cs.AI · 2026-07-08 · No. 47

Artificial Intelligence, 2026-07-08.

44 new papers in cs.AI. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

44 entries
  1. 01

    Rethinking Indic AI from a Lens of Cultural Heritage Preservation

    Aparna Madva, Sharath Srivatsa, Srinath Srinivasa, Tulika Saha

    cs.AI · cs.CL

    As Artificial Intelligence (AI) makes inroads into different parts of the Indian subcontinent, there is significant interest in studying how AI impacts the linguistic and cultural foundations of this civilization. AI is seen as a ''double-edged sword'' where on the one hand, it can enable access and inclusion for a large population, on the other, it can homogenize worldviews and exclude underrepresented languages and worldviews. In this...

    arxiv.org/abs/2607.06544 · PDF

  2. 02

    The Large Cancer Assistant (LCA): A Model-Agnostic Orchestration Framework for Scalable Clinical Decision Support in Oncology

    Ghassen Marrakchi, Basarab Matei

    cs.AI · cs.LG

    - Objective: Multimodal deep learning models in oncology are currently limited by monolithic designs that rigidly couple data ingestion, clinical routing, and artificial intelligence (AI) inference. To address this inflexibility, we propose the Large Cancer Assistant (LCA), a model-agnostic, post-hoc orchestration framework designed for scalable clinical decision support. - Methods: The LCA is mathematically formalized as a 7-tuple...

    arxiv.org/abs/2607.06531 · PDF

  3. 03

    DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression

    Anna Cordoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero, Julia Barrientos, Ainhoa Miranda, Jesus Olivera

    cs.AI

    Long-context language model inference is increasingly limited by the memory bandwidth and capacity required to store key-value caches, yet existing compression methods often apply uniform budgets across layers or tokens and degrade retrieval when lexical cues and semantic states require different preservation. We introduce DepthWeave-KV, a token-adaptive cache compression method that factorizes key and value states across neighboring...

    arxiv.org/abs/2607.06523 · PDF

  4. 04

    Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment

    Han-Jun Ko, Jr-Jen Chen, Haobo Yuan, Hsin-Ying Lee, Tiancheng Shen, Ming-Hsuan Yang, Yu-Chiang Frank Wang

    cs.AI · cs.CV

    Vision-language models (VLMs) struggle to generalize in interactive physical reasoning, particularly under unseen tasks and environments. Two key failure modes are prominent: hallucinated chain-of-thought (CoT) reasoning that contradicts physical reality, and misalignment between the model's reasoning and actions. We present VAORA (Visual Action Outcome Reasoning Alignment), a novel reward design that directly addresses both issues. VAORA...

    arxiv.org/abs/2607.06522 · PDF

  5. 05

    FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference

    Anna Córdoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero, Julia Barrientos, Ainhoa Miranda, Jesús Olivera

    cs.AI

    Long-context LLM inference is increasingly limited by the memory and bandwidth cost of KV caches, yet aggressive compression can remove the layer-specific evidence needed for retrieval and multi-step reasoning. We introduce FreqDepthKV, an inference-time cache compression method that factorizes adjacent-layer KV states into shared low-frequency depth components and sparse high-frequency residuals. A lightweight online probe assigns attention...

    arxiv.org/abs/2607.06519 · PDF

  6. 06

    FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games

    Chase McDonald, Nathan Tsang, Wesley N. Kerr

    cs.AI · cs.GT

    We present FootsiesGym, an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information game. Built on HiFight's minimalist 2D fighting game Footsies, it isolates the cyclic, non-transitive strategic interactions of fighting game neutral play while remaining simple enough for efficient analysis. We provide a vectorized simulator that enables high-throughput training on standard hardware, making the...

