Artificial Intelligence
CEDAR: Agent-Orchestrated Tree Search for Goal-Directed Optimization of Complex Systems
Yingtao Tian
Complex systems, core objects of study in artificial life, model diverse phenomena through nonlinear, feedback-driven interactions that produce emergent behavior, with applications from population dynamics and biology to economic policy and strategic decision-making. Yet the difficulty of predicting how feedback structure gives rise to emergent behavior, a central open problem in artificial life, makes goal-directed design exceptionally challenging. In established practice, system structures are written in specialized modeling
languages such as DYNAMO or STELLA, compounding the challenge with labor-intensive workflows that limit adoption and hinder timely decision-making. To address these challenges, we introduce CEDAR, an autonomous method that uses Large
Language Model (LLM)
agents to discover complex systems satisfying user-specified behavioral goals. Our key innovation is an LLM-driven Monte Carlo Tree Search (MCTS) deeply coupled with complex systems: at each iteration, an LLM Judge evaluates emergent behavior against specified goals and an LLM Editor proposes improved variants, with the Judge acting as a fitness function and the Editor as a variation operator, akin to a generate-and-evaluate loop in evolutionary computation. We represent complex systems as a restricted, runnable subset of Python with domain-specific primitives, letting LLMs modify system dynamics directly. CEDAR formalizes this as an MCTS variant with an LLM-parameterized transition kernel and value function, enabling goal-directed discovery of complex system behaviors while preserving solution diversity, and its LLM-based interpretability reveals how structural changes drive emergent behavior. CEDAR reduces human effort while enabling capabilities difficult to achieve with existing approaches, facilitating broader adoption of complex systems across domains.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection
Xuechao Zou, Shun Zhang, Kai Li et al. (+6 more)
The malicious use of generative artificial intelligence to create highly realistic deepfake
videos raises serious ethical concerns and poses substantial challenges to AI safety. However, existing deepfake
video benchmarks provide limited coverage of recent synthesis methods and generally lack reliable fine-grained textual annotations. Meanwhile, conventional detectors and
multimodal large
language models (MLLMs), whether operating as a single model or relying on a single analytical perspective, often fail to capture subtle forgery artifacts, limiting their generalization to emerging AI-generated methods. To address these limitations, we introduce FaceVid-Forensics-100K, a large-scale deepfake
video dataset comprising 100,000
videos and spanning 33 synthesis methods across face swapping, face reenactment, and entire-face synthesis, including recent generators such as Seedance 2.0. The
dataset provides fine-grained textual annotations of visual observations and verdict-consistent forensic explanations, automatically synthesized through a multi-model aggregation and conflict-resolution pipeline powered by advanced MLLMs. Building on this
benchmark, we propose a multi-
agent forensic
reasoning framework that employs four specialized domain-expert
agents to independently analyze forgery cues from four perspectives: texture, lighting, motion, and physics. A judge
agent then reconciles their reports to produce a final prediction together with an explanation. Extensive evaluations on out-of-domain test sets show that, despite being composed entirely of small open-source MLLMs, our framework outperforms all methods including closed-source GPT and Gemini models and ranks first across all reported metrics on this
benchmark. The project page is available at https://xavierjiezou.github.io/ARGUS/.
Read the full abstract ▾
All authors Xuechao Zou, Shun Zhang, Kai Li, Yi Zhou, Xinyu Sun, Yuhui Chen, Zhe Wu, Congyan Lang, Junliang Xing
Artificial Intelligence
Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents
Hongxi Yan, Ziyue Huang, Shichao Fan et al. (+1 more)
Training large
language model
agents in long-horizon environments requires assigning credit from sparse terminal outcomes to individual actions. Existing critic-free methods propagate trajectory-level rewards uniformly across steps, while recent approaches construct step-level groups by matching repeated states and compare actions within each group. The former cannot distinguish useful actions in failed trajectories from ineffective actions in successful ones. The latter rely on step credit derived directly from individual trajectory outcomes and fixed-weight fusion with episode-level credit. We propose Gated-BEPO, which derives step-level credit from empirical rollout graphs. For each rollout group, Gated-BEPO constructs an empirical graph and estimates node values through a mean-backup Bellman fixed point that reflects the empirical action distribution of the current policy. We then accumulate these temporal-difference residuals along each sampled trajectory using generalized advantage estimation, yielding step-level Bellman advantages that capture both immediate and downstream effects. To adaptively fuse episode- and step-level credit, a confidence gate incorporates Bellman credit only at states with multiple observed successors and otherwise uses episode-level credit. Experiments on WebShop, ALFWorld, and visual Sokoban show consistent improvements across
language and
vision-
language models, while diagnostic ablations support the effectiveness of Bellman fixed-point value estimation and show that step-level credit should be incorporated selectively rather than uniformly into the final advantage.
Read the full abstract ▾
All authors Hongxi Yan, Ziyue Huang, Shichao Fan, Qingjie Liu
Artificial Intelligence · Cross-listed from cs.LG
Bridging the Gap Between Hyperdimensional Computing and Kernel Methods via the Nyström Method
Quanling Zhao, Anthony Hitchcock Thomas, Ari Brin et al. (+2 more)
Hyperdimensional computing (HDC) is an approach from the cognitive science literature for solving information processing tasks using data represented as high-dimensional random vectors. The technique has a rigorous mathematical backing, and is easy to implement in energy-efficient and highly parallel hardware like FPGAs and "processing-in-
memory" architectures. The effectiveness of HDC in machine learning largely depends on how raw data is mapped to high-dimensional space. In this work, we propose NysHD, a new method for constructing this mapping that is based on the Nyström method from the literature on kernel approximation. Our approach provides a simple recipe to turn any user-defined positive-semidefinite similarity function into an equivalent mapping in HDC. There is a vast literature on the design of such functions for learning problems. Our approach provides a mechanism to import them into the HDC setting, expanding the types of problems that can be tackled using HDC. Empirical evaluation against existing HDC encoding methods shows that NysHD can achieve, on average, 11% and 17% better classification accuracy on graph and string
datasets respectively.
