cs.AI · 2026-08-06 · No. 76
Artificial Intelligence, 2026-08-06.
31 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
31 entries-
01
Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning
Boxiu Li, Zimo Wen, Yijia Fan, Junxiang Lei, Sufeng Guo, Jiaao Wu, Ruize Tang, Mukai Li, Yifei Shen, Xiaoyu Chen,...
cs.AI
Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and pivot when measurements reveal failure, hidden constraints, or a misspecified objective. We present Argus, a persistent, self-evolving runtime in which Manager, Planner, Engineer, and Reviewer execute bounded missions over durable project state. Argus separates stable user intent from operational objectives, constraints, and...
-
02
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
Indraneil Paul, Falko Helm, Goran Glavaš, Iryna Gurevych
cs.AI · cs.LG · cs.SE
Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflows. Existing long-context corpora, however, are dominated by books, academic articles, and code repositories, which are finite resources and often scarce in long-distance dependencies. In this work, we introduce OctoLong, a context engineering pipeline that instruments an AST...
-
03
CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
Hung Truong Thanh Nguyen, Hélène Fournier, Piper Jackson, Makoto Itoh, Shannon Freeman, Rene Richard, Hung Cao
cs.AI · cs.MA · cs.SE
AI-supported care planning can help clinicians, patients, caregivers, and care teams coordinate complex decisions across clinical, functional, psychosocial, and environmental needs. However, many AI systems present recommendations as fixed outputs, limiting stakeholders' ability to inspect, challenge, and revise plans when they conflict with clinical judgment, patient values, or real-world feasibility. We present CoPlan - a Co-Intelligent and...
-
04
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Yijun Lu, Rui Ye, Jiajun Wang, Yuwen Du, Tian Jin, Songhua Liu, Siheng Chen
cs.AI
Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer. However, existing methods for training these agents typically treat all steps within a trajectory uniformly during both supervised fine-tuning (SFT) and reinforcement learning (RL), failing to distinguish useful actions from erroneous or redundant ones. In this paper, we propose...
-
05
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
Xiawei Yue, Boran Wang, Xiaoqing Zhang, Shuxin Zheng, Ziwei Zhang
cs.AI
Agents for long term reasoning require a memory that can be efficiently and effectively updated over time, as new facts and external feedback continue to arrive. Recently, graph memory has been adopted to offer structural organization for multi-hop retrieval and reasoning. However, existing methods store all memories in a flat graph, and accumulated historical memories can introduce irrelevant contexts and increase the cost of evidence...
-
06
Item Response Theory for AI Safety
Joshua Fonseca Rivera, Neil Shah, David Demitri Africa, Konstantinos Voudouris
cs.AI · cs.CL
Language models differ in how safely they behave and these differences are measured by safety benchmarks. But aggregated benchmark scores are hard to trust and interpret, because benchmarks duplicate one another, correlate heavily, and models may sandbag when they detect evaluation. To address these issues, we draw on Item Response Theory (IRT), a statistical toolkit for measuring these latents from performance on items with inferred...
-
07
From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Score Reranking
Shaopeng Liang
cs.AI
Football score forecasting combines a strong statistical core with a difficult contextual edge. Dynamic Poisson-family models estimate team strength, expected goals, and coherent score probabilities, but do not directly understand roles, tactical matchups, motivation, or how a first goal changes behaviour. Large language models (LLMs) can reason about such concepts, yet are not calibrated probability engines. We combine both components...
-
08
Short-term load forecasting under EU-AI Act Requirements in Safety-Critical Environments: Results from a 41-day live challenge on the aggregated German transmission-grid load
Thomas Bartz-Beielstein
cs.AI · cs.LG
Short-term load forecasting (STLF) play a vital role in the electric power industry. It serves infrastructure that European and German law designate as critical. Determinism, reproducibility, and auditability are engineering requirements rather than optional extras. STLF is no longer purely an accuracy problem. It is also a software-engineering and compliance problem. This paper describes results from a 41-day live challenge that evaluated a...
