
memory-machines.
Read the full abstract ▾
All authors Ciaran Regan, Kai Arulkumaran, Luke Darlow, Stefania Druga, Sebastian Risi, Llion Jones
Artificial Intelligence
Isotropic Yet Undecodable: The Sequential Content-Sufficiency Gap in Latent-Predictive Text Representations
K. P. Santoso, N. Z. Fadil, F. P. Harsanti et al. (+2 more)
We study sequential content sufficiency by investigating whether a representation retains the ordered target information available in its input. An information-theoretic decomposition separates input ambiguity, representation loss, and readout mismatch. We construct recoverable views where perfect agreement and joint isotropic Gaussianity coexist with zero target information, and establish limits imposed by deterministic canonical anchors.
Token log-loss provides a one-sided information-loss bound; a fixed-penalty ridge analysis shows why rank alone cannot determine prediction risk. These results motivate CANOPE, a nonautoregressive framework with ordered latent canvases, canonical-
token supervision, and
geometric regularization. On 40,000 validation sequences, latent-agreement (PL0) and
token-grounded (PL2) have nearly identical pooled ranks but reach 13.5% and 98.8% positional Recall@1, respectively, under strong natural corruption when the correct target length is provided. On 3,930 LJSpeech validation utterances, frozen PL2 with a trained MatchaTTS readout yields 21.54% word error rate (WER) on corrupted text, versus 99.22% for frozen PL0, while end-to-end MatchaTTS reaches 10.93%. These results show that
geometric regularity alone does not guarantee recoverable sequential content or effective downstream access in the text settings studied here.
Read the full abstract ▾
All authors K. P. Santoso, N. Z. Fadil, F. P. Harsanti, R. V. H. Ginardi, G. N. Iyer
Artificial Intelligence · Cross-listed from cs.NI
IEEE 802.11bx - WLAN Intelligent Networking (WIN): Toward an AI-Ready Wi-Fi 9
Francesc Wilhelmi, Katarzyna Kosek-Szott, Szymon Szott et al. (+1 more)
Wi-Fi 9 is expected to go beyond mere communication and provide new services such as sensing or computation. At this juncture, Artificial Intelligence (AI) is taking a leading role in the definition of the 802.11bx amendment, named WLAN Intelligent Networking (WIN). In this tutorial, we survey the recent progress made toward Wi-Fi 9 within IEEE 802.11 standardization, tracing the drivers and technological advances that motivate an AI-ready Wi-Fi 9. We then examine AI's role along three complementary dimensions, i.e., AI as a protocol (AI is applied to Wi-Fi's PHY/MAC operation), AI as a platform (Wi-Fi infrastructure is repurposed to provide AI computation), and AI as traffic (AI flows call for new traffic-handling policies), and discuss candidate features and open challenges along each. As a concrete illustration of the AI as traffic paradigm, we present a case study on AI traffic differentiation, where we explore a potential extension of the current Enhanced Distributed Channel Access (EDCA) to support new AI traffic flows.
Read the full abstract ▾
All authors Francesc Wilhelmi, Katarzyna Kosek-Szott, Szymon Szott, Boris Bellalta
Artificial Intelligence · Cross-listed from cs.LG
Variance-Averse $n$-Step Offline Reinforcement Learning for Sparse Long-Horizon Environments
Guhyeon Kang and Minhae Kwon
Generative actors are transforming offline reinforcement learning (RL) by enabling expressive policy classes that model complex action distributions. However, this expressiveness also exposes a key challenge in heterogeneous
datasets: generative policies can reproduce unreliable action modes whose return distributions exhibit high variance, occasionally yielding high returns by chance but lacking consistency. Consequently, maximizing the expected $Q$-value alone is insufficient for identifying reliable actions. We propose VAN-Flow (Variance-Averse $n$-step Flow), a framework that promotes reliable actions in generative offline RL. VAN-Flow combines (i) a categorical distributional critic, (ii) a variance-averse expectation operator that smoothly reweights atom probabilities to favor actions with both high returns and low dispersion, and (iii) a flow-matching generative actor guided via rejection sampling. Unlike CVaR or mean-variance objectives, the operator redistributes probability mass over the categorical return distribution without hard truncation or auxiliary penalty terms. Across more than 40 tasks from D4RL and OGBench, VAN-Flow consistently outperforms strong baselines, with the largest gains in long-horizon and high-variance regimes where reliable action selection becomes critical.
