cs.AI · 2026-08-18 · No. 88

Artificial Intelligence, 2026-08-18.

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

01 — The papers

42 entries
  1. 01

    What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models

    Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu, Pratinav Seth

    cs.AI

    Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy. Such monitoring is meaningful only if a detector's verdict depends on the stated rule rather than on surface features of the scenario. We show this condition fails across the current class of...

    arxiv.org/abs/2608.16852 · PDF

  2. 02

    Policy Iteration with Human Feedback: Bringing Post-Training RL to In-context Learning

    Minh-Ha Nguyen, Cathy Shyr

    cs.AI · cs.CL

    Generative pretraining established reusable task representations; later work on language-based task conditioning and in-context learning showed that a fixed model could adapt its behavior from instructions and demonstrations. Policy Iteration with Human Feedback (PIHF) builds on this development and the recurrent evaluate-and-improve structure of generalized policy iteration. PIHF uses a pretrained language model as its execution substrate...

    arxiv.org/abs/2608.16831 · PDF

  3. 03

    Quipu: A Governed Bitemporal Knowledge Graph Store

    Steve Brown

    cs.AI · cs.DB

    Agents now write knowledge graphs, but knowledge-graph stores still carry defaults set when humans curated them: accept writes now and clean later, keep one time axis or none, treat every writer's facts as equally trustworthy, and leave governance to dashboards and middleware. These four defaults are individually convenient and jointly untenable under agent workloads. We present Quipu, an embeddable store that inverts all four: no fact enters...

    arxiv.org/abs/2608.16813 · PDF

  4. 04

    Cross-Sign Language Transfer Learning Using Domain Adaptation with Multi-scale Temporal Alignment

    Keren Artiaga, Yang Li, Ercan Engin Kuruoglu, Wai Kin, Chan

    cs.AI

    Sign language serves as a vital means of communication for individuals with hearing impairments, yet recognition resources for the over 100 distinct sign languages are severely lacking. In response, we present our work on sign language recognition using transfer learning and the domain adaptation method TA3N, which utilizes the Temporal Relational Network (TRN) module for aligning multi-scale temporal relations. Our findings highlight the...

    arxiv.org/abs/2608.16804 · PDF

  5. 05

    When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding

    Giuseppe Destefanis, Tomaso Aste

    cs.AI · cs.SE

    We study how teams of AI coding agents coordinate while solving programming tasks. Current evaluations usually report whether the agents complete the task and how much the run costs, leaving the coordination inside the team largely unmeasured. We introduce an instrument to measure this coordination. Each run is represented as a temporal network in which agents and files are nodes, and messages, file writes, and file reads are timestamped...

    arxiv.org/abs/2608.16801 · PDF

  6. 06

    GRIP: Grounded Reasoning via Information-Restricted Premises

    Lirui Teng

    cs.AI

    High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irrelevant. We call this failure mode query dominance. To address it, we introduce \textbf{GRIP} (Grounded Reasoning via Information-Restricted Premises), which imposes capacity asymmetry: the decoder keeps full-dimensional access to the query, while retrieved evidence passes through a severe...

    arxiv.org/abs/2608.16776 · PDF

  7. 07

    LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing

    Ruoqi Shu, Xuhui Wang, Isaac Wang, Yanming Mai, Bo Wan

    cs.AI

    Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and reproducibility under strict enterprise constraints. In practice, documents arrive with heterogeneous layouts and formats, semantically rich and context-dependent content, and embedded business rules that current pipelines struggle to process reliably. We introduce LAVA (Logic-Aware...

    arxiv.org/abs/2608.16763 · PDF

  8. 08

    FabriMAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy

    Aniri, Chen Yilin, Jinhe Bi, Junfei Guo, Donglai Ran, Xu Bian, Zengjie Jin, Yujun Wang, Yijun Tian, Volker Tresp,...

    cs.AI

    Vision-Language-Action models (VLAs) integrate visual perception, language instruction, and action generation into end-to-end policies across heterogeneous architectures. However, enabling VLAs to self-evaluate their action generation reliability without external supervision remains a major challenge. Existing methods either rely on expert annotations or estimate uncertainty only from output statistics, largely ignoring internal signals. In...

    arxiv.org/abs/2608.16697 · PDF

  9. 09

    Chronocooked: A Benchmark for Implicit Interval Timing in Reinforcement Learning Agents