Read the full abstract ▾
All authors Quanling Zhao, Anthony Hitchcock Thomas, Ari Brin, Xiaofan Yu, Tajana Rosing
Artificial Intelligence · Cross-listed from cs.CL
Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry
Yehan Yang, Junyuan Shang, Yang Li et al. (+3 more)
Long-context LLM inference is bottlenecked by quadratic
attention computation and growing KV-cache costs. Existing sparse
attention and KV-compression methods typically decide which
tokens or heads to preserve from runtime
attention scores, observation windows, calibration
prompts, or learned gates, making head diagnosis input-dependent and costly to deploy. We propose Autonomy-of-Heads (AoH), a data-free method that identifies
retrieval and streaming heads from the spectral geometry of query-key projections. AoH defines the kernel
attention operator $M_h = W_K^{h\top}W_Q^h$ and uses its effective-rank as a weight-space measure of head function: concentrated spectra indicate a small number of dominant query-key matching directions and are associated with
retrieval heads, whereas diffuse spectra indicate the absence of a dominant global matching direction and are associated with streaming heads. We further derive an efficient $d_\text{head}$-dimensional computation that avoids constructing the full $d_\text{model}\times d_\text{model}$
matrix. We conducted extensive experiments across models demonstrating that at 50% sparsity, AoH retains 96.5% of Full
Attention performance on average while reducing prefill and decode latency by up to 41.4% and 66.0%, respectively, and KV-cache
memory by 50.0% at 256K
tokens.
Read the full abstract ▾
All authors Yehan Yang, Junyuan Shang, Yang Li, Guanqun Zhao, Shuohuan Wang, Dianhai Yu
Artificial Intelligence · Cross-listed from quant-ph
Investigating Quantum-Embedded Transformers on Classical Datasets for Cross-Modality Classification
Hao-Yuan Chen
We test whether a parameterized
quantum circuit (PQC) improves a hybrid
quantum-classical model's performance on classical
datasets, using an interface-matched classical map as the control while holding all other components fixed. Our architecture,
Quantum-Embedded
Attention (QEA), uses a learnable projector to compress backbone features into an $n_q$-dimensional angle vector, a shallow PQC to map those angles to one- and two-
qubit Pauli expectations, and a classical
attention decoder to produce class logits. We hypothesized the PQC would improve accuracy or seed-to-seed stability over a classical map with matched input/output dimensions. We test this with an interface-matched $2\times2$ factorial on Breast Cancer Wisconsin at $n_q\in\{4,8\}$, independently swapping the PQC for a classical map and the
attention decoder for a linear head, across five paired seeds per
cell. Three of four paired
quantum-minus-classical $95\%$ confidence intervals include zero; the fourth, a $+1.63$ percentage-point contrast for the
attention decoder at $n_q=4$, reverses sign at $n_q=8$ and does not survive correction across the four contrasts. The experiment thus shows no consistent PQC contribution and cannot establish equivalence. A five-
dataset cross-modality grid shows comparable accuracy on AG~News, Breast Cancer Wisconsin, and BirdCLEF but a large deficit on CIFAR-10; these
cells are not interface-matched and are interpreted descriptively. We report all planned canonical runs, distinguish current Pauli-readout results from legacy probability-readout experiments, and analyze bottleneck, simulation, finite-shot, and noise limitations. The results do not establish a
quantum advantage; they demonstrate why controlled component attribution is necessary before crediting a hybrid model's performance to its
quantum layer.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from q-bio.MN
Control-Anchored Residual Flow Matching Conditioned on Gene Geometry for Virtual Cell Perturbation Modeling
Quanquan Li, Yihe Chi, Liuyang Song et al. (+10 more)
A central task in virtual
cell modeling is predicting single-
cell transcriptional responses to unseen genetic perturbations and drug combinations, and biological networks provide valuable priors on gene relationships. Existing graph-based models commonly use the same network to structure gene representations and mediate intergene interactions, thereby implicitly treating stable associations as perturbation-response pathways. Gene Ontology and control-derived coexpression networks encode relatively stable relationships rather than intervention-specific response directions or magnitudes. We therefore propose GeneGeoFlow, which conditions a control-anchored residual flow on gene-wise geometry derived from biological networks to learn intervention-specific transcriptional responses. GeneGeoFlow derives multi-scale spectral coordinates from Gene Ontology and control-derived coexpression networks. A perturbation-conditioned, gene-wise gating module selects relevant structural scales and network sources, yielding intervention-specific gene geometry. The resulting geometry conditions a control-anchored residual flow without explicitly propagating target-derived signals along the graph. Condition-wise optimal transport couples unpaired control and perturbed populations for training, while a Delta-correlation objective aligns the predicted and observed condition-level expression-shift directions. GeneGeoFlow achieves Pearson Delta scores of 0.8979 on the Norman additive
benchmark and 0.9088 on five held-out drug combinations in the fixed ComboSciPlex test split. These results support perturbation-conditioned gene geometry as an effective structural prior for intervention-specific response prediction, without conflating stable gene relationships with response propagation.