    arxiv.org/abs/2607.06514 · PDF

  7. 07

    RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models

    Qian Sun, Yong-Ming Tian, Jia-Wei Huang, Cheng Feng, Shao-Qun Zhang

    cs.AI

    Recent years have witnessed the emergence of multivariate modeling using time series foundation models (TSFMs), which achieve advanced zero-shot generalization. Modern multivariate TSFMs are predominantly pretrained on multivariate synthetic data, which is easier to scale but may fail to capture the complex temporal dynamics and cross-variable relationships present in real-world time series. This raises a key question: Whether and to what...

    arxiv.org/abs/2607.06504 · PDF

  8. 08

    Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade

    Kai Ruan, Zihe Huang, Ziqi Zhou, Qianshan Wei, Xuan Wang, Hao Sun

    cs.AI

    Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable. We show that failure is predictable early from the agent's internal representations: lightweight per-round probes on hidden activations anticipate eventual episode failure as early as the first interaction round, where scorers reading...

    arxiv.org/abs/2607.06503 · PDF

  9. 09

    Multi-Agent Deep Reinforcement Learning for Multi Objective Battery Management in Dairy Farms

    Marcos Eduardo Cruz Victorio, Karl Mason

    cs.AI

    The dairy industry in Ireland has a large potential for the integration of renewable energy and the reduction of carbon emissions. However, researchers of distributed generation control are mainly focused on residential and commercial applications. To contribute to the effective integration of renewable energy in the dairy sector, this paper presents a multi-objective optimisation control system based on differential evolution and multi agent...

    arxiv.org/abs/2607.06489 · PDF

  10. 10

    A Physics-Informed Neural Network Framework for Elastodynamic Wave Propagation in Bimaterial Systems

    Sonal Ankush Chibire, Jenn-Terng Gau, Bo Zhang

    cs.AI · math-ph

    Physics-informed neural networks (PINNs) provide a promising framework for solving partial differential equations while embedding the underlying physical laws directly into the learning process. This study presents a PINN-based framework for modeling transient elastodynamic wave propagation in bimaterial systems governed by the axisymmetric equations of linear elasticity. A steel-aluminum specimen representative of a Split Hopkinson Pressure...

    arxiv.org/abs/2607.06479 · PDF

  11. 11

    Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory

    Jihao Liu, Guoxiong Gao, Zeming Sun, Bin Wu, Shurui Liu, Jiedong Jiang, Haocheng Ju, Leheng Chen, Ronnie Cheng,...

    cs.AI · cs.CL · cs.MA

    Recent LLM-based mathematical reasoning agents have begun to tackle research-level problems and, in several cases, have contributed to the resolution of open problems. However, scaling and orchestrating such agents effectively remains challenging, due to the difficulty of coordinating parallel proof search while keeping intermediate claims organized and reliable. In this paper, we propose Danus, an orchestration system for research-level...

    arxiv.org/abs/2607.06447 · PDF

  12. 12

    Finding H. pylori in the Fine Print: Evidence-Linked Multi-Agent Case Finding from Gastric Biopsy Reports

    Yufan Wang, Anit Kumar Sahu, Yan Fei Ng, Daniel Kang, Shayan Vassef, Soorya Ram Shimgekar, Koustuv Saha, Piyum...

    cs.AI

    Data from Singapore indicated that about 31% of the population had evidence of Helicobacter pylori infection. Persistent H. pylori infection is associated with chronic active gastritis and peptic ulcer disease, and its eradication is key to gastric cancer prevention. However, evidence supporting \textit{H. pylori} positivity and H. pylori-associated gastritis may be distributed across heterogeneous coded and free-text report fields and may...

    arxiv.org/abs/2607.06435 · PDF

  13. 13

    ExplAIner: A Declarative Query Language for Explaining Classification Models

    Marcelo Arenas, Pablo Barceló, Diego Bustamante, Jose Caraball, María Alejandra Schild, Bernardo Subercaseaux

    cs.AI

    The XAI community has studied a wide range of queries and scores for explaining predictions of ML models. From a data management perspective, this proliferation of explanation notions calls for declarative query languages in which such notions can be specified, combined, and analyzed uniformly. In this paper, we develop such a framework for Boolean models. We first revisit FOIL, an interpretability query language for black-box models, and...

