Artificial Intelligence
Agentic Instruction Data Selection: Let DataMaster Interpret Your Intent
Fanqi Zhou, Qiaosheng Chen, Zixian Huang et al. (+1 more)
Although existing instruction data selection methods have introduced various metrics, the inherent complexity of real-world
datasets makes it impractical for any single metric to generalize across all scenarios. Developers are thus often forced to manually inspect data and craft heuristic rules for each new application—a tedious and error-prone process. In this paper, we propose a paradigm shift from manual configuration to automated orchestration via the Instruction Data Selection
Agent (DataMaster), which interprets user intent and autonomously composes optimal selection strategies. By allowing users to specify data needs through natural
language descriptions, DataMaster simplifies data curation and removes the burden of manual strategy design. Extensive experiments across the math, medical, and code domains show that DataMaster outperforms static baselines in most settings and surpasses full-pool training in a substantial number of cases. The implementation of DataMaster and the scripts needed to reproduce the reported pipeline are publicly available at https://github.com/nju-websoft/DataMaster.
Read the full abstract ▾
All authors Fanqi Zhou, Qiaosheng Chen, Zixian Huang, Gong Cheng
Artificial Intelligence
DashArena: Benchmarking LLMs on Interactive Analytic Dashboard Generation
Xiaotong Wang and Dazhen Deng
Analytic dashboards combine coordinated views and interactions for data exploration and decision-making. Recent models can generate them from data and natural-
language goals, but evaluating their usefulness remains difficult. Dashboard generation is open-ended, and neither static appearance nor successful execution alone captures analytical support and interaction quality. We introduce DashArena, to our knowledge the first
benchmark for open-ended, task-grounded generation of interactive analytic dashboards. Its key innovation is to require each system to generate both a dashboard and a replayable interaction trajectory. A browser executor replays the trajectory and turns the system's intended analytical workflow into reproducible visual and execution evidence. A VLM judge compares candidates using this evidence, and Bradley–Terry aggregation produces the leaderboard. We further distill the judge into the open-weight DashJudge-8B. Human evaluations show that DashJudge-8B effectively reproduces human judgments and ablations show that interaction evidence improves judge agreement. Experiments with frontier models reveal persistent rendering, analytical, and interaction failures. Together, these results show that realistic dashboard generation remains challenging and that interaction-aware evaluation captures failures missed by static or execution-only checks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Retrieval-Corrected Conformal Prediction for Time Series
Sangjin Jin, Kangmin Kim, Junhyeong Lee et al. (+1 more)
Conformal prediction (CP) provides distribution-free prediction intervals for fixed forecasters, but its standard calibration procedure is often inefficient for time series data, where forecast errors are temporally dependent and change across time and operating conditions. Recent time series CP methods improve local calibration using recent, weighted, or localized residuals. Yet local calibration can remain indirect, since broad residual weighting or additional adaptation procedures may dilute the evidence most relevant to the current prediction. This motivates a simple
retrieval and correction strategy that selects similar past residuals as local evidence and then corrects the coverage error left by
retrieval. In this paper, we propose
Retrieval–Corrected Conformal Prediction (RCCP), a
retrieval-augmented calibration method for time series prediction intervals. RCCP builds an asymmetric interval from retrieved one-sided residuals and calibrates its normalized
retrieval error with a scalar conformal correction. Thus,
retrieval provides local residual evidence, while conformal correction determines the final scale needed for coverage. We provide a coverage-gap bound based on the stability of the normalized
retrieval error distribution. Across standard
benchmarks and backbone forecasters, RCCP attains the target coverage in every setting and achieves the lowest Winkler scores, with fewer severe misses. RCCP also achieves low calibration and inference overhead, showing that
retrieval-corrected calibration is an effective and scalable approach to uncertainty quantification in time series
forecasting. Code is available at https://github.com/jinsaaang/rccp.
Read the full abstract ▾
All authors Sangjin Jin, Kangmin Kim, Junhyeong Lee, Yongjae Lee
Artificial Intelligence
Reinforcement Learning-Based Laser Cutting Machine Parameter Optimization
Khanh Quan Pham, Majid Kundroo, Geunwoo Ban et al. (+2 more)
Achieving high accuracy in
laser-based cutting of optical films requires careful tuning of parameters such as focal length and
laser power beam, adjusted according to the specific properties of each film type. Trial-and-error based traditional methods are used to find the most suitable cutting parameters for various films, but they are slow and inaccurate. To address this issue, this paper presents the Reinforcement Learning for
Laser Cutting (RL$^{2}$C)
algorithm, which uses Q-learning with an epsilon-greedy policy to dynamically optimize cutting parameters, significantly reducing taper size and film wastage. Additionally, RL$^{2}$C incorporates a dynamic environment space adaptability mechanism to allow it to adapt to new states encountered during the learning process over multiple batches of experiments. Experimental results demonstrate that RL$^{2}$C requires fewer steps and less time to find optimal cutting parameters compared to various RL-based optimization methods. Specifically, RL$^{2}$C reduces the number of optimization steps by up to 12.5% and processing time by up to 81.8% compared to existing methods. This study demonstrates the potential of RL in industrial
laser-cutting processes by improving cut quality, reducing time and film wastage, and minimizing manual interventions.