Read the full abstract ▾
All authors Quanquan Li, Yihe Chi, Liuyang Song, Hongbo Zhang, Jingyu Li, Xidong Xi, Conghua Wei, Yijie Sun, Yu Chen, Xin Liu, Qi Hu, Jing Ke, Guitao Cao
Artificial Intelligence · Cross-listed from cs.CL
FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding
Quanquan Li, Hongbo Zhang, Yihe Chi et al. (+9 more)
Token-level collaboration allows a large
language model (LLM) to assist a small
language model (SLM) when their predictions diverge. Existing methods either use LLM-generated intervention
tokens or rank candidates with the LLM's next-
token probabilities. Both rely on the LLM's local preference, even though an LLM-selected
token may be difficult for the SLM to build on. We present FutureBridge, which ranks joint LLM-SLM
token candidates according to how well they support the SLM's subsequent
reasoning. During training, an answer-verified LLM trajectory supplies a fixed shared future, and a frozen SLM evaluates every candidate under this common context. The resulting counterfactual scores supervise a lightweight
token reranker that observes only the current state and candidate
token. At inference, FutureBridge uses the LLM only to expand the candidate pool, selects one
token, and returns generation to the SLM without generating or appending a future suffix. Across five mathematical
reasoning benchmarks, FutureBridge improves the Qwen3-1.7B SLM's Math Avg. by 35.1% relative to greedy SLM decoding. These results indicate that
token selection benefits from modeling whether the receiving SLM can use each candidate to continue
reasoning, rather than relying on the LLM's local preference alone.
Read the full abstract ▾
All authors Quanquan Li, Hongbo Zhang, Yihe Chi, Jingyu Li, Xidong Xi, Liuyang Song, Hongzhen Zhang, Yuxiang Huang, Jing Ke, Siyuan Ma, Junyi Lin, Guitao Cao
Artificial Intelligence · Cross-listed from cs.SE
Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution
Jiahao Zhang, Yifan Zhang and Yu Huang
Resolving a real software issue with a large
language model (LLM)
agent is a long repair episode, often tens to hundreds of steps spanning exploration, hypothesis, implementation, and verification. Success depends on both the base model's local
reasoning and the
agent's ability to maintain an evolving plan and remember observations across phases. Existing repository-level
agents typically strengthen planning or
memory in isolation, leaving long trajectories vulnerable to stale evidence, repeated failed edits, and verification inferred from the
agent's own claims instead of execution evidence. We present PMCoder, an issue-resolution
agent that couples a hierarchical phase planner with episodic
memory. The coupling is bidirectional: the current plan phase conditions
memory retrieval, while
memory-derived trajectory statistics inform stuck detection and replanning. When available, issue-reproduction verdicts ground verification progress in execution evidence rather than self-reported completion. On SWE-bench Verified, PMCoder resolves an average of $25$ more cases ($+5.0$pp) than a harness-matched baseline, with gains persisting even where the reproduction gate never fires. Further Verified-500 evaluations show the same positive direction across Claude Haiku 4.5, DeepSeek-V4-Flash, and an OpenHands port, with at least $14$ additional resolved cases ($+2.8$pp). Separately, evaluation on TerminalWorld's official sample suggests that the plan-
memory substrate transfers beyond issue reports. Ablation and trajectory analyses show where the gains come from: coupling planning and
memory outperforms either component alone and reduces repeated failed actions, empty-patch exits, and context-window exhaustion.
Read the full abstract ▾
Artificial Intelligence
Evolving Parallel Algorithm Portfolios via Potential-Aware Instance Generation with LLMs
Shaofeng Zhang, Shengcai Liu, Zhiyuan Wang et al. (+1 more)
The Automatic Construction of Portfolios via Large
Language Models (LLM-ACP) suffers from poor generalization in practical few-shot scenarios when solving complex combinatorial optimization problems. Instance and
algorithm co-
evolution frameworks address this by expanding the training
dataset with generated hard instances on which the current
algorithm portfolio underperforms, thereby enhancing generalization. However, this paradigm faces two critical limitations: evaluating instance hardness relies on high-quality reference solutions, and single-mode generation patterns limit instance diversity. To overcome these limitations, we introduce the Potential-aware Instance and
Algorithm Co-
evolution (PIAC) framework. Our core contribution is twofold. First, we propose potential gain, a novel metric that eliminates the need for reference solutions. This metric estimates generalization gain by perturbing the generated
algorithms and assessing their improvement potential on generated problem instances. Second, PIAC leverages LLMs to synthesize diverse instance mutators, exploring a broader region of the problem-instance space and thereby enhancing the portfolio's generalization capabilities. Given that perturbation spaces vary across different
algorithms, we instantiate our framework on Greedy Constructive, Ant Colony Optimization, and Guided Local Search algorithmic backbones. Comprehensive evaluations on the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) across six distinct data distributions demonstrate that PIAC consistently outperforms state-of-the-art LLM-ACP baselines, notably achieving a 19.76% relative improvement for TSP Greedy Constructive portfolios.
Read the full abstract ▾
All authors Shaofeng Zhang, Shengcai Liu, Zhiyuan Wang, Ke Tang
Artificial Intelligence · Cross-listed from cs.CR
LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes
Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo et al. (+1 more)
Low-rank adaptation (LoRA) enables efficient specialization and distribution of large
language models through compact adapters. However, untrusted adapters introduce a supply-chain threat: a backdoored adapter can cause a model to generate harmful content, malicious code, political propaganda, or covert advertisements when an input contains a hidden trigger. Adapter-agnostic defenses merge the adapter with the base model, which dilutes
backdoor signals and reduces detection performance. Existing adapter-aware methods do not address how to safely use a potentially backdoored adapter. Instead, they either train a defensive adapter to repair a backdoored base model, addressing the inverse problem rather than securing the adapter itself, or rely on a classifier that flags the entire adapter as suspicious and requires separate mitigation. These methods overlook the distinct latent-space signatures produced by trigger-bearing inputs in backdoored adapters. We introduce LoRAScan, the first adapter-aware defense that detects and rejects trigger-bearing inputs at inference time without modifying adapter parameters. Our key observation is that a small subset of LoRA insertion sites, approximately 5%, remains stable across clean inputs but exhibits highly concentrated spikes in LoRA down-projection activations when a trigger is present. LoRAScan identifies these low-variance insertion sites before model deployment and monitors them during inference. Across standard LLM
backdoor benchmarks, LoRAScan rejects 98.49% of malicious inputs with a small error rate on clean inputs, outperforming existing defenses across diverse evaluation settings.