-
09
WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models
Bohai Gu, Yueyang Yuan, Taiyi Wu, Dazhao Du, Jian Liu, Xiaoyi Pang, Jie Zhang, Xiaocheng Lu, Haobin Zhong, Xiaotong...
cs.AI · cs.LG
Interactive video world models are essential for long-horizon planning and exploration, yet they suffer from compounding errors. Post-training methods such as reinforcement learning (RL) can improve these models, but they hit a verification bottleneck: for arbitrary action sequences, no ground-truth future state exists to measure long-term drift. Our key insight is that reversible action cycles make this verification possible: a sequence...
-
10
When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit
Ziang Wei, Minjun Yu, Zheyuan Lai, Mingjie Pang, Wei Li
cs.AI · cs.CV
Defensive driving scores are useful only when they preserve distinctions between policies that observe surrounding actors and those that do not. Re-simulation benchmarks may use reference-conditioned forgiveness, under which an agent receives credit when the logged human reference fails a compliance channel. When agent and reference share an unstable rollout transformation, this rule can propagate shared reference failures into broad...
-
11
ContextWeave: A Real-World Workflow Benchmark
Bo Wang, Yuqian Yao, Enxi Wang, Luozhijie Jin, Yang Liu, Yiran Suo, Yuxuan Cai, Enyu Zhou, Yufei Gao, Honglin Guo,...
cs.AI
Memory is essential as language agents move from isolated tasks to long-horizon, stateful workflows, yet existing evaluations often reduce it to retrieval or question answering. We introduce ContextWeave, a longitudinal benchmark that evaluates whether recalled experience improves downstream agent performance in realistic office-work streams. ContextWeave reconstructs privacy-preserved, multi-month workflows of 14 participants into 1,005...
-
12
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
Sarthak Harne, Chinmay Karkar, Yash Pandya, Ahmed Awadallah, Akshay Nambi
cs.AI · cs.LG
Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI) about the answer such as a reference solution, supplies dense per-token supervision to a student that never sees it. Reported gains, however, come almost exclusively from narrow, low-difficulty settings, leaving open a basic question: as a lone objective, with no...
-
13
NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment
Yu Zhao, Jiangyu Pan, Tao Hu, Ming Yin, Fan Yang, Jiangfan Liu, Xiubo Liang
cs.AI
The ability to accurately assess and anticipate risks in safety-critical scenarios is crucial for autonomous driving systems. While existing research has made progress in collision prediction, accurately quantifying risk levels from monocular vision inputs remains challenging due to the complex dynamics of multi-agent interactions and the inherent uncertainty in real-world environments. To address these challenges, we present NSF-HRPT, a...
-
14
Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning
Qiyuan Zhu, Dezhi Li, Pengyu Cheng, Tianle Chen, Jiacheng Wang, Ruijie Shen, Hao Gu, Sida Lin, Zirui Liu, Jiacheng...
cs.AI
Large Reasoning Models (LRMs) excel on complex tasks through long chain-of-thought (CoT) reasoning, but their lengthy intermediate steps cause severe overthinking that inflates inference cost. KV-cache compression is a common solution, yet existing reasoning-oriented methods apply a uniform policy across the trajectory and judge compression only by what it removes from the cache. Two observations point the other way. First, a reasoning...
-
15
EviGraph: Evidence-Guided Autonomous Research Agents
Zhenjiang Ren, Ruiji Li, Xujing Zhang, Ziliang Pang, Shuo Ren, Jiajun Zhang
cs.AI
Autonomous research agents can generate hypotheses, execute experiments, and draft manuscripts, yet their outputs often contain unsupported claims and inconsistencies between research questions, experiments, results, and conclusions. We argue that this problem is partly architectural: existing systems organize research as sequential pipelines but do not explicitly maintain or validate the evolving claim-evidence structure across stages.In...
-
16
Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings
Agatha Duzan, Asa Cooper Stickland
cs.AI
Chain-of-thought (CoT) monitoring is increasingly treated as an important safety layer for frontier reasoning models. Most monitorability evaluations study explicit-influence settings: setups where the prompt directly incentivizes the model to hide something, e.g., by instructing it to perform a hidden side-task. A complementary axis for CoT-monitor evaluations is implicit-influence settings, where the prompt contains no instruction to hide,...