Read the full abstract ▾
All authors Khanh Quan Pham, Majid Kundroo, Geunwoo Ban, Seongho Bae, Taehong Kim
Artificial Intelligence · Cross-listed from cs.NI
ImpactHO: Importance-Aware KV Cache Transfer for Multi-User Edge LLM Handover
Minwoo Kim, Soochang Song, Namyoon Lee et al. (+2 more)
Edge LLMs must preserve inference continuity when a user hands over between edge nodes, requiring key-value (KV) cache transfer to the target node. However, simultaneous handovers saturate the backhaul, preventing full cache delivery within the mobility-imposed transfer window. Rather than allocating bandwidth as if all cache entries were equally valuable, we order each user's KV cache by importance and transmit only its most informative fraction, turning
token-level sparsity into communication savings. We cast the transfer as a multi-user backhaul allocation problem that maximizes average accuracy across users. Each user's partial-cache accuracy serves as its utility: a sigmoid that fits measurements on the RULER
benchmark with $R^2>0.99$ across models and context lengths. Because importance ordering front-loads the high-value entries, the concave region of the accuracy curve spans nearly the entire cache. Our proposed allocator keeps served users within this region, making each per-slot allocation problem convex. The optimum is derived via a closed-form weighted water-filling solution that generalizes information-theoretic water-filling and enables online scheduling. The proposed allocator attains over 93.7% average accuracy in a 500ms transfer window, within 0.5pp of the full-cache ceiling, and reaches 98.2-99.5% of a clairvoyant upper bound.
Read the full abstract ▾
All authors Minwoo Kim, Soochang Song, Namyoon Lee, Bang Chul Jung, Yongjune Kim
Artificial Intelligence · Cross-listed from cs.CV
Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration
Sangwoo Jo, Donggeun Ko, Jayeon Kang et al. (+3 more)
Image restoration is fundamentally constrained by the tradeoff between distortion and perception: minimizing pixel-wise error yields over-smoothed results, whereas optimizing for perceptual realism often introduces structural deviations. Recent approaches attempt to balance this tradeoff via posterior sampling or multi-stage generative pipelines, yet remain computationally expensive and architecturally complex. To overcome these limitations, we propose PCFlow (Perceptually Consistent Flow Matching), a unified framework that directly parameterizes a continuous transport from degraded observations to clean targets, jointly optimizing distortion and perceptual quality. While its latent consistency flow objective drives stable and efficient few-step inference, a Latent Consistency Perceptual Loss (LCPL) imposes semantic constraints directly on the guiding velocity field, steering the dynamics toward visually sharp data
manifolds. Furthermore, recognizing the inherent conflict between structural and perceptual consistencies, we integrate a conflict-free gradient projection strategy to stabilize the multi-objective optimization landscape. Combined with lightweight, convolution-only backbone, PCFlow achieves competitive performance across diverse restoration tasks at a fraction of traditional computational costs.
Read the full abstract ▾
All authors Sangwoo Jo, Donggeun Ko, Jayeon Kang, Youngsang Kwak, Jaehwa Kwak, Sungjoon Choi
Artificial Intelligence
SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models
Chenhao Dang, Siyuan Xiong, Conghui He et al. (+1 more)
Agent skills represent a standardized format for packaging procedural knowledge and domain expertise, serving within
agent harness systems as an essential mechanism to continually constrain a
language model's behavior space for repeatable, high-quality task execution. However, because strong closed-source models entail high inference costs, current popular
agent harnesses, such as Codex and OpenClaw, remain prohibitively expensive when deploying these skills to accomplish real-world tasks. The rapid capability enhancement of open-source models deployable on consumer-grade GPUs presents a compelling opportunity to drastically reduce these costs by leveraging skill-based behavioral constraints. Nevertheless, automatically generating effective skills tailored specifically for such compact models remains a significant practical challenge. To address this, we propose SKILLER, a natural-
language-driven reinforcement learning framework designed to automatically generate executor-specific skills for small models, which employs a strong model as the actor and critic, treats the small-model
agent system as the environment, and propagates all reinforcement learning signals entirely via natural
language. Extensive experimental evaluations across five relevant
benchmarks using Qwen3.5-9B and Qwen3.5-4B demonstrate that SKILLER outperforms three open-source and one closed-source skill generation or
evolution methods, achieving absolute gains ranging from 4.3 to 20.4 percentage points for the 9B model and 1.8 to 13.3 points for the 4B model, while remarkably matching the performance of strong closed-source models on single-skill tasks in SkillsBench. The project is available at https://github.com/DANG-ai/SKILLER.