    arxiv.org/abs/2607.06407 · PDF

  14. 14

    A Definition and Roadmap for World Models

    Xinyuan Chen, Haoyu Guo, Shi Guo, Bingqi Jiang, Chunhua Shen, Xing Shen, Tianfan Xue, Yufei Xue, Mulin Yu, Weinan...

    cs.AI

    World models -- internal simulators that learn the structure and dynamics of an environment -- have become one of the most actively debated concepts in AI. From model-based reinforcement learning and video generation to embodied robotics and ultimately, physical AI, researchers across AI subfields are building systems that they call "world models", yet there is no consensus on what a world model fundamentally is, what it should predict, or...

    arxiv.org/abs/2607.06401 · PDF

  15. 15

    TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting

    Xiachong Lin, Du Yin, Arian Prabowo, Hao Xue, Wen Hu, Imran Razzak, Matthew Amos, Sam Behrens, Flora D. Salim

    cs.AI

    Building sensors are embedded in physical topology, spatial hierarchy, and operational context, yet existing forecasters often treat them as isolated time series or rely on fixed covariate sets. We present TopoBrick, a training-free framework for zero-shot building IoT (Internet-of-Things) forecasting. TopoBrick uses building knowledge graphs to construct a compact structural skeleton and employs an agentic topology sampler to select...

    arxiv.org/abs/2607.06349 · PDF

  16. 16

    Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Models

    Franz Motzkus, Sebastian Bernhard

    cs.AI · cs.CV · cs.RO

    The increasing adoption of end-to-end learning for autonomous driving introduces increased model complexity and opacity, raising the risk of learning undesired or erroneous behavior. In this work, we integrate unsupervised dictionary learning as a post hoc interpretability module within state-of-the-art driving models to decompose driving behavior into semantically meaningful concepts while demonstrating their causal influence on the model's...

    arxiv.org/abs/2607.06328 · PDF

  17. 17

    DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail

    He Liu, Changtao Miao, Xinjie Yang, Tianle Song, Yin Wu, Junchi Chen, Bintao He, Xinyuan Zhang, Bo Zhang, Shi Yan,...

    cs.AI

    Large language models deployed in open-world applications require safety guardrails that are both robust to complex risks and efficient enough for low-latency runtime moderation. Existing guardrails face a practical trade-off between lightweight classification-based models, which are efficient but often struggle with concealed intent, ambiguous semantics, and borderline safety decisions, and reasoning-based guards, which improve judgment...

    arxiv.org/abs/2607.06326 · PDF

  18. 18

    Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval

    Yanping Chen, Weijie Shi, Wen Yang, Jiajie Xu

    cs.AI

    Skill usage can significantly enhance the ability of modern agent systems to complete complex tasks. However, the growing scale of skill libraries makes accurate skill selection increasingly challenging. In real-world scenarios, ambiguous semantic matching often arises between a specific task requirement and multiple generic yet semantically similar candidate skills. Moreover, existing methods tend to overlook the dynamic influence of task...

    arxiv.org/abs/2607.06283 · PDF

  19. 19

    From Application-Layer Simulation to Native Meta-Architecture: Structural Tension as an Endogenous Driver for Heterogeneous AI Evolution

    Heting Mao

    cs.AI · cs.CL

    Current large language models (LLMs) are fundamentally stateless: their behavior is fully determined by input at inference time, and any higher-order cognitive architecture must be simulated at the application layer through prompt engineering and context management. This paper proposes a theoretical framework for submerging such application-layer cognitive protocols into a native meta-architecture by introducing three interlocking mechanisms:...

    arxiv.org/abs/2607.06269 · PDF

  20. 20

    Demonstrating TOFFEE: A Learned System for Synthesizing Data Agent Trajectories at Scale