    Amrapali Pednekar, Alvaro Garrido-Perez, Yara Khaluf, Pieter Simoens

    cs.AI

    This paper presents Chronocooked, a reinforcement learning (RL) benchmark suite for studying implicit interval timing in RL agents. Inspired by Overcooked, the suite comprises cooking scenarios that require temporal decision making. The tasks and reward functions are designed such that temporal information is unobserved yet critical for optimal performance. The environment is intentionally kept simple to enable controlled experiments and...

    arxiv.org/abs/2608.16666 · PDF

  10. 10

    Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies

    Shaolong Chen, Yanlin Fei, Nazhou Liu, Xinmiao Yu, Lei Li, Rahul Thapa, Madalina Ciobanu, Qingqing Mao, Ritankar Das

    cs.AI · cs.CL · cs.MA

    Can a language model recover the true research idea of a published paper when given only that paper's pre-publication bibliography? We introduce Reconstruction, a blind idea-recovery benchmark that withholds the seed paper and all contemporaneous or future literature, and asks models to propose hypotheses that an independent large language model judge matches against the held-out ground-truth idea. A strict anti-leakage protocol-temporal...

    arxiv.org/abs/2608.16645 · PDF

  11. 11

    PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning

    Veit Laule, Jiangtao Shuai, Manfred Hauswirth, Sonja Schimmler

    cs.AI

    LLMs remain unreliable for long-horizon planning, often generating logically inconsistent or non-applicable plans. Recent hybrid methods instead translate natural language into the Planning Domain Definition Language (PDDL), allowing symbolic planners to produce verifiable plans. However, existing methods frequently rely on rigid generation pipelines, a partial PDDL definition, or human feedback. Furthermore, their evaluation is hindered by...

    arxiv.org/abs/2608.16637 · PDF

  12. 12

    Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement

    Shenao Chen, Yidan Xu, Xiangmin Han, Rundong Xue, Duanpo Wu, Yuhan Gao, Chenggang Yan, Yue Gao

    cs.AI

    Modern Multimodal Retrieval-Augmented Generation (M-RAG) systems are fundamentally limited by the binary connectivity paradigm of traditional simple graphs, which fails to capture the intricate, high-order correlations among heterogeneous entities, such as the N-ary relationships between a visual chart, its scattered textual descriptions, and underlying numerical data. Furthermore, existing refinement strategies often rely on exhaustive,...

    arxiv.org/abs/2608.16628 · PDF

  13. 13

    A Shop Floor Production Scheduling Case based on RFID-supported Smart Factory

    Zhihui Chen, Yize Sun, Yuhao Dong, Zeyu Xiao, Ray Y. Zhong

    cs.AI

    Radio frequency identification (RFID) technology has been widely implemented for real-time data collection in manufacturing shop floors, which, in turn, can be used to support dynamic shop floor production planning and scheduling. Within such an environment, uncertainty in operation and production processes collectively contribute to the dynamicity in manufacturing, thereby hampering the scheduling system from achieving maximal utility. To...

    arxiv.org/abs/2608.16626 · PDF

  14. 14

    Cost Scales with Change, Not Corpus Size: Incrementally Maintaining an Evolving Semantic Substrate

    Yusuke Takahashi, Kyle Wild, Asako Uraki

    cs.AI · cs.DB · cs.IR

    Retrieval-augmented and agentic question-answering systems increasingly re-derive the meaning of a corpus at query time. Put plainly, instead of re-deriving what a corpus means on every question, the work is done once when a document arrives and is thereafter merely consulted -- a compiler, not an interpreter, of meaning. An alternative is to compile that meaning once, at ingest time, into a compact, queryable semantic substrate and maintain...

    arxiv.org/abs/2608.16621 · PDF

  15. 15

    CACSurv: Concordance-Aligned Comparative Learning with Large Language Models for Cancer Survival Prediction

    Tianqi Xiang, Qixiang Zhang, Xinpeng Ding, Yi Li, Xiaomeng Li

    cs.AI

    Cancer survival prediction supports treatment planning, risk stratification, and follow-up management. Existing methods use structured clinical variables, whole-slide images, genomic profiles, or multimodal inputs, while patient reports remain underexplored. We study report-centric survival prediction using reports that organize pathological, clinical, and molecular evidence. Large language models (LLMs) can reason over such reports, but...