Read the full abstract ▾
All authors Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo, Kaichen Yang
Artificial Intelligence · Cross-listed from cs.IR
Progressive Alignment of Recommender Foundation Model through Multi-Phase Post-Training
Oseong Choi, Hoeinn Kim, Jihoon Lee et al. (+2 more)
Foundation model(FM) for recommendation has shown strong ability to model long-horizon sequential user behavior. In practice, a single pretrained foundation model is often adapted to diverse downstream serving surfaces through Supervised Fine-Tuning(SFT). However, optimizing task-specific objectives such as clicks or likes does not necessarily align the serving policy with the business metrics that determine recommendation quality. We propose a three-phase progressive post-training framework that explicitly separates downstream adaptation from business-metric
alignment. The adaptation stage is decomposed into Linear Probing(LP) and Full Fine-Tuning(FFT): LP first stabilizes randomly initialized downstream heads within a frozen pretrained representation space, and FFT then jointly specializes the full model for the target task. On top of this stabilized policy, Reinforcement Fine-Tuning(RFT) aligns the model with practical business objectives using a learned reward model. Rather than directly optimizing the serving policy on sparse business targets, we train the policy on dense implicit feedback and use business-metric supervision only for reward modeling. Offline experiments show that the progressive LP-FFT-RFT framework outperforms single-phase alternatives, and that reward-based
alignment yields a stronger serving policy than directly using the reward model itself for ranking. Large-scale online A/B tests further show that the proposed framework improves production recommendation quality over a conventional non-foundation baseline. A reference implementation is available at https://github.com/webtoon/rec-fm-progressive-
alignment
Read the full abstract ▾
All authors Oseong Choi, Hoeinn Kim, Jihoon Lee, Byungsoo Kang, Taeyeong Jang
Artificial Intelligence · Cross-listed from cs.AR
HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation
Yuebo Luo, Ahmad Sedigh Baroughi, Philip Stachura et al. (+4 more)
Application-specific FPGA accelerators offer substantial performance and energy-efficiency gains across many application domains, but developing them is costly, often requiring months of specialized effort. Even with high-level synthesis (HLS), designers still need extensive hardware expertise to build high-performance accelerators. Although large
language models (LLMs) have demonstrated strong software-generation capabilities, even frontier models lack the hardware intuition and procedural knowledge needed to reliably translate baseline C/C++ programs into high-performance HLS designs: they struggle to identify effective architectures, follow the optimization processes used by HLS experts, and apply hardware transformations consistently across diverse kernels. We present HLSmith, an expert-guided framework for translating C/C++ programs into optimized HLS accelerators. HLSmith combines three components: an HLS optimization expertise library that encodes guarded transformation recipes, their applicability and prerequisite conditions, and unsafe cases to avoid; a staged, feedback-driven orchestration flow modeled on expert HLS development practice that guides
agents through synthesis, bottleneck analysis, and optimization; and a tool-grounded model-adaptation pipeline that converts optimization trajectories from commercial frontier models into training data for fine-tuning open-weight LLMs. We evaluate HLSmith on PolyBench against ChatHLS, a leading prior
agent-orchestration framework for HLS accelerator development. HLSmith achieves a
geometric mean speedup of 4.24x over ChatHLS while producing functionally correct designs, in both software and RTL simulation, for every
benchmark, compared with ChatHLS's 57% valid-design rate. It further reaches speedups of up to 252x and 138x with commercial frontier models and open-weight models, respectively.
Read the full abstract ▾
All authors Yuebo Luo, Ahmad Sedigh Baroughi, Philip Stachura, Le Chen, Venkatram Vishwanath, Zhenman Fang, Caiwen Ding
Artificial Intelligence · Cross-listed from q-bio.QM
Genotypic Triggers: Exposing Pharmacogenomic Blind Spots via Host-Specific Backdoors in Generative Antimicrobial Peptide Models
Doniyorkhon Obidov, Xiaolong Guo, Yonghui Li et al. (+1 more)
Large
Language Models (LLMs) have accelerated drug discovery, particularly in the automated design of antimicrobial peptides (AMPs). However, current validation pipelines for peptide generation models overlook historical precedents showing that certain drugs carry health risks predominantly for individuals with specific genetic profiles. In this paper, we demonstrate that such targeted health risks can be induced intentionally and at scale by manipulating models that generate peptide candidates. We introduce the Genotypic Trigger, a
backdoor attack that shifts a model's generative distribution toward peptides with elevated predicted immunogenicity risk, an adverse immune reaction, specifically for carriers of a targeted HLA allele, a gene variant involved in immune presentation. Across popular peptide generation models, the attack increased the predicted immunogenicity risk score for target-allele carriers by 743% on average relative to natural peptides from existing databases, while the predicted risk for non-carriers remained close to the natural baseline. Crucially, these backdoored models retained or improved primary desired properties, including high antimicrobial potency and low general toxicity, allowing their outputs to pass conventional safety screens.