Read the full abstract ▾
Artificial Intelligence
Textual Environmental Context and Spatial Graphs for LLM-Based Regional SST Forecasting
Xiong Li, Xiaowei Zhou, Yanwei Yu et al. (+2 more)
Sea surface temperature (SST) forecasting depends on local temporal persistence, regional spatial dependence, and environmental conditions that evolve with the forecast date. We study how these heterogeneous conditions can be presented to a large
language model (LLM) for regional multi-step forecasting without serializing the full SST grid as text. We formulate forecasting as conditional numerical generation: historical SST and anomaly sequences, date-aligned environmental records, and static ocean knowledge form a textual context, while regional spatial state is supplied through continuous graph-derived prefixes. A static graph encodes persistent geographic–climatological relations, and a dynamic graph encodes recent SST correlations and localized tropical-cyclone influence. Two graph neural networks produce a target-node representation that is mapped by a spatial-prefix fusion and injected into the LLM input. On SST forecasting in the South China Sea, the complete configuration achieves the best MAE and $\Rtwo$ among the compared methods over ten forecast steps. Alongside the numerical forecast, a rule-based module matches predicted trends and environmental-factor directions with knowledge entries to return source-linked, post-hoc contextual explanations.
Read the full abstract ▾
All authors Xiong Li, Xiaowei Zhou, Yanwei Yu, Qian Cui, Junyu Dong
Artificial Intelligence · Cross-listed from cs.CL
Visual Abstention in Unified Multimodal Models
Chufan Shi, Cheng Yang, Tiannuo Yang et al. (+4 more)
Unified
multimodal models (UMMs) integrate understanding and generation, yet their generative behavior is rarely governed by what they understand about the task. We formalize visual abstention: when a requested visual transformation is impossible under the task's rules, the model should recognize that no valid solution exists, state this, and decline to generate. We introduce Draw-or-Decline (DoD), a
benchmark of 1,050 feasible-infeasible request pairs across 7 task categories that jointly measures editing success and the refusal of infeasible requests. Evaluating 8 UMMs, we find that editing ability and abstention are distinct capabilities: even the strongest editor, at 68.4% editing accuracy, refuses only 0.4% of infeasible requests under ordinary instructions. Their
reasoning shows why: the models rarely notice the conflict, and instead plan the edit as if the request were possible, often describing objects that are not in the image, or quietly change the request into one they can complete. Explicitly prompting these UMMs to report infeasibility increases textual refusals but reduces editing accuracy. We propose VisTA (Visual Transformation and Abstention), a training method that pairs feasible and infeasible examples so that a model judges feasibility before deciding whether to generate. We train VisTA-BAGEL to perform feasible edits and decline infeasible requests. Without any reminder, it refuses 93.0% of infeasible requests, up from 0.4% for the strongest editor, while falsely refusing only 0.8% of feasible ones. Unlike a reminder, this does not cost editing accuracy: VisTA-BAGEL completes 74.3% of feasible edits, more than any of the 8 evaluated UMMs.