Read the full abstract ▾
All authors Chenhao Dang, Siyuan Xiong, Conghui He, Weijia Li
Artificial Intelligence
Measuring Semantic Abstractness of SAE Features via Nonlocality
Chuqiao Lin, Shivaji Sondhi and Xiao-Liang Qi
Sparse autoencoders (SAEs) have helped uncover mechanistic explanations for LLM behaviours such as
reasoning, jailbreaking etc., via understanding the corresponding task-relevant and causally effective features. To evaluate such mechanistic explanations, downstream studies must distinguish surface lexical features from genuinely high-level ones. However, neither an autointerp-based semantic description nor causal steering utility fully resolves the abstraction level of a feature. To this end, we introduce Feature Nonlocality (FNL), defined as the
entropy of the normalized per-position influence on an SAE feature's activation. We report that FNL correlates with existing LLM-based proxy metrics of feature semantic abstractness, and successfully distinguishes context-dependent
reasoning features from
token-driven ones, correctly assigning the higher FNL to the contextual feature in $73$–$84\%$ of randomly drawn pairs that consist of one contextual and one
token-level feature. We demonstrate two downstream applications. We audit SAE-based features used for jailbreak mitigation and find surprisingly that most effective features are positional features with low FNL rather than genuinely recognizing harmful intents. We report that steering high-FNL features in DeepSeek-R1-Distill-Llama-8B improves MATH-500 accuracy by $4.6$ points over the unsteered model and outperforms steering low-FNL features, though the gains are model-specific. We conclude that FNL provides an LLM-independent, label-free, correlational witness of the abstraction level of an SAE feature, with applications in evaluating mechanistic explanations as well as selecting features for downstream interventions.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models
Md Jafrin Hossain, Mohammad Arif Hossain and Nirwan Ansari
Large
Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous
agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent
memory. When these
agents operate with real-world privileges—calling APIs, modifying files, and querying databases—a compromised
reasoning step can trigger unauthorized data access, irreversible state changes, or cascading failures, yet the security research community has not kept pace. To quantify the state of the field, we conducted a systematic literature review under PRISMA 2020 guidelines across six databases, screening 743 records and retaining 85 papers (2023–2025) on agentic LLM security. Attack research outpaces defense work by 3.9:1. Perception-layer vulnerabilities (
prompt injection, jailbreaking,
adversarial perturbations) dominate, accounting for 66% of papers, while action-layer vulnerabilities (tool misuse, code injection, sandbox escape) appear in only 4.7%, misaligned with real-world risk. Code execution security accounts for 3.5%, and tool-augmented
agents 12%. We contribute a four-layer taxonomy mapping 13 vulnerability types across perception,
brain, action, and interaction layers, and identify seven open problems centered on containment. Agentic LLM insecurity stems from architectural coupling, where weak isolation allows vulnerabilities to propagate across layers.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Robust Multi-Agent Bandits with Heavy-Tailed Rewards and Information Asymmetry
Daphne Feng, Ricardo Parada, Lily Jiang et al. (+2 more)
The multi-armed bandit problem is a central framework in sequential decision-making, extensively studied under sub-Gaussian reward assumptions. However, real-world applications often involve heavy-tailed reward distributions and decentralized, information-asymmetric interactions. We study multi-
agent multi-armed bandits with heavy-tailed rewards under three information-asymmetry regimes: unobserved actions with common rewards, observed actions with independent rewards, and unobserved actions with independent rewards. We develop robust decentralized
algorithms for each setting and derive regret guarantees that nearly match centralized heavy-tailed rates. Experiments on a Pareto-distributed reward environment validate our theoretical findings and illustrate the trade-offs between synchronization, coordination, and exploration across the three regimes.
Read the full abstract ▾
All authors Daphne Feng, Ricardo Parada, Lily Jiang, Sophia Yi, William Chang
Artificial Intelligence · Cross-listed from cs.LG
Coordinating the Unknown Lipschitz Constant in Multiplayer Bandits
Ricardo Parada, Chenzhang Zhao and William Chang
Motivated by decentralized applications, we study cooperative multi-
agent bandits in continuous (Lipschitz) action spaces when the Lipschitz constant is unknown. We consider three information structures: (A)~unobserved actions with common rewards, (B)~observed actions with independent rewards, and (C)~unobserved actions with independent rewards. In each case we design and analyze an
algorithm that estimates the Lipschitz constant, chooses a discretization of the joint action space, and applies a cooperative bandit method to the induced discrete problem. Players never communicate once learning starts, so the central difficulty is that they must reach the same discretization from their own data. We prove regret guarantees showing that common rewards and observable actions each supply this agreement for free, and that in their absence agreement can still be bought, through a dithered quantization of the estimate, at no cost in the leading order of the regret.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Dynamic Context Adapters: Efficiently Infusing History into Vision-and-Language Models
Yuhang Song, Bor-Jiun Lin, Jiaxu Liu et al. (+3 more)
Historical context integration presents a fundamental challenge for
Vision-
Language Models (VLMs) in sequential decision-making tasks. Current VLMs process visual inputs independently, which creates critical limitations for downstream applications that require temporal understanding. Direct incorporation of historical frames into
Transformer inputs produces quadratic
attention complexity and excessive
memory consumption. Existing approaches suffer from significant drawbacks: computational inflation or substantial information loss through temporal compression. To address these challenges, we introduce Dynamic Context Adapter (DCA), a novel context injection approach for pretrained VLMs. Our method employs fixed-size, dynamically compressed
memory to preserve historical semantics without frame concatenation. DCA bridges static VLMs and recurrent policies and enables
memory capabilities in pretrained models while maintaining computational efficiency. DCA achieves over $25\%$ reduction in
attention FLOPs and $13\%$
memory savings while improving performance on long-horizon tasks.