Read the full abstract ▾
All authors Doniyorkhon Obidov, Xiaolong Guo, Yonghui Li, Kaichen Yang
Artificial Intelligence
Surg-UniWorld: A Unified Surgical World Model with Multimodal Control Experts
Rulin Zhou, Wanhao Liu, Guoheng Ma et al. (+8 more)
Controllable
surgical world models can provide a generative foundation for
surgical artificial intelligence and simulation by synthesizing realistic instrument–tissue interactions. However, existing methods lack a unified
multimodal control paradigm, while direct fusion of heterogeneous visual conditions often causes anatomical distortion, instrument appearance drift, and temporally inconsistent interactions. In this work, we propose {Surg-UniWorld}, a unified
surgical world model with
multimodal control experts. Surg-UniWorld first constructs a {Hierarchical
Surgical Anchor} from first-frame appearance and hierarchical semantic masks to preserve persistent scene identity, anatomical organization, and interaction boundaries. {Anchor-Relative Modality Experts} then interpret edge, depth, and optical-flow evidence relative to the shared anchor, capturing complementary boundary,
geometric, and motion information. A {
Multimodal Control Expert} further performs contribution-preserving stage-wise composition of the activated modality increments and generates control hints for the Wan2.2
video diffusion backbone. To support
multimodal surgical world modeling, we further construct Cholec80-SurgWAM, a
benchmark for controllable
surgical video generation. Extensive experiments demonstrate that Surg-UniWorld consistently outperforms existing controllable
video generation methods and
surgical world-model baselines in generation quality, temporal consistency, and
multimodal controllability.
Read the full abstract ▾
All authors Rulin Zhou, Wanhao Liu, Guoheng Ma, Liangjin Shao, Qiujie Song, Yidu Wang, Guankun Wang, Tong Chen, Long Bai, Luping Zhou, Hongliang Ren
Artificial Intelligence · Cross-listed from cs.LG
Hidden Gauge Controls Feature Specialization in ReLU Networks
Tongxi Wang
The success of deep learning depends on learning useful representations, yet predicting how training organizes these representations across
neurons remains difficult. In this work, we show that changing the scale of initial weights can determine which
neurons learn a feature without altering any
neuron's initial contribution. We construct ReLU networks with identical initial features and predictions that reach the same final predictions with different roles for their
neurons. In one, all
neurons share the learned feature. In the other, one
neuron acquires it while every other
neuron's contribution vanishes. The only change is the relative scale of each
neuron's input and output weights. Our analysis explains how an initial learning advantage persists through convergence: as one
neuron learns the target, it reduces the error driving the others and limits their subsequent adaptation. We prove this outcome in a nonlinear model under gradient flow and small-step gradient descent, and quantify how scale changes the speed and path of feature learning. Experiments verify the predicted dynamics and show that scale also changes feature assignment when two features compete. These results reveal how initialization can control the organization of a learned representation without changing what the network initially represents.
Read the full abstract ▾
Artificial Intelligence
Where Does Neural Advantage Arise in Continuous-Time Dynamic Graph Prediction?
Minwoo Yu and Young-guk Ha
Aggregate performance on continuous-time dynamic graphs (CTDGs) combines, in a single score, the portion attributable to known temporal regularities and the additional predictive power of neural models. This study separates the two at the query level. We construct a mechanism-constrained predictor that uses pair recurrence, recency and history position, renewal patterns, and short sequential transitions while learning the compatibility within each mechanism. Across four CTDG
datasets, this predictor recovers a substantial portion of the performance of strong neural baselines, and the recovered performance quickly saturates with a small,
dataset-specific set of explicit mechanisms. Neural residuals concentrate on queries for which the positive and negative candidates have similar mechanism-execution profiles. Allowing conditional interactions among mechanisms is more effective than simply reweighting their existing contributions. Conditioning the contribution of one mechanism on the execution state of another recovers 54.9-73.2% of the original neural-only queries and improves overall paired accuracy on all four
datasets. Although the magnitude of the effect varies across
datasets, these results show that the performance gap of neural CTDG models need not be treated solely as an opaque difference in representational capacity. At least part of the gap is localized to queries with similar candidate execution profiles and can be functionally explained by conditional coordination among known, low-dimensional mechanisms.
Read the full abstract ▾
Artificial Intelligence
Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence
Ying Chen, Weizhen Li, Zhe Hu et al. (+7 more)
Vision-
language models are increasingly serving as the
reasoning core of
embodied agents.
Robot execution is inherently iterative: each action reshapes the scene and physical state, continually renewing what must be perceived, reasoned about, and verified. Meeting these demands requires complementary capabilities that differ in supervision signals, prediction formats, and verification criteria. Existing approaches typically develop these capabilities against isolated, task-specific objectives, leaving open how they should be organized and integrated around execution as a whole. We present Capek 0.5, an
embodied vision-
language model built around an execution-centric capability taxonomy. Rather than organizing training by
datasets or tasks, the taxonomy groups
embodied capabilities according to their functional roles throughout execution and comprises four capability families: Spatial
Reasoning, Temporal Understanding, Action Guidance, and State Verification. Each capability is first acquired by a dedicated specialist through reinforcement learning with verifiable rewards from a shared backbone, and the specialists are then consolidated into a single inference-time model through weight-space merging followed by routed policy-space
distillation. We instantiate Capek 0.5 at the 2B and 35B-A3B scales and evaluate it from three complementary perspectives: comprehensive
benchmark suites including Capek-StateBench, a new
benchmark for state verification; a controlled study of capability retention from specialists to the unified model; and closed-loop evaluation in simulated
embodied environments. Capek 0.5 improves the large majority of matched
benchmark rows over its initialization, retains all four specialized capabilities in one checkpoint with quantified losses, and transfers to closed-loop
embodied task execution.