Read the full abstract ▾
All authors Chufan Shi, Cheng Yang, Tiannuo Yang, Isadora White, Yiwei Chen, Taylor Berg-Kirkpatrick, Xuezhe Ma
Artificial Intelligence
ShanLiangRen: A Nutrition Agent for Personalized Daily Meal Planning
Miao Xie, Xiao Zhang, Yuan Wang et al. (+2 more)
Dietary nutrition planning plays an important role in chronic disease management and maintaining a healthy body. In applications, it must simultaneously satisfy personalized constraints and reasonable multidimensional nutritional goals. These two aspects often conflict, and user constraints evolve with feedback, resulting in a substantial gap between generic guidelines and executable plans. To bridge this gap, we first propose the personalized fully quantified multiobjective dietary planning problem (MDP). To tackle MDP, we develop a nutrition
agent, ShanLiangRen. The system first transforms dietary specifications, nutrient data, user attributes and natural
language requirements into an individualized constrained planning instance. It then employs an exact
retrieval-augmented generation method to shrink the feasible candidate set from a large scale ingredient and recipe space. Finally, it adopts a refinement guided by Pareto principles, where an LLM iteratively revises candidate plans under deterministic nutrition computation and feedback from constraint verification. The system outputs fully quantified meal plans with explicit ingredients and portion sizes, together with reports on nutrition compliance that show constraint satisfaction and nutrient interval attainment. We have released the system online as a WeChat Program, ShanLiangRen. A demo
video is available at https://www.youtube.com/watch?v=652OtY5VlGA.
Read the full abstract ▾
All authors Miao Xie, Xiao Zhang, Yuan Wang, Ruixin Zhu, Chunli Lv
Artificial Intelligence · Cross-listed from cs.LG
Label-Efficient Deep Learning for ECG Delineation: A Multi-Dataset Benchmark against Widely Used Delineation Tools
Jeonghwa Lim, Minje Park, Yeongyeon Na et al. (+6 more)
Electrocardiogram (ECG) delineation, the identification of waveform boundaries, is a foundational step that translates raw ECG signals into clinically interpretable measurements. Deep learning has advanced this task but remains dependent on costly expert annotations. Label-efficient strategies such as self-supervised pretraining and semi-supervised learning are expected to ease this burden, yet it remains unclear whether they yield reliable delineation and whether the deep models they produce outperform the delineation tools used in practice. We address this in two stages. First, comparing self-supervised objectives with supervised or semi-supervised fine-tuning across one internal and four external
datasets, we find that pretraining helps but the objective matters, and that the value of semi-supervised fine-tuning depends on the pretraining objective. Second, we
benchmark the selected deep learning model against widely used open-source (NeuroKit2, Prominence, ECGdeli) and commercial (CalECG) tools using three complementary metrics. The model ranks best on every metric and
dataset, outperforming the strongest tool by a clear margin on the rhythm-diverse set (mIoU 71.3 vs. 54.8%; averaged point-wise sensitivity 92.6 vs. 76.4%), and degrades the least from sinus to arrhythmia. A rhythm-stratified and point-wise analysis further characterizes the distinctive behavior of each tool, yielding practical guidance for tool selection. These results provide systematic, multi-
dataset evidence that self-supervised pretraining is effective for ECG delineation and enables a label-efficiently trained deep learning model to outperform widely used delineation tools by leveraging abundant unlabeled data. This supports adopting such models in diverse, real-world clinical settings.