    Ziting Wang, Yin Li, Zuhao Yang, Xiuchang Li, Jiale Bai, Gao Cong

    cs.AI

    LLM-powered data agents are playing an increasingly important role in data-driven decision making. However, existing data agents struggle to generalize to unseen data environments and analytical workflows, especially in heterogeneous enterprise settings. This creates a growing need for synthesizing high-quality data agent trajectories that capture complex analytical workflows for given data environments. Such trajectories support two key...

    arxiv.org/abs/2607.06233 · PDF

  21. 21

    Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents

    Yijun Zhang, Fan Xu, Jiaxin Ding, Yule Xie, Shiqing Gao, Xin Ding, Haoxiang Zhang, Luoyi Fu, Xinbing Wang

    cs.AI

    Reinforcement learning has become a promising paradigm for improving large language model (LLM) agents on long-horizon search tasks, where the agent must make a sequence of intermediate decisions before receiving a final outcome. However, existing methods still face a key limitation: the rollout budget is often allocated without explicitly assessing the utility of intermediate states. As a result, substantial computation may be spent on...

    arxiv.org/abs/2607.06223 · PDF

  22. 22

    A toy framework for single and multi-agent human-AI curiosity ecosystems

    Ilya E. Monosov

    cs.AI

    This paper offers a toy framework for considering curiosity as an ecosystem. First, it suggests that a single agent's inquiry policy (how, when, and why an agent asks a question) depends on how the agent values immediate uncertainty reduction, costs, delayed return, and the value of keeping the question open. A key concept in the framework is that the weights on these decision-related terms can change with experience. For example, a period of...

    arxiv.org/abs/2607.06214 · PDF

  23. 23

    When do prophets profit in prediction markets?

    Anri Gu, Nicole Kagan, Alec Sun, Jibang Wu, Haifeng Xu

    cs.AI · cs.CE · cs.GT

    Prediction markets aggregate dispersed beliefs into prices that act as probabilistic forecasts of uncertain events. Classical theory establishes a clean equivalence between forecasting accuracy and trading profit, but only for the specific automated market maker (AMM) design. However, the largest exchanges today are based on central limit order books in which informed forecasters routinely lose money while uninformed strategies can profit on...

    arxiv.org/abs/2607.06166 · PDF

  24. 24

    Reward-Density Heuristic for Dynamic Multi-Vehicle Routing: Performance and Computational Efficiency

    Manish Kolachalam, Rani Malhotra

    cs.AI

    The Vehicle Routing Problem (VRP) and its variants represent some of the most practically consequential optimization challenges in modern logistics and urban mobility. In this study, we address a dynamic, online variant combining elements of the VRP and the Orienteering Problem (OP), in which a fleet of vehicles must maximise cumulative reward collected within a fixed time horizon while continuously replanning as new tasks arrive. We propose...

    arxiv.org/abs/2607.06066 · PDF

  25. 25

    PolyWorkBench: Benchmarking Multilingual Long-Horizon LLM Agents

    Hongliang Li, Yijin Liu, Zhiwei Zhang, Zihe Liu, Xinyue Lou, Jinan Xu, Fandong Meng, Kaiyu Huang

    cs.AI · cs.CL

    Large language model (LLM) agents have shown strong performance in long-horizon tasks that require planning, tool use, and interaction with external environments. However, most existing benchmarks implicitly assume a monolingual setting, where the entire execution process, including reasoning, tool invocation, and output generation, is conducted within a single language. In contrast, real-world applications often involve multilingual inputs...

    arxiv.org/abs/2607.06008 · PDF

  26. 26

    Information Limits and Attractor Dynamics in Economies of Frontier LLM Agents: A Pre-Registered Test