Read the full abstract ▾
All authors Ying Chen, Weizhen Li, Zhe Hu, Zhenjiang Li, Rui Jiang, Zhifeng Gu, Lihuang Fang, Jiangping Liu, Lei Yi, Jie Chen
Artificial Intelligence
Mind the Gap: A Dual Knowledge Graph Framework for Unified Multi-task User Intent Inference
Tzu-Cheng Peng, Chien Chin Chen, Chih-Hao Ku et al. (+1 more)
This paper proposes DKG-MTI, a dual knowledge graph framework for unified multi-task user intent inference from online travel reviews. Existing approaches often rely on hierarchical pipelines that suffer from error propagation or
retrieval methods that ignore structural relationships in domain knowledge. To address these limitations, we introduce an inference-only knowledge augmentation framework that dynamically constructs a User-Specific Intent Knowledge Graph from each review and aligns it with a Global Hotel Knowledge Graph through structure-aware semantic smoothing. The aligned knowledge is combined with the original review and processed by a large
language model to simultaneously predict aspect ratings and generate reverse user intent statements. Experiments on TripAdvisor reviews show that DKG-MTI consistently outperforms strong LLM and
retrieval-based baselines in both classification and intent generation tasks, demonstrating the effectiveness of structure-aware knowledge
alignment for scalable and explainable intent inference.
Read the full abstract ▾
All authors Tzu-Cheng Peng, Chien Chin Chen, Chih-Hao Ku, Yung-Chun Chang
Artificial Intelligence · Cross-listed from cs.CV
Beyond Starry Night: Shortcut-Aware Control-State Planning for Artist-Grounded Text to Image Generation
Kuan Xing, Ye Wang, Changyi Gan et al. (+4 more)
Artist-grounded image generation requires more than appending an artist name to a
prompt. Image models often respond to artist names through canonical shortcuts, such as recurring motifs, generic palettes, or overrepresented period signatures, rather than preserving the user's intended scene. We introduce Atelier, a shortcut-aware control-state planning framework for artist-grounded image generation. Atelier translates underspecified artistic intent into an explicit control state that separates scene anchors, preserve/transform decisions, style-regime hypotheses, role-bound artist evidence, and shortcut-avoidance constraints. It grounds this state using artist-level knowledge and local patch references, compiles backend-aware generation plans, and iteratively refines candidates through global and local authenticity feedback. We further introduce ArtIntentBench, a
benchmark covering Van Gogh and Qi Baishi across artwork re-rendering, period/style-controlled generation, historically unseen subjects, shortcut
auditing, and human preference evaluation. Across open-weight and closed-source generators, Atelier improves artist-level style fidelity, preserves source structure more faithfully, and substantially reduces shortcut substitution compared with
prompt-engineered,
retrieval-augmented, and general-purpose
agent baselines. These results suggest that artist-grounded generation is bottlenecked not only by image synthesis, but by the upstream inference of explicit, evidence-grounded artistic controls.
Read the full abstract ▾
All authors Kuan Xing, Ye Wang, Changyi Gan, Yuheng Li, Thao Nguyen, Yi Chang, Yilin Wang
Artificial Intelligence · Cross-listed from cs.CL
Progressive Content Refinement with Decaying Reward Joint LinUCB
Shion Ishikawa, Pablo Loyola, Young-joo Chung et al. (+1 more)
Iterative refinement has significantly enhanced Large
Language Model (LLM) performance; however, existing methods ranging from feedback-based Self-Refine to traditional bandit approaches often rely on static options or overlook the saturation effect. This neglect leads to over-exploitation, where the continuous use of identical
prompts or arms results in diminishing rewards over time. To address this challenge, we propose a novel contextual bandit
algorithm that explicitly incorporates reward decay modeling. Utilizing an Expectation-Maximization (EM)
algorithm, our method simultaneously estimates both arm-specific and decay parameters. Furthermore, by
embedding prompts as arms, we facilitate the joint learning of arm values, distinguishing our approach from the traditional disjoint Linear Upper Confidence Bound (LinUCB) framework. Experimental results on Sentiment Reversal and GSM8K
benchmarks demonstrate that our method achieves significant performance gains over strong baselines. Finally, our ablation study confirms that the integration of reward decay modeling within the bandit framework is crucial for mitigating over-exploitation and optimizing the iterative refinement process.
Read the full abstract ▾
All authors Shion Ishikawa, Pablo Loyola, Young-joo Chung, Yun Ching Liu
Artificial Intelligence · Cross-listed from cs.LG
KReF: Training-Free Retrieval for Long-Term Time-Series Forecasting and Predictive Uncertainty
Yang Zhang and Rui Su
Probabilistic long-term time-series
forecasting commonly relies on trained models. Training-free conformal methods typically construct intervals around a pre-existing point forecaster and do not natively represent a complete predictive distribution; sequential variants additionally suffer from increasingly delayed feedback at long horizons. We propose KReF, a training-free
retrieval framework that treats retrieved historical futures as a querylocal empirical predictive distribution. After robust preprocessing, KReF embeds each lookback using handcrafted statistics or frozen random
Fourier features and retrieves similar historical lookback-future pairs. Their similarity weights directly define predictive masses,
quantiles, CRPS, and a weighted-mean point forecast. KReF further uses the observed query lookback to construct a probability-integral-transform map and applies validation-selected expansion and shrinkage rates to adapt interval boundaries. Across six LTSF
benchmarks and four horizons, KReF obtains the lowest CRPS in all 12
dataset-
embedding settings and the lowest IS90 in 9 settings. Without gradient-based fitting, its point forecasts also match or surpass trained baselines on two of six
datasets. An archive-oracle analysis further reveals substantial headroom under finer horizon- and channel-wise routing. These results establish
retrieval as a useful and underexplored inductive bias for LTSF.
Read the full abstract ▾
Artificial Intelligence
MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents
Bingfan Zeng, Zhisheng Chen, Zhengwei Xie et al. (+8 more)
Long-horizon
agents performing multi-step Web tasks must reuse earlier page observations and interactions to support subsequent actions. However, preserving relevant history does not ensure that it exposes the relations needed for the current decision. We call this gap representation mismatch. To this end, we propose MemPrism, a task-conditioned relational
memory framework that separates persistent experience storage from decision-time working
memory. MemPrism records interactions as the event stream and dynamically constructs relational views according to the current task context. A lightweight view policy selects the relation structure, evidence range, outcome condition, and granularity, while a deterministic composer and renderer transform historical facts into a temporary optical working-
memory view for a frozen task policy. Experiments on long-horizon
embodied and web-
agent benchmarks show that MemPrism consistently improves the task performance, especially as trajectories become longer, while reducing
memory token consumption. Furthermore, the learned view policy transfers across different VLMs without additional adaptation, demonstrating the effectiveness of task-conditioned relational views as a general
memory interface for
agents.