    arxiv.org/abs/2608.16594 · PDF

  16. 16

    Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents

    Batu El, Jinhee Paeng, Fatih Dinc, Shiye Su, Mete Erdogan, Aneesh Pappu, Haotian Ye, Wanjia Zhao, Surya Ganguli, James Zou

    cs.AI · cs.MA · cs.SI

    AI agents increasingly operate as part of interacting systems rather than in isolation. As agents exchange information and jointly make decisions, their interactions can improve collective reasoning but may also produce herding, polarization, or amplify shared biases. Understanding and predicting these collective dynamics is therefore important for designing effective and aligned multi-agent systems. Here, we study over 10,000 communities of...

    arxiv.org/abs/2608.16578 · PDF

  17. 17

    Probabilistic Circuits as Reasoning Machines in Artificial Intelligence (Part I)

    Robert Peharz

    cs.AI · cs.LG · math.PR

    This cumulative habilitation thesis studies probabilistic circuits (PCs) as a powerful and tractable framework for reasoning and learning under uncertainty in artificial intelligence (AI). It first advocates for probability as a core language for AI, emphasizing its connections to logic and information theory; the conceptual simplicity of probabilistic reasoning---based primarily on the sum and product rules; the parallels between...

    arxiv.org/abs/2608.16565 · PDF

  18. 18

    CUBICS: Situation-aware performance estimation for safety-relevant ML components

    Benjamin Herd, Jessica Kelly, Mario Trapp

    cs.AI

    Machine learning (ML) is a key technology driving innovation today, but ensuring ML safety remains a major challenge for safety-related applications. A promising idea is to build proven-in-use arguments from field data, e.g. by running ML components (MLCs) in shadow mode or within safety envelopes so that their outputs can be monitored as 'safe probes' without affecting safety. These probes can then be used to build a statistical argument...

    arxiv.org/abs/2608.16564 · PDF

  19. 19

    DeepInsight II: One Trace from Benchmark to Robot

    Siyi Li, Yuchen Kang, Wuliang Wang, Zhengjie Zhang, Jiangpin Liu, Jianhao Yao, Jie Chen

    cs.AI

    Across a Physical AI stack, evaluation maturity is inversely aligned with deployment risk: foundation models enjoy mature, standardized harnesses, while the embodied layers on which deployment actually turns remain fragmented across benchmark-specific simulators, embodiments, and interfaces. The first DeepInsight report (v1) unified evaluation across this stack behind three abstractions---task, resource, and result---but its quantitative...

    arxiv.org/abs/2608.16556 · PDF

  20. 20

    Large language models as synthetic clinical experts to inform longitudinal rare-disease modeling

    Clemens Schächter, Astrid Pechmann, Janbernd Kirschner, Jan Hasenauer, Harald Binder

    cs.AI

    Due to the limited amount of information, modeling longitudinal rare-disease data can benefit from integrating clinical knowledge. Yet, elicitation of expert knowledge and formalization for model fitting is challenging, in particular due to limited time of clinical experts. To nevertheless make domain knowledge accessible during model fitting, we use large language models (LLMs) as synthetic clinical experts to supervise a...

    arxiv.org/abs/2608.16507 · PDF

  21. 21

    Offline Reinforcement Learning for Hemodynamic Management of Sepsis in the ICU: a MIMIC-IV Study with Dual Off-Policy Evaluation

    Marc Pérez-Roig, David Fernández-Narro, Carlos Sáez

    cs.AI · cs.LG

    The dosing of intravenous fluids and vasopressors in sepsis is a sequential decision made under uncertainty and guided largely by clinical judgment, which makes it a natural target for reinforcement learning from historical care. Because a learned policy cannot be trialed on patients, its value must be estimated off-policy, and such estimates can be fragile and optimistic. This work advances the reliable evaluation of sepsis treatment...

    arxiv.org/abs/2608.16482 · PDF

  22. 22

    JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills

    Xiaoyu Wen, Jiajia Li, Zhida He, Peng Yu, Chenxu Wang, Han Qi, Ziyuan Zhou, Cheng Jin, Ying Wen, Xingcheng Xu,...