Read the full abstract ▾
All authors Jeonghwa Lim, Minje Park, Yeongyeon Na, Yujin Eom, Soyeon Lim, Young Ho Lee, Yu Jeong Kim, Sunghoon Joo, Ki Hong Lee
Artificial Intelligence
Self-Referenced Social Preferences: Cooperation without Observing Others Rewards
Mohamed Ayman Mohamed, Harshil Kotamreddy and Marcos Menon Jose
Social preferences can promote cooperation in multi-
agent reinforcement learning, but existing approaches often require
agents to observe the rewards of their peers. In many real-world interactions, however, an
agent can, as humans do, observe others' behavior and outcomes without access to their private reward signals. We introduce self-referenced social preferences, in which each
agent learns a model of its own reward, applies it to other
agents' observed transitions to assess their outcomes from its own perspective, and feeds these self-referenced assessments into standard social preferences. We study two ways to incorporate these assessments: modifying the learning reward, or using them to weight policy updates. We evaluate the approach on three sequential social dilemmas, Escape Room, Clean Up, and Commons Harvest, which require volunteering, public-good contribution, and resource restraint, respectively. Across all three environments,
agents learn cooperative behavior without observing others' rewards, including in settings where independent learners fail to cooperate, and frequently achieve more equitable divisions of jointly produced returns than
agents with access to true rewards. The effective integration point depends on the social preference: inequity aversion works best in the reward together with a value look-ahead, whereas a purely benevolent preference benefits from policy-update weighting. Under partial observability, the policy-update approach continues to support cooperation. These results show that explicit access to other
agents' reward signals is not necessary for learning cooperative behavior: social preferences can instead be grounded in self-referenced assessments of others' outcomes derived from their observed behavior.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
ReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon Agents
Yupeng Su, Jiayi Tian, Zheng Zhang et al. (+1 more)
Long-horizon LLM
agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with steps until the sessions exceed the context window. Existing methods manage the context through context requirement prediction, relying on additional model calls, heuristic rules, or trained policies. However, these predictive approaches introduce runtime overhead, invalidate prefix caches, and permanently discard content with no guarantee of recovery. To overcome these limitations, we introduce ReFold: a training-free rendering layer that preserves the underlying interaction history while compressing only the model's rendered context. It removes two kinds of inter-turn redundancy without an auxiliary predictor: content an earlier turn already displayed, replaced by a stub, and turns the
agent itself reports finished, folded into a one-line note. Both operators use chunked rendering, rewriting the cached prefix once every few steps rather than at every step. Every removal is strictly reversible, a wrong removal costs one restore from the history rather than permanent content loss. Because it operates at the rendering layer, ReFold is plug-and-play across standard ReAct-style harnesses. Evaluations across five long-horizon
benchmarks and two frontier LLMs demonstrate that ReFold reduces
token consumption by up to 2.5x and halves the KV-cache
memory per session without degrading task success rates. Under capped context budgets, it avoids up to 92% of forced compactions. Under concurrent serving workloads, it reduces request queuing delays by up to 100%, accelerating inference by up to 1.7x, while cutting inference costs by up to 3.4x.
Read the full abstract ▾
All authors Yupeng Su, Jiayi Tian, Zheng Zhang, Souvik Kundu
Artificial Intelligence · Cross-listed from cond-mat.mtrl-sci
A self-learning scientific agent for X-ray diffraction
Bin Cao, Huichi Zhou, Runyu Yang et al. (+7 more)
A central challenge for scientific
agents is to turn analytical experience into reusable expertise grounded in physical evidence. Here we introduce Gan Jiang, a self-learning
agent for powder X-ray diffraction built on a diffraction-analysis ecosystem we developed: XMatcher, XQueryer, XDecomposer and WPEM. Together, these engines span phase identification, multiphase decomposition and physics-constrained whole-pattern modelling. Gan Jiang converts analytical experience into executable skills by diagnosing failures, revising skill instructions and code, and validating revisions before reuse, without retraining the
language model or changing the underlying physical models. Skills selected using development data and frozen before held-out evaluation achieve higher refinement scores than the original expert-designed skills across FullProf, GSAS-II and PyWPEM. The
agent resolves strongly overlapping reflections, quantifies a five-phase ancient Egyptian cosmetic, tracks
lattice evolution in an operating battery and compares atomic configurations in a disordered oxide catalyst. On DeltaXRDbench, it leads the evaluated methods in single- and multiphase identification across simulated and experimental data. Without supplied composition, single-phase top-1 accuracies reach 96.30%, 81.78% and 40.83% on MP500, RRUFF and opXRD, respectively, compared with 58.00%, 58.47% and 26.45% for the strongest comparator. These results demonstrate how an integrated scientific tool ecosystem can support
agents that extract structural knowledge from measurements while accumulating validated analytical expertise that transfers to new samples.