Read the full abstract ▾
All authors Yuhang Song, Bor-Jiun Lin, Jiaxu Liu, Te-Chuan Chiu, Anh Nguyen, Chun-Yi Lee
Artificial Intelligence · Cross-listed from cs.CV
Rethinking Text-Based Image Retrieval in Specific Domain
Jingyang Tan, Sheng Yang, Yuanpeng Chen et al. (+4 more)
Driven by the rapid advancement of
vision-
language representation learning, Text-based Image
Retrieval (TBIR) has made notable progress. However, existing
benchmarks are predominantly constructed on an exclusive single-match assumption between query and images. While effective in general scenarios, this assumption fails to reflect practical system performance in specific domains (e.g., surveillance), where a single query often corresponds to multiple relevant candidate images. To address this limitation, we design a Domain-Specific Multi-Match Text-based Image
Retrieval (DSMM-TBIR) data engine. Leveraging this engine, we construct Security Multi-Match TBIR (SecMM-TBIR), a
benchmark comprising 50k surveillance images with 200 comprehensive queries. Furthermore, we observe that vanilla contrastive learning in specific domains suffers from severe false negatives, forcing the model to push apart semantically similar pairs and thus degrading
retrieval performance. We propose the Semantic-Aware Fine-Tuning (SAFT) framework to address semantic compression in specific domains, which incorporates Semantic-Aware Soft-Label Supervision (SASS) and Intra-modal Structural
Distillation (ISD) to establish a promising paradigm for domain-specific TBIR tasks. Experiments across diverse CLIP-like models demonstrate that SAFT yields an average mAP@20 gain of 7.8 points on SecMM-TBIR over standard image-text contrastive (ITC) fine-tuning, while also improving general-domain performance. The entire
benchmark will be released to facilitate further research.
Read the full abstract ▾
All authors Jingyang Tan, Sheng Yang, Yuanpeng Chen, Jian Wang, Nianjin Ye, Chen Xing, Lanpeng Jia
Artificial Intelligence · Cross-listed from cs.DS
Improving TensorSketch Using Complex Random Variables
Amit Sharma, Mohammad Azhar Khan, Rameshwar Pratap et al. (+1 more)
TensorSketch by~\cite{pham2013fast,kar2012random} provides efficient sketching
algorithms for high-dimensional
polynomial kernels $\vec{x}^{\otimes p} \in \R^{d^p}$. \cite{kar2012random} uses dense Johnson-Lindenstrauss (JL)-type projections with computational cost $O(pDd)$, where $D$ denotes the sketch dimension, whereas~\cite{pham2013fast} extends the sparse CountSketch~\citep{count_sketch}
algorithm, yielding a faster
algorithm for high-dimensional sparse inputs with running time $O\big(p(\nnz{\vec{x}} + D \log D)\big)$. However, the variance of both
estimators grows exponentially with the
polynomial degree $p$, scaling as $3^{p}/D$. Recent work by~\cite{pmlr-v206-wacker23a} showed that using complex-valued distribution reduces this dependence to $2^{p}/D$ for the approach of~\cite{kar2012random}. However, their method relies on dense JL-type projections with computational cost $O(pDd)$ and does not extend to the
algorithm of~\cite{pham2013fast}. In this work, we introduce a simple variant of TensorSketch~\citep{pham2013fast} that achieves the same variance bound as~\cite{pmlr-v206-wacker23a}, while retaining its advantage of the input-sparsity running time. We validate our results with supporting experiments on synthetic and real-world
datasets.
Read the full abstract ▾
All authors Amit Sharma, Mohammad Azhar Khan, Rameshwar Pratap, Keegan Kang
Artificial Intelligence · Cross-listed from cs.CV
Unlocking the Power of Medical Tabular Data via Semantic-Aware Multimodal Pre-training
Yingsheng Liu, Haiming Li, Jingmin Zhu et al. (+6 more)
While
vision-
language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent in structured clinical tables. However, existing
multimodal pre-training methods underutilize this potential due to semantic-agnostic designs that treat tabular inputs as flat vectors and employ unstable continuous regression objectives. To overcome this, we propose a novel semantic-aware framework explicitly modeling the intrinsic two-dimensional structure of tabular data. First, addressing the inter-feature hierarchy of varying diagnostic importance, we introduce Importance-Aware Adaptive Masking to construct a label-free curriculum prioritizing salient features. Second, addressing the intra-feature continuity-discreteness duality, we propose a Soft-Label Discretized Module that replaces unstable numerical regression with stable distribution matching, thereby mathematically preserving ordinal relationships. Extensive experiments across large-scale dermatology (SLICE-3D, HOP) and ophthalmology (EyePACS)
datasets establish a new state-of-the-art (SOTA), demonstrating exceptional robustness and cross-domain generalizability.
Read the full abstract ▾
All authors Yingsheng Liu, Haiming Li, Jingmin Zhu, Jiajun Sun, Victoria Mar, Monika Janda, H. Peter Soyer, Zongyuan Ge, Zhen Yu
Artificial Intelligence · Cross-listed from cs.CV
SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning
Caoyuan Ma, Wenpu Liu, Weichu Xie et al. (+12 more)
Large
vision-
language models (LVLMs) remain vulnerable to jailbreak attacks that exploit visual inputs to bypass safety
alignment inherited from their
language backbones. We propose SafeCap, a reinforcement-learning framework that aligns LVLMs through learned self-captioning. SafeCap trains a policy model to first generate a safety-relevant image caption and then produce a final answer; the caption is further optimized by whether it enables a frozen LLM to reach a safety-aligned decision. This caption-mediated objective encourages the policy to expose visual cues relevant to safe response generation rather than relying solely on direct refusal supervision. Across five
multimodal safety
benchmarks and six
vision-utility
benchmarks, SafeCap substantially improves aggregate safety performance under its intended DirectCap protocol, with gains of 3.7-19.0 points in safety average across four model settings while maintaining comparable or improved
vision utility. Under controlled comparisons on matched backbones and data, SafeCap outperforms safety SFT, DPO, and SafeGRPO, demonstrating the effectiveness of caption-mediated reinforcement learning for
multimodal safety
alignment.