    Cheng Qian

    cs.AI · cs.MA

    We report a pre-registered, two-part experiment on small economies of frontier language-model agents (Claude Opus 4.8), testing two quantitative predictions about coupled multi-agent systems: an information-theoretic capacity region for wealth growth under market coupling, and a mean-field residual-scaling law for population misalignment under incentive and control levers. All predictions, acceptance bands, and decision rules were frozen in a...

    arxiv.org/abs/2607.06001 · PDF

  27. 27

    AgoraSim: A Hybrid Agent-Based Modeling Framework

    Chung-Chi Chen

    cs.AI

    LLM-agent simulations make natural-language social scenarios easy to instantiate, but their outputs can be overread as predictions and are often difficult to compare with explicit social dynamics. We present AgoraSim, a hybrid agent-based modeling framework for scenario-oriented social reaction analysis. AgoraSim resolves textual or multimodal artifacts into editable ABM configurations, runs ratio-controlled populations that mix LLM,...

    arxiv.org/abs/2607.05999 · PDF

  28. 28

    Auto-DSM Under the Lens: A Black-Box Evaluation Framework for LLM-Based DSM Generation

    Niels Potters, Theo Hofman

    cs.AI · cs.AR · cs.CE · eess.SY

    This paper presents a black-box evaluation framework to systematically assess the ability of Large Language Models (LLMs) to generate Design Structure Matrices (DSMs) from structured technical documentation. Motivated by the closed-source nature of current Auto-DSM pipelines, the framework introduces a reproducible methodology that benchmarks generated DSMs (GEN-DSMs) against manually validated ground-truth matrices (GT-DSMs). The evaluation...

    arxiv.org/abs/2607.05985 · PDF

  29. 29

    Integrating knowledge graphs and multilingual scholarly corpora for domain-adaptive LLMs in SSH

    Adam Faci, Alessio Miaschi, Anne Combe, Pascal Cuxac, Francesca Frontini, Nicolas Larrousse, Stéphane Pouyllau

    cs.AI · cs.CL

    The integration of Large Language Models (LLMs) into scientific research workflows, particularly for bibliographic discovery and literature synthesis, raises significant methodological, epistemic and regulatory challenges for the Social Sciences and Humanities (SSH), especially with regard to disciplinary diversity, multilingual access to sources and the evaluation of results. This paper presents an on-going use case developed within the...

    arxiv.org/abs/2607.05956 · PDF

  30. 30

    SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation

    Zhengbo Jiao, Yiming Cheng, Yilei Jiang, Kaituo Feng, Rui Huang, Tianyi Jiang, Juanxi Tian, Jiapeng li, Qunzhong...

    cs.AI

    Training multimodal search agents to perform multi-hop reasoning remains challenging due to a fundamental structural disconnect: existing pipelines construct training data, search environments, and reward signals independently, causing synthesized structural metadata to be discarded, environments to rely on irreproducible external engines, and RL rewards to remain sparse at the trajectory level. We present \textbf{SearchEyes}, which uses a...

    arxiv.org/abs/2607.05943 · PDF

  31. 31

    PCBWorld: A Benchmark Environment for Engine-Grounded PCB Design Automation

    Hyungseok Song, Junseok Park, Won-Seok Choi, Seohui Bae, Han-Seul Jeong, Youngjoon Park, Soonyoung Lee

    cs.AI

    PCB routing is the task of connecting the nets of a board with copper traces under strict design rules, yet learning-based methods still lag behind rule-based routers. We introduce PCBWorld, an open-source engine-grounded PCB routing environment built on the KiCad EDA engine. As a human engineer does, agents in PCBWorld interactively route a board through the engine's native operations, using its Design Rule Check (DRC) feedback to keep the...

    arxiv.org/abs/2607.05915 · PDF

  32. 32

    Uncovering Latent Depression Severity for Binary Depression Detection via Advantage-weighting Ranking