Read the full abstract ▾
All authors Bin Cao, Huichi Zhou, Runyu Yang, Jingsong Li, Shuchen Sun, Yan Song, Hanyu Gao, Zhongwei Yu, Tong-Yi Zhang, Jun Wang
Artificial Intelligence
WorkflowOps: Learning Agent Collaboration Priors for Multi-Agent Workflow Orchestration
Qi Cheng, Shengyu Chen, Wei Cheng et al. (+4 more)
Multi-
agent systems are increasingly deployed for complex knowledge work, yet their orchestration layers remain largely memoryless: each new task is decomposed, assigned, and executed from scratch with no benefit from prior successful executions. We present WorkflowOps, a multi-
agent workflow orchestration framework that learns
agent collaboration priors from historical workflows and expands its
agent pool on demand to cover new capability requirements. Our approach introduces three coupled mechanisms. First, a transition probability
matrix captures pairwise
agent collaboration frequencies from past workflows and applies them as soft guidance during DAG workflow construction through intra-layer ordering optimization, probability-thresholded edge suggestion, and transitive reduction for parallelism maximization. Second, a sufficiency-driven
agent creation loop detects capability gaps via semantic matching scores, generates specialized
agents through an LLM, and simultaneously injects them into the collaboration
matrix, so that newly created
agents are immediately usable with predicted collaboration priors. Third, a layered semantic matching strategy uses pre-trained sentence
embeddings for fast, deterministic capability matching as a first pass, invoking LLM verification only for low-confidence cases, thereby reducing LLM routing calls by over 80% compared to pure-LLM approaches. Experiments on mixed code, math, and question-answering suites show that WorkflowOps improves end-to-end pass rates over recent workflow-construction baselines, with the largest gains on structured, decomposable tasks where past
agent handoff patterns transfer.
Read the full abstract ▾
All authors Qi Cheng, Shengyu Chen, Wei Cheng, Zhengzhang Chen, Xiaowei Jia, Haoyu Wang, Haifeng Chen
Artificial Intelligence
RA-MoWE: Workflow-Affinity Embeddings for Query Clustering and Agentic Workflow Generation
Qi Cheng, Shengyu Chen, Wei Cheng et al. (+4 more)
Agentic workflows enable large
language models (LLMs) to solve complex tasks by coordinating
reasoning, tool use, and verification. However, a workflow optimized for an entire task collection can overlook differences in the
reasoning strategies that individual queries need, while searching for a new workflow for every query repeats costly optimization. To address this tradeoff, we introduce RA-MoWE, a framework that uses workflow-affinity
embeddings to cluster queries and guide the generation of reusable expert workflows. Each
embedding records how well a fixed set of reference workflows solves a query, revealing similarities in which
reasoning strategies are effective. RA-MoWE uses each cluster's queries and average
embedding to initialize and refine a specialized workflow through execution feedback. An
embedding encoder predicts these
embeddings from query text, allowing new queries to select a generated expert without first executing the reference workflows. On a 300-query test set drawn from four
benchmarks spanning mathematics, science, and programming, RA-MoWE improves average task score by 4.04 percentage points over selecting among the reference workflows, while using 27.7% fewer
language-model calls at inference.
Read the full abstract ▾
All authors Qi Cheng, Shengyu Chen, Wei Cheng, Yiqun Xie, Haoyu Wang, Haifeng Chen, Xiaowei Jia
Artificial Intelligence · Cross-listed from cs.CL
Dynamic Positional Attention Modulation for Parameter-Efficient Fine-Tuning of Large Language Models
Dayan Pan, Jingyuan Wang and Xie Yu
Parameter-efficient fine-tuning (PEFT) has become a standard approach for adapting large
language models to downstream tasks. However, most existing PEFT methods rely on uniform and static adaptations, without accounting for the structured heterogeneity of
attention across dimensions, heads, layers, and input
tokens. In practice,
attention representations exhibit non-uniform behavior, and positional encoding mechanisms such as rotary positional
embeddings (RoPE) induce dimension-dependent positional structure, making uniform adaptation suboptimal. In this work, we propose DyPAM (Dynamic Positional
Attention Modulation), a PEFT method that adapts how positional information contributes to
attention by operating directly on the query and key representations. DyPAM combines input-conditioned, dimension-wise modulation with head-wise and layer-wise structural modulation, performing fine-grained adaptation of positional
attention aligned with the RoPE-induced structure without modifying the pretrained backbone. Extensive experiments on mathematical and commonsense
reasoning benchmarks across multiple backbone models demonstrate that DyPAM consistently outperforms existing strong PEFT baselines.