-
17
When Prompts Become Pixels: Prompt-Region Grounding for Multimodal Reasoning
Yongxin Wang, Ruizhe Zhou, Yueling Tang, Yingying Zhu, Xuemin Zhao, Xiaojun Chang, Xiaodan Liang
cs.AI · cs.CV
Multimodal large language models increasingly reason over screenshots and documents where the task itself may be written in pixels. Yet benchmarks usually place questions in text, leaving it unclear whether models use the same instruction equally well across channels. We introduce Visualized Task Semantics (VTS), a controlled intervention that moves the question into the image while keeping the source problem and answer fixed. Across six...
-
18
Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools
Atul Anand, Sourav Chattaraj
cs.AI
Agent evaluations tell us that a model picked the wrong tool, but rarely why. We introduce canary tools: diagnostic probe tools planted in an agent's Model Context Protocol (MCP) tool set, each engineered to probe one specific tool-selection weakness. A six-type taxonomy (semantic decoys, parameter traps, capability mirages, prerequisite blindness, temporal decoys, and granularity traps) turns a single "wrong tool" outcome into a...
-
19
Traceable LLM-Generated Hazard Scenarios for Operational Safety Analysis of Aviation Systems Using ASRS Reports
Cristian Mascia, Roberto Pietrantuono, Daniel Rodriguez, Stefano Russo
cs.AI
Operational hazard analysis of aviation system operations must consider interactions among weather, ATC actions, airspace constraints, aircraft operations, and human factors - distinct from the functional hazard assessment applied at the aircraft-system level. We present an AI-assisted approach that generates candidate hazard scenarios from NASA's Aviation Safety Reporting System (ASRS). Given a target adverse outcome, it produces a...
-
20
Calibrating Artificial Guilt: Neurally Grounded Reward Shaping for Prosocial Multi-Agent Reinforcement Learning
Aaditya Mehta, Arya Shah
cs.AI
Cooperative multi-agent reinforcement learning often adds social terms to individual rewards, yet the scale of those terms is usually chosen by hand. We ask whether a guilt signal can instead be calibrated from human neural and behavioural data and transferred to artificial agents. Using the public SoDec responsibility fMRI dataset (40 participants), we fit a subject-fixed-effects regression of momentary-happiness changes on outcome-type...
-
21
AI Literacy for Legal Translation: Developing Digital Resilience
Łucja Biel
cs.AI · cs.CL · cs.CY · cs.HC
Generative AI is transforming legal translation by introducing opportunities alongside linguistic, technical, legal, ethical and cognitive risks. This chapter examines the implications of AI for professional legal translation and proposes an AI literacy framework tailored to the profession. It argues that AI does not change the fundamental objectives of legal translation but requires an extension of professional competence through AI...
-
22
A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing
Zhuohang Jiang, Yuxin Chen, Yongsen Pan, Zheng Hu, Wenqi Fan, Qing Li, Hongyang Wang, Jun Wang, Wenwu Ou
cs.AI
Industrial recommendation strategy iteration heavily relies on large-scale A/B experimentation. Traditional tuning requires experts to repeatedly design strategies, configure experiments, analyze results, and adjust parameters, making the process labor-intensive and time-consuming. Meanwhile, valuable knowledge from historical experiments is often fragmented, making systematic reuse difficult through manual expert effort alone. Existing RAG...
-
23
Agreement Before Diversity: Verification-First Complementarity for Heterogeneous Language-Model Coordination
Ruitong Li, Binjie Guo, Aisheng Mo, Guowei Su, Jie Li, Ru Zhang
cs.AI
Heterogeneous language-model ensembles expand the space of candidate responses, yet they lack a principled criterion for when a newly generated answer should supersede an already supported one. We decouple candidate headroom from replacement authority, rendering the latter as an explicit, auditable object. Our proposed method, Agreement-Before-Diversity (ABD), is a frozen, label-free decision rule: an anchor answer is retained if two...