Read the full abstract ▾
All authors Bingfan Zeng, Zhisheng Chen, Zhengwei Xie, Bangde Cao, Yuxuan Li, Jinhan Li, Zheng Lu, Xiangchen Guan, Zikai Xiao, Rui Qian, Jingwei Song
Artificial Intelligence
IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agents
Senhao Wang, Chenghao Cai, Haitao Hu et al. (+4 more)
Reinforcement learning (RL) has achieved strong results in improving large
language models (LLMs) on tasks with stationary, verifiable rewards, such as mathematical
reasoning and code execution. In these settings, the environment follows fixed rules and does not adapt strategically to the
agent. Strategic dialogue differs in this respect: the environment is another
agent that adapts to the policy, and success depends on the interaction between the two sides. Despite this interactive nature, current RL approaches typically train a target
agent against a fixed counterpart or simulator. We find that this training paradigm encourages the policy to exploit counterpart-specific regularities rather than learn strategies that generalize across counterparts. We call this problem the static-counterpart mismatch, which we quantify directly in our experiments. To address it, we propose Isolated Bilateral Reinforcement Learning (IB-RL), in which the two roles coevolve through joint rollouts while each role optimizes its own reward through fully independent advantages, action masks, and update paths. We evaluate frozen policies against fully independent held-out counterparts in both domains. On Vehicle TeleSales, IB-RL achieves 89.6% Success@1, compared to 84.6% for the best unilateral RL baseline. On Deal-or-NoDeal, it reaches 98.4% agreement against DeepSeek V4 Pro, compared to 86.4% for the best unilateral baseline. These results indicate that jointly training both roles with strict peragent isolation produces policies that generalize more effectively to unseen counterparts.
Read the full abstract ▾
All authors Senhao Wang, Chenghao Cai, Haitao Hu, Mingxing Huang, Xingguang Wang, Wenhao Li, Zecheng Lin
Artificial Intelligence
From Cheap Fakes to Pure Synthesis: Addressing the New Era of T2V Fake News Videos
Yifeng Luo, Yupeng Li, Liang Lan et al. (+1 more)
Recent text-to-
video (T2V) generation models enable fake news
videos to be synthesized from scratch, shifting the threat beyond cheap fakes assembled from existing footage. Such news
videos can closely match fabricated narratives, creating a modality
alignment trap for existing detectors. Existing
datasets lack pure synthesis fake news
videos. Although directly prompting T2V models with descriptions of fake news
videos can yield perfectly aligned samples, it reduces the fake news
video detection (FNVD) to unimodal shortcuts and causes semantic-visual degeneration. To counter this, we formulate T2V-FNVD as a novel ternary classification task with three labels (real, cheap fake, and pure synthesis fake) and construct the first pure synthesis fake news
video dataset (PS-FNVD). PS-FNVD includes fabricated events with aligned deception (Type 1) and true events with false visual provenance (Type 2), preventing models from exploiting unimodal shortcuts. Furthermore, we propose the
Reasoning-guided T2V-FNVD (R-T2V) framework. Trained through conditioned rationale generation and supervised fine-tuning, R-T2V integrates high-level semantic logic with low-level physical generative traces to predict the ternary veracity label. Extensive experiments across 10 prevailing baselines show that R-T2V achieves the state-of-the-art performance, outperforming the second-best baseline by 12.20 percentage points in accuracy and 8.46 percentage points in macro $F_1$.
Read the full abstract ▾
All authors Yifeng Luo, Yupeng Li, Liang Lan, Tian Wang
Artificial Intelligence
bioMoR: Biology-Guided Mixture-of-Recursions for Effective Genomic Learning
Koushik Howlader, Tirtho Roy, Md Tauhidul Islam et al. (+1 more)
Transformer models for high-dimensional omics analysis process thousands of genes or pathways, although only a subset requires deep computation. Mixture-of-Recursions (MoR) improves efficiency through adaptive
token-choice or expert-choice routing. We propose bioMoR, which, to the best of our knowledge, is the first framework to apply MoR to gene-level and pathway-level learning. Our contributions include identifying three locations for integrating structured biological knowledge within an MoR backbone: graph-based information sharing refines
token embeddings, a structural bias guides self-
attention toward biologically related
tokens, and a graph-aware router uses neighborhood information to determine each
token's recursion depth. These techniques are centered on our insight that additional knowledge of
token interaction can effectively help models construct
embeddings and select which
tokens should be learned more deeply. Across eight
benchmarks spanning diverse omics data types and evaluated under a unified five-fold cross-validation protocol, bioMoR improves average macro-F1 by 8.2 percentage points and balanced accuracy by 7.1 percentage points over the strongest biology-agnostic MoR baseline while using 75 percent fewer parameters and up to 58 percent fewer FLOPs than a non-recursive
Transformer. The selected marker genes or pathways provide biological interpretability, while their
token-specific recursion depths reveal how computation is allocated.