    cs.AI

    Automated red-teaming has produced a growing collection of attack strategies, yet they typically remain scattered across prompts and workflows, making them difficult to systematically integrate, reuse, and improve at scale. We introduce \textsc{JailbreakSkill}, a skill-centric framework for scaling automated red-teaming through reusable and continuously evolving attack capabilities. \textsc{JailbreakSkill} packages existing attack strategies...

    arxiv.org/abs/2608.16465 · PDF

  23. 23

    HaReCAP: Habitual-action Grounding for Recursive Large Language Model Agents

    Shen Liu, Zhenguo Xu, Shaopu Wang, Yike Gao, Chunlei Wang

    cs.AI · cs.RO

    Long-horizon embodied tasks require LLM agents to iteratively decompose high-level goals, revise plans in response to environmental feedback, and ground leaf-level subgoals into valid executable actions. Recursive context-management methods such as ReCAP improve planning stability through multi-level task decomposition and parent-node refinement, but still repeatedly invoke the LLM at leaf nodes to ground atomic subtasks into exact valid...

    arxiv.org/abs/2608.16447 · PDF

  24. 24

    Time to Reason: Scalable Neurosymbolic Learning for LTLf via Fuzzy Semantics

    Riccardo Andreoni, Andrei Buliga, Alessandro Daniele, Paolo Felli, Chiara Ghidini, Marco Montali, Massimiliano Ronzani

    cs.AI

    Neurosymbolic (NeSy) Artificial Intelligence aims to integrate Deep Learning (DL) architectures with symbolic reasoning. While initial NeSy approaches have targeted mainly symbolic reasoning in propositional and first-order logics, recent works have started to address the construction of neurosymbolic frameworks for Temporal Logics, and in particular for LTLf. These approaches have established temporal NeSy as a promising research direction,...

    arxiv.org/abs/2608.16443 · PDF

  25. 25

    The Value of a Prompt: An LLM-Relative Kolmogorov-Complexity Approach

    Rafael Pass

    cs.AI · cs.CC · cs.IT

    In a world where valuable artifacts are increasingly created, completed, or processed by LLMs, the central economic question is not only what the LLM can produce, but what \emph{value} remains in the inputs (i.e., the prompts) we provide to it. Given a prompt, hint, critique, problem statement, or partial solution that helps an LLM produce an artifact $z$---a proof, program, design, or scientific hypothesis---how should we measure the value...

    arxiv.org/abs/2608.16438 · PDF

  26. 26

    Drive, Pack, Fly: The Travelling Thief Problem with Drone

    Kabir Murjani, Abhay Sobhanan

    cs.AI · cs.NE · math.OC

    In collection operations, accumulating payload progressively slows the vehicle, imposing a cumulative penalty on routing efficiency. An onboard drone can offset this penalty by retrieving outlying items, thereby shortening the makespan and increasing operational profit. However, travel time remains load-dependent, and each item collected by the ground vehicle shifts the arrival times that govern the drone's launch and rendezvous points. This...

    arxiv.org/abs/2608.16435 · PDF

  27. 27

    ParaTempo: Efficient Parallel Reasoning via Temporal Confidence

    Xuteng Zhang, Wenhao Zeng, Xiaodong Gu, Chao Hu, Haotian Lin, Yuling Shi, Min Wang, Beijun Shen

    cs.AI

    Parallel reasoning improves the accuracy and robustness of large reasoning models by exploring multiple solution paths, but its computational cost grows with reasoning depth and branch count. Existing methods for managing these parallel paths typically rely on final-answer consensus, local token confidence, or isolated intermediate probes. However, these signals are often delayed, weakly tied to actual reasoning progress, or too noisy for...

    arxiv.org/abs/2608.16425 · PDF

  28. 28

    Reasoning-supported Robustness Validation of Automotive E/E Components

    Jan Novacek, Alexander Viehl, Oliver Bringmann, Wolfgang Rosenstiel

    cs.AI

    This paper presents an ontology-supported approach to tackle the complexity of the Robustness Validation (RV) process of automotive electrical/electronic (E/E) components. The approach uses formalized knowledge from the RV process and stress, operating, and load profiles, so-called Mission Profiles (MPs). In contrast to the error-prone industrially established manual procedure, we show how component characteristics are formalized in OWL in...