Read the full abstract ▾
Artificial Intelligence
DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent Reasoning
Jie Ren, Jiakang Yuan, Chenyu Huang et al. (+3 more)
LLM-based multi-
agent systems (MAS) have demonstrated strong capabilities in solving complex problems across diverse domains. Recently, the dynamic orchestration of
agent systems has become an important research direction. However, existing methods suffer from limited composition, misaligned dependencies, and inflexible scale, restricting their ability to adapt to
reasoning requirements during execution. To address these limitations, we reframe MAS design as a partially observable Markov decision process, in which both the composition and scale of the MAS are dynamically determined. We propose DHCG, a novel framework that coordinates three modules (Planner, Worker, and Generator) to progressively construct a dynamic hierarchical collaboration graph from scratch based on the query and evolving execution feedback. At each step, guided by feedback, the Planner generates a set of distinct and complementary roles tailored to the current
reasoning needs and selectively routes relevant information to each role. It can also finalize the hierarchical collaboration graph early or progressively expand it when additional
reasoning is required. We further introduce action-aware preference optimization to train the Planner to make more effective decisions when constructing hierarchical collaboration graphs. We systematically evaluate DHCG across code generation, mathematical
reasoning, and domain-specific
reasoning benchmarks. DHCG achieves state-of-the-art average performance among the compared methods, improving over the single-
agent baseline by 13.06 points and outperforming both static and dynamic MAS baselines by 2.77-8.02 points. Additional experiments further demonstrate its generalization across different Planner backbones and unseen Worker models.
Read the full abstract ▾
All authors Jie Ren, Jiakang Yuan, Chenyu Huang, Hezeer Ma, Jiayuan Fan, Tao Chen
Artificial Intelligence · Cross-listed from cs.SE
Harness Engineering for Software Engineering via Modular Executable Dev-Primitives
Haibo Jin, Xinjie Li, Peng Kuang et al. (+1 more)
Large
language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, existing
agents remain brittle on long-horizon workflows, where they must repeatedly reconstruct program state scattered across source files, configurations, tests, dependencies, and runtime behavior, leading to increasingly long interaction histories, context explosion, and semantic drift. Large repositories further complicate the identification of task-relevant components. To address these challenges, we introduce Dev-Primitives (Development Primitives), a modular and executable abstraction that transforms repository components from passive software artifacts into active participants in software engineering. Each Dev-Primitive pairs a repository artifact with a resident LLM, which gives the artifact an
agent-native interface grounded in its own implementation and dependencies, enabling natural-
language reasoning, inter-component communication, and localized self-modification. Building on Dev-Primitives, we propose HERMES, a Harness Engineering framework for software engineeRing via Modular Executable Dev-PrimitiveS, which instantiates these primitives at repository scale through a dependency-aware dynamic activation mechanism and a bug diagnosis mechanism that maps execution evidence back to the components that must be revised. Extensive experiments on four software engineering
benchmarks demonstrate that HERMES outperforms matched baseline harnesses by 12.4% on average. Moreover, when paired with strong activation and diagnosis models, HERMES, even with Qwen3-8B Dev-Primitives, remains within 4.5% of the homogeneous GPT-5.6 Sol configuration across all four
benchmarks, while reducing inference cost by 26.2% on Terminal-Bench 4.0, highlighting the importance of harness design in software engineering
agents.
Read the full abstract ▾
All authors Haibo Jin, Xinjie Li, Peng Kuang, Haohan Wang