Read the full abstract ▾
All authors Koushik Howlader, Tirtho Roy, Md Tauhidul Islam, Wei Le
Artificial Intelligence · Cross-listed from cs.LG
Multi-Level Modeling of Large Language Model Inference Latency and Energy via Hybrid Analytical–Machine-Learning Predictors
Saeid Shokoufa, Mohammad Erfan Sadeghi, Mehdi Kamal et al. (+1 more)
The rapid scaling of Large
Language Models (LLMs) has significantly increased computational cost, energy consumption, and inference latency, making accurate estimation essential for sustainable artificial intelligence deployment and hardware-aware design. In this work, we introduce Hybrid Modeling for Energy and Latency of LLMs (HYMELL), a hybrid three-level framework for estimating LLM inference latency and energy by combining analytical modeling with machine learning (ML). HYMELL models LLM execution through a three-level hierarchy: analytical estimation of primitive operations, ML prediction of higher-level components, and an end-to-end model that captures system-level overheads across both prefill and decode phases. The framework supports diverse architectures, including dense and mixture-of-experts (MoE) feed-forward networks (FFNs), as well as multi-head
attention (MHA) and grouped-query
attention (GQA) mechanisms. Evaluated on an NVIDIA H100 graphics processing unit (GPU), HYMELL achieves high predictive accuracy; notably, for LLaMA 3 8B, it attains less than 5% error for both prefill and decode phases. By predicting execution costs directly from architectural parameters, it enables fast, hardware-free design space exploration and energy-efficient optimization.
Read the full abstract ▾
All authors Saeid Shokoufa, Mohammad Erfan Sadeghi, Mehdi Kamal, Massoud Pedram
Artificial Intelligence
The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows
Junbo Li, Boyi Liu, Canwen Xu et al. (+5 more)
Recent systems for optimizing
prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits, or textual-gradient methods. We ask a fundamentally different question: how much of this search policy can be internalized by a single tool-using
agent? We present ReASearch, a unified framework for
reasoning-driven optimization in which the
agent autonomously decides what to evaluate, how to diagnose failures, which edits to make, and when to verify or restart. Rather than serving only as a proposal generator guided by hand-designed heuristics, the
agent actively analyzes outcomes, allocates budget, and refines its strategy over long horizons through persistent
memory. With a shared
agent loop and domain-specific tools, ReASearch instantiates the exact same scaffold to optimize
prompts, programs, and ML workflows. Across 14 diverse tasks, it is competitive with and mostly better than specialized optimization systems, achieving gains of 2% to 40% over strong domain-specific baselines, and in some cases discovering solutions that improve on prior human best-known results. Crucially, we observe that complex search behaviors, which are typically implemented by explicit controllers, emerge naturally from the
agent's
reasoning process.
Read the full abstract ▾
All authors Junbo Li, Boyi Liu, Canwen Xu, Yite Wang, Yuxiong He, Zhangyang Wang, Qiang Liu, Zhewei Yao
Artificial Intelligence
MolBioKG: Grounding Out-of-Graph Molecules in Biomedical Knowledge Graphs via Multi-Resolution Structural Anchoring
Yiming Zhang, Hikaru Shindo, Shuan Chen et al. (+5 more)
Biomedical knowledge graphs (KGs) accelerate drug discovery, but standard pipelines assume query molecules already exist as graph entities, leaving unregistered molecules disconnected. We address this cold-start challenge, termed the out-of-graph molecule problem, by introducing MolBioKG. This two-layer system grounds unseen molecules in biomedical evidence via multi-resolution structural anchoring. It connects an index of 2.74 million molecules (represented by scaffolds, fragments, functional groups, and fingerprints) to a 9.6-million-edge KG. Given only a SMILES string, MolBioKG retrieves structurally related graph entities and traverses their biomedical neighborhoods without task-specific training. It features two inference mechanisms: static multi-anchor
retrieval using Reciprocal Rank Fusion, and Adapt-KG, a tool-using LLM policy for adaptive traversal. Evaluated across in-graph link recovery, complex multi-hop
reasoning, and out-of-graph generalization, MolBioKG outperforms strong baselines. Notably, it raises Hits@10 from 0.585 to 0.876 in multi-hop
reasoning and out-of-graph target recall from 0.145 to 0.269, all while ensuring predictions retain traceable structural anchors and source-attributed KG evidence.
Read the full abstract ▾
All authors Yiming Zhang, Hikaru Shindo, Shuan Chen, Kaushalya Madhawa, Jun Jin Choong, Yuna Oikawa, Takashi Fujiwara, Keisuke Ozawa
Artificial Intelligence · Cross-listed from cs.LG
Dueling World Models: Advantage-Style Action Channels for Common-Mode Distractor Rejection
Jiazhuo Li, Yiming Fei, Zhiruo Zhou et al. (+1 more)
Latent world models plan by predicting future states from an action, but when a scene contains motion the
agent does not control, they quietly go action-blind: predictions for different actions become indistinguishable even as the training loss keeps improving. Existing remedies suppress this distraction with reconstruction, task reward, or auxiliary objectives, each adding machinery or assumptions. We show that a minimal alternative suffices, borrowed from the dueling decomposition of value into a state baseline and an action advantage: in latent dynamics, subtracting a prediction's mean effect over actions cancels whatever the actions share–the action-independent variation where distractors live–leaving a clean, controllable channel, with no reward, no reconstruction, and no distractor-specific auxiliary loss. Because this is only a subtraction at readout time, it applies unchanged to any action-conditioned world model, including frozen pretrained ones. Across a gridworld, synthetic generators with known factors, distracting continuous control, and natural-pixel Atari, the isolated channel recovers the
agent's own effect where entangled predictors fail, with nuisance leak indistinguishable from zero; applied post hoc it surfaces an action channel in off-the-shelf models that their raw readouts miss, and it converts into goal-reaching control in the gridworld. We prove the cancellation is exact in finite samples for both discrete and sampled action sets, and we state its measured boundary–distractors whose motion tracks the action–together with the remaining limitations in the appendix.
Read the full abstract ▾
All authors Jiazhuo Li, Yiming Fei, Zhiruo Zhou, Heikichi Hayashi