    arxiv.org/abs/2608.16421 · PDF

  29. 29

    A Policy Algebra for Trust-Preserving Agentic AI Execution

    Bhaskar Tripathi, Anurag Kumar, Ramendra Kumar, Bhavesh Gadhe

    cs.AI

    Large language model-based agentic frameworks primarily optimize capability: whether an agent can reason, retrieve information, call tools, delegate work, and complete a goal. Enterprise execution requires a stronger property. A successful result is not reliable if it was produced through unauthorized data access, widened delegated authority, unapproved side effects, unrecoverable budget consumption, or incomplete evidence. This paper defines...

    arxiv.org/abs/2608.16402 · PDF

  30. 30

    Think Inside the Chunk: RegulaRAG for Regulation-Compliant Scenario Generation using LLMs: A Case Study of UN Regulation No. 152

    Vahid Zolfaghari, Nenad Petrovic, AndrÉ Schamschurko, Alois Knoll

    cs.AI · cs.IR

    Generating regulation-compliant test scenarios is essential for validating safety-critical automotive systems, yet Large Language Models (LLMs) struggle to ground outputs in long, hierarchical standards. We present RegulaRAG, a Retrieval-Augmented Generation (RAG) pipeline that couples SmartChunking, reference-aware enrichment of paragraphs and tables via graph traversal, with Smart Retrieve & Rerank over these enriched units. To test our...

    arxiv.org/abs/2608.16394 · PDF

  31. 31

    AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems

    Zhenhang Nie, Gui Zheng, Xudong Sun, Tailong Zhu, Bin Zhang

    cs.AI

    Agentic systems often organize execution and state around a single conversation, model invocation, or agent instance, even when real work spans many calls and stages. We introduce a unified execution model that maintains a work item's persistent identity and versioned authoritative state across calls. Each step receives input scoped to a specific state version and new material; a result advances state only after validation and recording. We...

    arxiv.org/abs/2608.16381 · PDF

  32. 32

    What Does Context Compression Cost an Agent? Interaction Costs Unrevealed by Task-Completion Metrics

    Shuyu Liu

    cs.AI

    Task completion is the standard metric for evaluating context compression, yet it is incomplete: compression can increase an agent's interaction cost by forcing it to reacquire dropped state while leaving completion statistically unchanged. We introduce a controlled runtime measurement protocol for reacquisition cost in a bounded-horizon tool-using agent. The agent acts in a deterministic planning environment under a fixed 24-turn horizon. We...

    arxiv.org/abs/2608.16370 · PDF

  33. 33

    DriveCache: Action-Aware Caching for Driving World Model Inference

    Jianchun Yang, Jian Liang, Xianda Guo, Pinhan Fu, Yanlun Peng, Conglang Zhang, Wenke Huang, Mang Ye

    cs.AI · cs.CV

    Driving video generation models support autonomous-driving development by predicting controllable future scenes for simulation, planning evaluation, and offline data generation. Diffusion-based driving generators repeatedly evaluate large backbones across denoising steps, which limits generation throughput. Existing diffusion acceleration methods reduce this cost, but general-purpose designs omit driving signals available before generation,...

    arxiv.org/abs/2608.16354 · PDF

  34. 34

    AeroCopilotBench: A Two-Tier Benchmark for Evaluating LLM Agents as Aviation Copilots in an Interactive Virtual Cockpit Environment

    Yuchen Yuan, Zhenghuang Wu, Yuangan Li, Liang Ma, Ke Li

    cs.AI

    Large language model (LLM) agents may assist flight crews with complex decisions and task execution, but existing aviation evaluations centered on static knowledge do not support systematic testing of procedural execution and safety compliance in interactive environments. This paper presents the AeroCopilot Operational Environment (ACOE), a reproducible interactive virtual-cockpit test environment, and AeroCopilotBench, a two-tier aviation...

    arxiv.org/abs/2608.16349 · PDF

  35. 35

    Process-Constituted Intelligence: A Shared Criterion for Humans and Machines

    Michael J. Richardson, Ayeh Alhasan, Cassandra Crone, M. Paula Diaz Monfort, Patrick Nalepka, Mark Dras, Rachel W....

    cs.AI · cs.ET

    Intelligence is constituted by \textit{process} (iterative activity through which output emerges), not in the output itself. Generative AI (GenAI) is trained on \textit{traces} (textual and visual residues of human cognitive processes), reproducing samples from a distribution of those traces. Its outputs resemble reasoning, problem-solving, and creativity, yet the activity that produces such outputs in humans remains largely absent. Current...