-
24
Joint UAV Flight and Opportunistic Routing under Reinforcement Learning for Delay-Tolerant Networks
Xiao Wang, Shun-Ren Yang
cs.AI
The growing deployment of delay-tolerant networks (DTNs) has made store-carry-forward (SCF) communication indispensable under sparse connectivity. However, intermittent contacts, finite buffers, and limited message time-to-live (TTL) often give rise to sparse delivery and congestion, leading to substantial end-to-end performance degradation. To address this challenge, this study explores the joint optimization of decentralized opportunistic...
-
25
What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills
Tao Li, Junfeng Liu, Qinghua Zhao, Yifan Li, Lei Wang, Bo Shao, Xuejun Liu, Linjun Shou
cs.AI
Agent skills are increasingly optimized by automated feedback loops, producing long structured artifacts whose internal value remains unclear. We study skill valuation: assigning credit to the internal units of a fixed skill, such as rules, examples, scripts, and heuristics, under a fixed agent and held-out task distribution. Skill valuation differs from data or prompt-span valuation because skill units are structured: they may depend on...
-
26
Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness
Haoting Qian, Qingjie Zhang, Zhicong Huang, Cheng Hong, Han Qiu
cs.AI · cs.CL
Benchmarking machine unlearning methods is critical to understand whether sensitive knowledge is removed from large language models (LLMs) or not. Current unlearning benchmarks include mainly single-hop questions and a narrow set of multi-hop questions. Although effective, they still face two challenges. (1) Knowledge is not isolated, whereby diverse multi-hop reasoning paths can potentially induce knowledge leakage than normal queries. (2)...
-
27
CARGO-VL: Counterfactual Arbitration with Risk-Constrained Group Optimization for Vision-Language Models
De Jiang, Zhengyang Zhang, Kehong Yuan, Shaohua Ma
cs.AI
Vision-language systems combine images with retrieved text, but these sources can disagree or jointly fail to support an answer. Reliable models must identify the trustworthy source and abstain when neither is adequate. Existing post-training objectives score instances independently and therefore do not enforce coherent behavior under counterfactual evidence changes. We introduce CARGO-VL, a group-relative framework that optimizes matched...
-
28
Architectural Implications of Agentic AI Workflows
Jirong Yang, Peizhe Liu, Chaojie Zhang, Jovan Stojkovic
cs.AI · cs.AR · cs.OS
Agentic AI is emerging in datacenters, but its architectural implications remain unexplored. We organize agentic workflows in a taxonomy and present its first architectural characterization with a production study at Microsoft Azure and a controlled study of open-source frameworks. We show that agentic execution is fragmented and heterogeneous. Requests expand into a workflow of LLM inferences, tool invocations, and orchestration decisions...
-
29
Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language
Shengxin Kong, Liwen Xu, Jingwen Fu
cs.AI
Neural PDE solver auto-design is fundamentally a search-space representation problem. In the space of unrestricted Python programs, valid solvers form an extremely sparse subset: most candidate programs are syntactically incorrect, semantically incompatible, or numerically unstable. Direct code generation therefore forces an LLM to spend most of its search capacity navigating implementation failures rather than reasoning about solver quality....
-
30
NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning
Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung, Mandana Samiei, Mo Chen
cs.AI · cs.LG
Continual learning (CL) requires models to learn tasks sequentially, yet deep neural networks often suffer from plasticity loss and poor knowledge transfer, which can impede their long-term adaptability. Drawing high-level inspiration from global neuromodulatory mechanisms in the brain, we introduce Neuromodulation and Synchronization (NeuMoSync), a novel architecture that integrates dynamic, neuron-specific modulation into deep neural...
-
31
SafeCommit: Certifying When Memory-Grounded Agents May Safely Act
Mayur Akewar, Ravi Ranjan
cs.AI · cs.CL
Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects. A central failure mode is premature commitment: an agent acts before resolving whether its memory grounding is stale, conflicting, incomplete, or corrupted. We formalize this problem as safe commitment under memory uncertainty and introduce SafeCommit, a risk controlled layer between agent reasoning and external execution. The layer...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.