Read the full abstract ▾
All authors Caoyuan Ma, Wenpu Liu, Weichu Xie, Tian Gu, Shilei Zhao, Lingxi Min, Shuai Dong, Yuqi Xu, Ji Zhao, Ziyue Wang, Wenzheng Chang, Taiqiang Wu, Yongfu Zhu, Wenqi Shao, Yinqiang Zheng
Artificial Intelligence
MAP-Graph: Provenance-Aware Shared Memory for Multi-Agent Workflows
Yiqi Wang, Zihao Yan, Jiaqi Zhang et al. (+5 more)
Shared
memory helps
language-model
agents reuse information across long workflows, yet relevant evidence may not be admissible for a particular
agent or action. Because restrictions propagate through derivations, summaries can conceal private, poisoned, untrusted, or revoked sources, enabling unauthorized reads or unsafe actions. Existing approaches provide semantic
retrieval, scoped access, or lineage tracking, but do not clearly separate hard authorization from graded trust or adapt evidence requirements to action risk. We introduce MAP-Graph, a provenance-aware
memory layer that represents
agents, sources,
memories, claims, and actions in a typed execution graph. It traces ancestry, excludes permission-ineligible records, reranks eligible
memories by semantic similarity and multiplicative path trust, and applies a risk-sensitive gate before action execution while retaining affected lineage for audit. On a controlled
benchmark of 2,700 synthetic tasks per method across three domains, MAP-Graph achieves 94.96% overall task success, 72.70% exact decision accuracy, and 90.22% in the clean setting, where success requires a correct Allow rather than a safe intervention. Ablations isolate the roles of permission filtering, path trust, and action gating, while transfer tests with two additional backbones preserve the exact-decision and access-control advantages. These results support provenance as an operational control signal, rather than only post-hoc audit metadata, within the evaluated setting.
Read the full abstract ▾
All authors Yiqi Wang, Zihao Yan, Jiaqi Zhang, Zhangkai Wu, Mingkai Zheng, Zequn Sun, Yanming Zhu, Taotao Cai
Artificial Intelligence
RadFusion: Towards Threshold-Controllable Radiology Report Generation
Ying Jin, Noel C. F. Codella, John Corring et al. (+3 more)
Automated radiology report generation is advancing rapidly in response to the shortage of radiologists, yet unlike a perception model, existing generation models offer no control over the sensitivity-specificity trade-off of their diagnostic content. Such control is essential because clinical scenarios diverge: emergency triage prioritizes sensitivity to reduce missed findings, whereas confirmatory interpretation emphasizes specificity to limit unnecessary interventions. A single fixed report can neither adapt to these scenarios nor support the ROC-based validation widely expected for regulatory clearance. We introduce RadFusion, a framework that equips report generation with threshold controllability. Our method fuses a multi-label classifier, which provides per-disease confidence scores, with a VQA-based report generator, which describes medical findings in detail; an LLM then rewrites the report so that its stated diagnoses follow the classifier's decisions at the selected threshold while staying grounded in the generator's descriptions. On MIMIC-CXR, the performance of RadFusion conforms to the classifier's ROC curve: sweeping the threshold and mapping the reports back to class labels reproduces the classifier's validated ROC performance. This conformance makes generated reports quantitatively evaluable through ROC analysis, strengthening the case for regulatory clearance, and enables operating-point selection that matches report behavior to clinical context. Moreover, combining the two model types improves diagnostic accuracy over uncontrolled generation: sensitivity increases by 6.9% at matched specificity, and specificity by 20.7% at matched sensitivity. These results show that RadFusion makes report generation clinically adaptable, quantitatively verifiable, and diagnostically more reliable.
Read the full abstract ▾
All authors Ying Jin, Noel C. F. Codella, John Corring, Mu Wei, Dinei Florencio, Eric Horvitz
Artificial Intelligence
MEGA: Self-Evolving Agent Optimization Infrastructure via Wisdom Graph
Jung Hwan Lee, Kyu Ho Lee and Gwang Hoon Yoo
As coding
agents increasingly handle implementation, the central challenge shifts from building individual
agents to building an infrastructure that systematically improves them. Current approaches optimize
agent systems without accumulating transferable knowledge, accumulate knowledge without compositional
reasoning over it, and lack a mechanism for that knowledge to self-evolve through operational evidence. MEGA (Meta Evaluation-Grounded Adaptation) addresses these gaps as a self-evolving infrastructure: each optimization cycle produces durable assets, compositional
reasoning over those assets guides subsequent optimization, and operational evidence refines both the accumulated wisdom and the
reasoning that governs it. Layer 1 distills reusable wisdom from
agent sessions through behavioral-pattern clustering and empirical A/B validation, transforming each process into a durable asset. Layer 2 decomposes these assets into atomic PCR (Primary-Context-Resultant) units within a typed Wisdom Graph and performs deductive, abductive, and inductive
reasoning to expand implicit relations; it then assembles context-specific execution plans through compositional
retrieval that surfaces bridging knowledge unreachable by
embedding similarity alone. Layer 3 performs multi-
agent collaborative optimization over heterogeneous
agent workflows (code nodes, LLM calls, and tool-using
agents), attributing improvement effects to specific strategy changes through controlled evaluation that eliminates data variance. Evidence fed back from Layer 3 drives the self-
evolution of both the curation strategies that govern wisdom composition and the optimization trajectories accumulated across runs. The result is an infrastructure in which optimizing an
agent system and evolving the knowledge that guides optimization are one and the same process.