    arxiv.org/abs/2608.16213 · PDF

  36. 36

    BaT: Towards Self-Evolving Medical Research Agent with Stage Rubrics

    Junqi Liu, Yufan He, Yexiao He, Pengfei Guo, Dong Yang, Andriy Myronenko, Can Zhao, Hanrong Ye, Tianhao Qi, Yuyin...

    cs.AI

    Long-horizon agents are beginning to automate complete workflows that produce code, reports, and research artifacts. Medical imaging workflows are multi-stage and data-sensitive, while expert trajectories remain scarce and difficult to share. Structured benchmarks can localize failures through stage-level rubrics, but standard post-training discards these diagnostics before the next training round. We present Benchmark-as-Teacher (BaT), a...

    arxiv.org/abs/2608.16211 · PDF

  37. 37

    Competing at Every Price Point with Agentic Evolution over a Menu of LLMs

    Andrew Borthwick

    cs.AI

    Consider a firm that surveys its competition for a particular agentic task and seeks to offer superior accuracy at every competitor price point. A firm that Pareto-dominated its competitors would leave no rational customer a reason to buy elsewhere. This paper shows a path to this kind of capability via agentic evolution over a menu of LLMs, from training pools of at most 100 examples. Given a priced menu of nine LLM endpoints; brief...

    arxiv.org/abs/2608.16207 · PDF

  38. 38

    Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior

    Yifan Lu, Xiaopeng Yuan, Haohan Wang

    cs.AI · cs.HC

    Personalized game generation requires inferring a player's abilities and behavioral style from how they play. Large language models have made this inference more attainable than ever: an LLM can read a raw gameplay transcript and produce a fluent, plausible profile of the player. Plausible, however, is not verified, and verification is precisely what the field lacks: latent traits are unobservable; questionnaires provide noisy proxies and...

    arxiv.org/abs/2608.16196 · PDF

  39. 39

    Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication

    Jia Guo, Xiaohan Zhao, Changwang Liu, Shuqing He, Chenyang Zhang, Bingchuan Zhao, Jinqi Zhu

    cs.AI

    Generative visual-token communication reduces transmission load by sending only selected discrete tokens and reconstructing missing content at the receiver. However, existing token-selection criteria based on local uncertainty, importance, or diversity do not directly determine whether changing the current selection improves the final reconstruction under the same packet budget. To address this problem, we propose Gated Counterfactual...

    arxiv.org/abs/2608.16192 · PDF

  40. 40

    Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terrain

    Rocky Liu, Tengyu Liu, Baoxiong Jia, Fangwei Zhong, Xinyi Tong, Hongzhao Xie, Siyuan Huang

    cs.AI · cs.RO

    Training locomotion policies for complex unstructured terrain requires a curriculum to avoid early exploration failures. However, since unstructured terrain lacks explicit difficulty ordering for curriculum design, existing methods resort to heuristic curricula over parameterized terrains. This abstraction limits generalization, as policies can overadapt to near-fixed perceptual patterns. To address this, we propose \textbf{\ourname{}}, an...

    arxiv.org/abs/2608.16164 · PDF

  41. 41

    TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents

    Huan Zhang, Mingju Chen, Dongxu Zhou, Can Lv, Heng Chang, Sen Cui, Faguo Wu, Shiji Zhou

    cs.AI

    Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult. Existing approaches either rely on process evaluators, which incur annotation and inference costs, or derive step-level credit from successful trajectories. However, successful trajectories are extremely scarce during early-stage reinforcement learning,...

    arxiv.org/abs/2608.16156 · PDF

  42. 42

    FeatureHospital: A Skill-Driven Multi-Agent Framework for Automated Algorithm Customization in Multi-View Multi-Label Feature Selection

    Junxuan Li, Zhiqi Chen, Yuzhou Liu, Peng Zhang, Huaxiao Liu

    cs.AI

    Multi-view multi-label feature selection aims to identify a compact and informative feature subset from heterogeneous views while preserving discriminative information for multiple labels. Existing methods are generally developed from specific modeling perspectives and incorporate mechanisms tailored to particular data characteristics. Designing suitable feature selection algorithms across datasets with diverse and heterogeneous...

    arxiv.org/abs/2608.16148 · 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.