    Manning Gao, Tingyi Liu, Leheng Zhang, Haifeng Hu, Yuncheng Jiang, Sijie Mai

    cs.AI

    Automatic depression detection using audio-visual data faces significant challenges, particularly in disentangling overlapping feature distributions and establishing robust decision boundaries. To address this, we propose a fine-grained multimodal framework featuring a temporal encoder and a mutual transformer to facilitate deep cross-modal fusion. Our core contribution is the Binary Advantage-weighting Ranking Loss, which optimizes the...

    arxiv.org/abs/2607.05901 · PDF

  33. 33

    StateFuse: Deterministic Conflict-Preserving Memory for Multi-Agent Systems

    Sergey Volkov, Yang Li, Ye Luo

    cs.AI · cs.CL · cs.MA

    Agent systems accumulate conflicting observations across branches, retries, and replicas, yet many practical memory layers still collapse disagreement behind overwrite rules that are difficult to inspect or correct. We present StateFuse, a conflict-aware replicated memory contract built on standard OpSet/CRDT merge. StateFuse does not introduce a new join algebra; it defines an agent-facing semantics layer with immutable history, explicit...

    arxiv.org/abs/2607.05844 · PDF

  34. 34

    Onnes: A Physics-Grounded Multi-Agent LLM Simulator for Cryogenic Fault Diagnosis in Quantum Computing Infrastructure

    Praneeth Narisetty, Uday Kumar Reddy Kattamanchi, Shiva Nagendra Babu Kore

    cs.AI · cs.LG · quant-ph

    Dilution refrigerators are the enabling infrastructure of superconducting quantum computers, yet their fault diagnosis is still dominated by threshold alarms that report that something is wrong, not what. We present Onnes, a physics-grounded digital-twin simulator of a dilution refrigerator (a forward physics model with a learned real-fridge noise fingerprint) that drives a live multi-agent LLM operations layer, and use it for a controlled...

    arxiv.org/abs/2607.05805 · PDF

  35. 35

    TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

    Yuhang Zhou, Kai Zheng, Haoling Li, Dengyun Peng, Can Xu, Jingjing Chen

    cs.AI · cs.CL

    On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajectories, offering a promising framework for language agent training. However, its application to long-horizon agentic tasks remains insufficiently explored. We identify two key inefficiencies in vanilla agent OPD: (1) full-horizon rollouts often waste wall-clock resources on tail turns that provide weak and noisy KL supervision, and...

    arxiv.org/abs/2607.05804 · PDF

  36. 36

    From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space

    Yue Xu, Yutao Sun, Yihao Liu, Mengyu Zhou, Jiayi Qiao, Lu Ma, Kai Tang, Wenjie Wang, Xiaoxi Jiang, Guanjun Jiang

    cs.AI

    Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfaces, making the model a consumer of pre-selected evidence. We introduce NapMem, a framework for learning to use long-term user memory as a structured action space rather than passively retrieved context. NapMem organizes user history into a linked multi-granularity memory pyramid, where raw...

    arxiv.org/abs/2607.05794 · PDF

  37. 37

    Controlling Tool Use with Heading-Specific Activation Steering

    Yuqi Chen, Vincent Siu, Yang Liu, Dawn Song, Chenguang Wang

    cs.AI

    Tool-augmented large language models extend their capabilities beyond parametric knowledge through external tools, but tend to invoke them unnecessarily. We investigate whether tool-use decisions have any stable internal representation that can be extracted and manipulated, a question that is non-trivial given that tools exist entirely in context at inference time and have no direct encoding in model weights. We show that steering vectors...

    arxiv.org/abs/2607.05790 · PDF

  38. 38

    Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents

    Wael Albayaydh, Rui Zhao, Ivan Flechais

    cs.AI

    Large language model (LLM) agents are increasingly evaluated on their ability to use tools, plan multi-step tasks, coordinate with other agents, and operate over extended horizons. Reported benchmark gains often obscure recurring failure modes documented across otherwise unrelated evaluation efforts. This paper synthesizes 27 benchmark, taxonomy, and audit papers (2023-2026), spanning 19 distinct benchmarks, into a cross-cutting taxonomy of...