Read the full abstract ▾
Artificial Intelligence
From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents
Yiqi Wang, Caili Yu, Jiaqi Zhang et al. (+5 more)
Persistent
memory lets
language model
agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed record can alter
reasoning, tool use, answers, and subsequent
memory writes. Existing defenses mainly detect or delete suspicious
memories, or revise the current response. Deleting the source leaves already propagated claims, actions, and derived
memories active, whereas resetting the store or replaying the full trace destroys benign state and repeats unnecessary computation. We therefore formulate post-failure
memory recovery: given a failed execution and diagnosed faulty
memories, regenerate the answer and clean up affected persistent state while retaining unaffected work. Our dependency-guided rollback repair builds a typed
memory-to-action graph from runtime provenance, traces explicit downstream dependencies, preserves candidates with independent trusted support, deactivates unsupported
memory state, and selectively replays only answer-relevant affected computation. We evaluate this approach on a 150-case controlled
benchmark spanning three tool-use domains and four
memory failure types, and on a 50-case trajectory-derived stress test adapted from LongMemEval-V2. On the controlled
benchmark, it achieves 85.3% immediate recovery versus 77.3% for LLM-judge repair, the strongest baseline, while preserving all benign
memories and using 41.8% fewer LLM calls. Selective replay, however, leaves higher recurrence than LLM-judge repair (26.6% vs. 12.1%), exposing a trade-off between targeted repair and broader recomputation. On the adapted subset, it reaches 68.0% recovery versus 54.0% for the next best method, with 5.9% recurrence. Code and data are available at https://github.com/xiaoqi-7/
memory-rollback.
Read the full abstract ▾
All authors Yiqi Wang, Caili Yu, Jiaqi Zhang, Yiqun Duan, Mingkai Zheng, Zhangkai Wu, Kaize Shi, Taotao Cai
Artificial Intelligence · Cross-listed from cs.LG
Exploration-Driven Personalized Federated Reinforcement Learning via Intrinsic Motivation
Md Rafid Islam, Rafsan Jany, Zahid Hasan et al. (+1 more)
Personalized
Federated Reinforcement Learning (PFRL) takes a decentralized approach to storing and accessing information based on past experiences while keeping each client's data private during the learning of each client's policy. Many current methods for PFRL rely heavily on exploiting existing reinforcement learning reward signals to derive an optimal policy for each client, thereby neglecting exploration in non-stationary or sparse-reward environments. In this work, we introduce a new exploration-driven framework, Exploration-Driven Personalized
Federated Reinforcement Learning via Intrinsic Motivation (EDPFRL-IM), that leverages an inherent curiosity-driven exploration at each client to promote local exploration and protect client
privacy. Furthermore, to facilitate policy discovery via exploration in previously unexplored state spaces, clients add an intrinsic random network
distillation (RND) signal to their extrinsic reward. Additionally, the server does not have access to clients' raw experiences or local gradient estimates; instead, the server sends global exploration priors and collects minimal novelty summaries from each client to enable both diverse and coordinated exploration among clients. Experiments in
benchmark environments show that our framework outperforms average PFRL
benchmarks in policy personalization and sample efficiency, primarily in delayed and sparse reward systems. Overall, EDPFRL-IM enables the integration of a flexible exploratory learning structure into
federated reinforcement learning systems while preserving client
privacy.
Read the full abstract ▾
All authors Md Rafid Islam, Rafsan Jany, Zahid Hasan, Ratun Rahman
Artificial Intelligence
GeoForge: Non-Parametric Self-Evolving Agents for Earth-Observation Reasoning
Xin Xiao, Jiang Zhong, Junnan Zhu et al. (+4 more)
Earth observation (EO)
agents construct scientifically valid tool workflows and ground their conclusions in current geospatial evidence. This is challenging because EO workflows are constrained by sensing semantics, product dependencies, spatial and temporal compatibility, and parameter requirements. Existing
agents often search a broad operation space for each query, while recent self-evolving systems do not fully organize heterogeneous EO trajectories into reusable knowledge across different decision levels. To solve this problem, we present GeoForge, a training-free, self-evolving framework that transforms completed trajectories into a structured nonparametric execution state. GeoForge constrains the operation space according to the sensing context, then retrieves a task-conditioned prior from three complementary
memories. Workflow Graph
Memory captures global operation order, Action-Level Experiences provide local corrections, and the Adapted Skill Standard Operating Procedure preserves procedural and data constraints. The retrieved prior guides tool execution, while current observations remain the basis of the final answer. After each task, a safety-gated
distillation process converts grounded trajectories into reusable execution knowledge for future
retrieval. This execution,
distillation, and reuse loop improves planning without updating the backbone LLM. Experiments on multiple geospatial
benchmarks demonstrate that GeoForge consistently improves both task accuracy and tool-use trajectory quality across diverse LLM backbones, while substantially reducing tool-planning and
reasoning errors for most LLMs.