    arxiv.org/abs/2607.05775 · PDF

  39. 39

    Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning

    Akshay Arora, Ishan Nigam, Ashutosh Aggarwal, Shefali Bansal, Krishna Singh, Sweta Kumari, Nikhil Mittal, Shariq...

    cs.AI

    As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making. We introduce AgenticAI-Supervisor, an API and UI-driven RL Gym environment that decouples environment creation from scalable execution. By moving to verifiable execution outcomes, the platform generates high-fidelity traces and applies multi-dimensional reward shaping. Critically, our framework mitigates...

    arxiv.org/abs/2607.05773 · PDF

  40. 40

    Synthetic Consumer Insight Generation with Large Language Models

    Stephen L. France, Pia. A. Albinsson

    cs.AI

    Modern data-driven marketing relies on large amounts of consumer data, yet collecting such data can be costly, time-consuming, and difficult to scale. This research examines whether large language models (LLMs) can be used to generate synthetic consumer data for projective techniques, a set of methods designed to elicit consumer associations, emotions, wants, and needs. We test LLM-generated responses across multiple projective tasks, LLMs,...

    arxiv.org/abs/2607.05761 · PDF

  41. 41

    ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation

    Yunhan Xu, Qifeng Wu, Xunjin Li, Yuanwei Bin, Qingsong Yao, Jianghang Gu, Guan Wang, Weihao Lv, Huiyu Yang, Wenfa...

    cs.AI · cs.GR

    Computer-aided design (CAD) for industrial components requires long-horizon procedural modeling, robust feature dependencies, editable parametric geometry, and production-grade B-Rep execution. Existing text-to-CAD methods have made promising progress in generating CAD programs from natural-language descriptions, but they still struggle when user prompts are ambiguous, underspecified, or only describe high-level design intent. They also...

    arxiv.org/abs/2607.05750 · PDF

  42. 42

    Akashic: A Low-Overhead LLM Inference Service with MemAttention

    Yang Liu, Zhaokai Luo, Huayi Jin, Ruozhou He, Chenchen Hong, Zhiyong Wang, Yifei Liu, Yunfei Gu, Chentao Wu, Junhao Hu

    cs.AI

    Recent LLM-based agent systems continuously accumulate context across multi-turn interactions, tool invocations, and cross-session workflows. Replaying the full history for every request quickly becomes impractical: long contexts increase prefill cost, may exceed context limits, and often bury task-relevant evidence in irrelevant content, degrading both serving efficiency and output quality. We propose Akashic, a low-overhead memory system...

    arxiv.org/abs/2607.05708 · PDF

  43. 43

    Memory in the Loop: In-Process Retrieval as ExtendedWorking Memory for Language Agents

    Yusuf Khan, Carlo Lipizzi

    cs.AI · cs.CL

    Language agents run a loop - observe, reason, act - but the memory they reason over sits outside it: a store queried at most once per turn. We study the regime where memory moves inside the loop, read and written on every step. The obstacle has always been latency: networked stores answer in tens to hundreds of milliseconds, and in-loop retrieval can inflate end-to-end latency by up to 83x when retrieval is expensive. Prior work manages that...

    arxiv.org/abs/2607.05690 · PDF

  44. 44

    FirstResearch: Auditable Question Formation for LLM Scientific Discovery Agents

    Yufeng Wang

    cs.AI

    LLM systems for scientific discovery increasingly assist with ideation, literature synthesis, experiment planning, and report generation, but the first research question they propose can remain difficult to audit: it may sound plausible without exposing the mechanism, falsifier, or assumption that a scientist should inspect. We introduce FirstResearch, a first-principles research-question formation framework for scientific LLM agents whose...

    arxiv.org/abs/2607.05682 · PDF

This edition is part of The Daily Abstract — cs.AI archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.