Read the full abstract ▾
All authors Xin Xiao, Jiang Zhong, Junnan Zhu, Yingchao Feng, Peijin Wang, Yidan Zhang, Kaiwen Wei
Artificial Intelligence
INSIDE the Student's Mind: Jointly Modeling Latent Reasoning and Action in LLM Student Simulators
Rose Niousha, Minwoo Kang and Narges Norouzi
Large
Language Model (LLM)-based simulators often reproduce observable actions but fail to capture the underlying
reasoning behind them. In education, where student simulation is increasingly used for various applications such as evaluating tutoring systems, this gap is especially pronounced. Two students may submit identical submissions for entirely different reasons. We present INTERNAL STUDENT DIALOGUE (INSIDE), a student modeling framework that fine-tunes LLMs not only to act like students but also to think like them. INSIDE generates internal dialogue grounded in Bloom's Taxonomy across cognitive, affective, and action dimensions, and fine-tunes models on paired think traces and actions. We baseline against different prompting frameworks and evaluate on two axes: fidelity of simulated actions and quality of generated internal dialogue. Our evaluations show that INSIDE improves simulation fidelity in both action fidelity, matching code generation of real students, and
reasoning alignment, achieving the highest
alignment across models up to 57.9%.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Lost in Reconstruction: Aligning Action Representations with Language in Vision-Language-Action Models
Li Wenjie, Yash Jangir, Ignacy Stepka et al. (+3 more)
Action verbs describe not only the physical outcomes of actions, but also how those actions are performed. Yet action representations in
vision-
language-action models (VLAs) are typically optimized for reconstruction under L1/L2 losses in raw action space, where numerical proximity need not reflect linguistically meaningful distinctions. On BridgeV2, we show that action trajectories contain verb-grounding information beyond visual state changes, and that reconstruction-only discrete tokenization systematically erodes this information. To address this problem, we introduce SALT, a Semantically ALigned action Tokenizer that augments a VQ-VAE-style tokenizer with an auxiliary objective requiring a frozen
vision-
language model to recover the episode instruction from quantized action latents. Policies trained with SALT achieve 71.9% average success in SimplerEnv, compared with 42.7% for a reconstruction-only VQ-VAE tokenizer and 31.2% for FAST. SALT also develops verb-specialized codes while maintaining reconstruction fidelity. These results show that
robot action trajectories provide a source of
language grounding and that preserving this structure in action representations can substantially improve
language-conditioned control.
Read the full abstract ▾
All authors Li Wenjie, Yash Jangir, Ignacy Stepka, Yash Agarwal, Marion Kipsang, Yonatan Bisk
Artificial Intelligence
Predicting Space Groups of Double Perovskites by LLM with Dynamic Few-Shot Learning
Jongwon Park, Inhyo Lee, Junhyeong Lee et al. (+1 more)
Double perovskites (DPs) offer broad compositional tunability, but predicting the space groups (SGs) of stable structures remains difficult because available
datasets are often strongly imbalanced toward dominant SG classes. We refer to dominant SG classes as major SGs and underrepresented classes as minor SGs. We introduce Dynamic and Diversity-enhanced Few-shot
Retrieval and Rule-Guided Inference for Space-Group Prediction (DyRIS), an LLM-
agent-based framework that predicts ranked SG candidates from a given DP composition. DyRIS uses diversity-enhanced dynamic few-shot prompting to retrieve relevant in-context examples while limiting the dominance of frequently represented SGs. It further incorporates rule-guided inference based on B/B' cation ordering, quantitative indicators, and major-SG bias control to refine and rank the final Top-3 SG candidates. We evaluate DyRIS on 3,528 thermodynamically filtered DP entries and compare it with composition-based and descriptor-based baselines. At a training-data ratio of 0.5, DyRIS achieves competitive overall accuracy while obtaining the best Overall Top-1 macro-F1 score and the best performance across all Minor-SG metrics. DyRIS improves Minor-SG Top-1 accuracy by 3.26 percentage points relative to CrabNet and achieves higher Minor-SG Top-3 accuracy than the strongest PyCaret-based baseline. Ablation studies show that diversity-enhanced
retrieval, quantitative indicators, major-SG bias control, and B/B' ordering information each contribute to prediction performance. Additional experiments show that the final rule-guided inference step is not easily replaced by conventional classifier- or ranker-based models. These findings demonstrate the potential of combining
retrieval-based LLM
reasoning with crystallographic domain knowledge for SG prediction in imbalanced materials
datasets.
Read the full abstract ▾
All authors Jongwon Park, Inhyo Lee, Junhyeong Lee, Seunghwa Ryu
Artificial Intelligence
Multi-Granular Rationale-Guided Molecular LLM for Property Prediction
Junwoo Park, Minyoung Shin, Cheol Soon Lee et al. (+1 more)
Large
language models (LLMs) are widely applied across chemical tasks, such as molecular property prediction, which underpins drug discovery. Molecular LLMs represent a molecule through several modalities, notably a 1D SMILES sequence or a 2D molecular graph. Both encode molecular information implicitly, so the contribution of individual substructures remains opaque.
Retrieval and augmentation methods add context, but from external sources. However, the cues chemists reason over are the internal substructures that drive a property up or down. We propose MR-MoL, a multi-granular rationale-guided molecular LLM that supplies this evidence directly. A fine-tuned GNN scores each substructure through masking, and the most influential ones are serialized as a ranked, direction-tagged rationale that the LLM reads alongside the SMILES sequence and molecular graph. The rationale spans three levels of granularity: Murcko scaffolds with their side chains, BRICS fragments, and functional groups. This is, to our knowledge, the first method to expose GNN-derived attributions to an LLM as evidence for property prediction. On eight MoleculeNet tasks, MR-MoL achieves the best overall results among generalist models and narrows the gap to specialist models tuned for each task. Five diagnostics further confirm that the model reads the rationale rather than merely benefiting from its presence. Its direction, rank, and substructure each shape the prediction, and its attributions reproduce known structure-property relationships.
Read the full abstract ▾
All authors Junwoo Park, Minyoung Shin, Cheol Soon Lee, Sujee Lee
Artificial Intelligence
Evaluating Rational Contracting in Natural Language
Bhavyesh Sajja, Max Kleiman-Weiner, Roger Zimmermann et al. (+1 more)
The emergence of
language-based AI
agents promises to transform the scope of machine economic activity. Instead of just proposing bids or following hard-coded protocols, such
agents can be used to negotiate and execute agreements in natural
language. However, most evaluations of these abilities have focused on one-off exchanges or simple economic games, leaving open the rich space of time-extended, contingent, and incomplete contracts expressible in
language; they also focus on raw profit, without measuring the qualities required for trustworthy contracting. We address this by formulating a rational framework for how
agents should negotiate and perform natural
language contracts in uncertain multi-step environments. Using this framework, we develop metrics and baselines for quantifying rational and cooperative play. We instantiate our framework in ContractSim, an evaluation suite where two players negotiate and execute a multi-turn supplier contract under environmental and inter-player uncertainty. We find that LLM-based
agents agree on efficient contracts when environmental uncertainty is low, but under high uncertainty, often fail to negotiate satisfiable, efficient, or mutually beneficial contracts, underperforming even heuristic baselines. When executing contracts, LLM
agents are also frequently uncooperative, violating contracts for extra profit even when they are easy to satisfy. These findings highlight room for improvement in the design of
language agents that can negotiate and execute contracts both rationally and cooperatively.
Read the full abstract ▾
All authors Bhavyesh Sajja, Max Kleiman-Weiner, Roger Zimmermann, Tan Zhi-Xuan
Artificial Intelligence · Cross-listed from cs.LG
Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning
Daoyi Li, Yixian Zhang, Wenbo Ding et al. (+2 more)
Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static
datasets while improving them through online interaction. However, directly reusing an offline-trained critic can hinder online fine-tuning: as the policy and data distribution change rapidly, value estimates inherited from offline training may become misaligned with the online environment, leading to inaccurate policy improvement and inefficient exploration. To address this problem, we introduce Critic-Free Pretraining: an efficient paradigm that completely abandons the approach of offline critic training, allowing a freshly initialized critic to adapt without inheriting biased estimates. CFP is compatible with various mainstream O2O
algorithms and consistently matches or improves upon conventional O2O
algorithms across a diverse set of tasks, with particularly pronounced gains on several challenging tasks.
Read the full abstract ▾
All authors Daoyi Li, Yixian Zhang, Wenbo Ding, Yu Wang, Chao Yu
Artificial Intelligence
RLMOpt: Adaptive Prompt Optimization via Recursive Language Models
Subhash Bangalore Satheesha, Nirvik Pande, Deepthi Duddempudi et al. (+1 more)
Prompt optimizers automate the search for
prompts that improve
language-model performance, but existing methods rely on a predefined optimization procedure: the
algorithm determines which candidates to explore and how the search progresses, while the
language model generates or refines
prompt proposals. We introduce RLMOpt, a
prompt optimizer that makes the search policy itself
language-model-driven through a recursive
language model (RLM). The RLM
agent operates over a tool-based environment, inspecting task information, analyzing failures, generating candidates, allocating evaluation budget, and deciding when to stop. A deterministic harness complements the
agent by enforcing objective scoring, Pareto-based selection, and regression constraints. We evaluate RLMOpt across four
benchmarks spanning structured clinical information extraction (Chia), multi-hop question answering (HotpotQA), verifiable instruction following (IFBench-2025), and multi-turn tool-calling
agents (BFCL). In a matched comparison at a single seed, RLMOpt obtains the best held-out score on all four
benchmarks and leads the four-task mean (0.610 against 0.589 for GEPA). Repeating each
benchmark across seeds yields 11 matched
benchmark-seed comparisons, in which RLMOpt outperforms GEPA in 9 cases. Across all 11 runs, it never produced a
prompt that underperformed its seed, whereas GEPA fell below its starting point twice. It is also more efficient, achieving these results with fewer search rollouts while producing
prompts that are 27-79% the size of those produced by GEPA. Our results further show that optimization gains are determined primarily by the headroom available in the seed
prompt, rather than by the search budget. Efficient optimization therefore depends on reaching the available headroom reliably and with minimal search
Read the full abstract ▾
All authors Subhash Bangalore Satheesha, Nirvik Pande, Deepthi Duddempudi, Bharath Dandala
Artificial Intelligence
Quantum Incremental Learning with Mixed State Prototypes
Yu Wu, Qianli Zhou, Xinyang Deng et al. (+3 more)
Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and
memory constraints. In the Noisy Intermediate-Scale
Quantum (NISQ) era, although
quantum neural networks offer advantages in feature mapping, hardware limitations restrict
circuit width. Furthermore, traditional
quantum classifiers are constrained by the number of orthogonal basis states, limiting their capacity to accommodate a continually growing number of categories. Thus, we introduce a novel
quantum incremental learning framework based on trainable mixed-state prototypes. Its original design incorporates new classes by adding class prototypes rather than increasing the
circuit width of the shared
quantum backbone. The use of mixed-state prototypes is another key contribution, since they have representation capabilities to represent information than a single pure-state prototype. And the decomposable mixed-state calculation provides lower production costs and a convenient
Hilbert-Schmidt (HS) distance metric for classification. Simulation results show that our model achieves high-dimensional feature concentration using a minimal number of
qubits, while demonstrating lower computational complexity and robust representation in incremental learning tasks compared with classical baselines.
Read the full abstract ▾
All authors Yu Wu, Qianli Zhou, Xinyang Deng, Wen Jiang, Kang Hao Cheong, Witold Pedrycz