cs.AI · 2026-07-09 · No. 48
Artificial Intelligence, 2026-07-09.
27 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
27 entries-
01
Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety
Yujiao Chen
cs.AI · cs.GT · cs.MA
We introduce institutional red-teaming, an evaluation methodology for testing deployment rules in multi-agent AI: hold the agents, objectives, and task state fixed, vary only one rule, and attribute the resulting change in collective behavior to that rule. We instantiate the methodology in IABench-CA, a consequence-allocation benchmark spanning 228 contexts, five canonical rules, and seven model populations (33,924 games), with a normative...
-
02
SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents
Tianming Sha, Yue Zhao, Lichao Sun, Yushun Dong
cs.AI
Autonomous AI agents can execute complex tasks with limited human review, yet they often lack the grounded operational knowledge to make their outputs not just executable but correct, secure, and maintainable. We introduce SkillCenter, to our knowledge the largest open skill library for agents by total count: 216,938 structured skills across 24 domain bundles. A SkillGate-filtered pipeline contributes 114,565 source-grounded skills from...
-
03
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
Mingguang Chen, Licheng Wang, Bo Qu
cs.AI
AI systems increasingly participate in their own improvement: revising their outputs, adapting their own harnesses during deployment, training on data they generate, and, increasingly, conducting AI research itself. This literature is described under a vocabulary ("self-refine," "self-reward," "self-play," "self-evolve") that conflates fundamentally different ambitions. We survey 1,250 arXiv papers (2024-2026) along two axes: what the system...
-
04
RL Post-Training Builds Compositional Reasoning Strategies
Azwar Abdulsalam, Nishil Patel, Andrew Saxe
cs.AI · cs.CL
Does RL post-training merely amplify primitive skills already latent in a base model, or can it compose primitive skills into new higher-level strategies? We study this question in a fully observable rewrite-grammar environment where the pretraining distribution is known and every generated rewrite can be audited. A Transformer is pretrained on primitive symbol-rewrite chains and post-trained on a Trace-based reasoning task with only a binary...
-
05
Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows
Wei-Jung Huang
cs.AI
Product data scientists often ask LLM-based agents to help with recurring execution tasks such as cleaning data, writing SQL, choosing statistical tests, and formatting results. Reusable skill files are meant to avoid prompting from scratch by packaging guidance for a task family. Expert-written skills can encode high-quality guidance, but writing and maintaining them across many data-science task families creates a manual bottleneck. We ask...
-
06
Search, Fail, Recover: A Training Framework for Correction-Aware Reasoning
Dmitry Beresnev, Vladimir Makharev, Roman Khalikov, Ivan Oseledets, Petr Anokhin
cs.AI
Many reasoning tasks are not well described by a single left-to-right chain: a solver may need to pursue a plausible branch, observe delayed failure, and return to the latest prefix that can still be completed. We introduce Pyligent, a training and inference framework inspired by the Diligent Learner formulation that represents reasoning as validated search over partial solution chains. A task validator labels generated continuations and...
-
07
SpaCellAgent: A Self-Evolving LLM-Based Multi-Agent Framework for Trajectory Analysis
Songhan Wang, Haoang Chi, He Li, Zhiheng Zhang, Jiayan Yuan, Cheems Wang, Hao Peng, Xinwang Liu, Wenjing Yang
cs.AI
Spatial and Single-cell transcriptomics are transformative in deciphering cellular dynamics. As the fundamental paradigm for reconstructing cell developmental paths, trajectory inference (TI) is critical. However, existing methods require extensive manual intervention and proficiency in heterogeneous tools, posing a significant barrier to efficient TI analysis. To bridge this gap, we propose SpaCellAgent, an autonomous large language model...
-
08
The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
Xing Zhang, Yanwei Cui, Guanghui Wang, Ziyuan Li, Wei Qiu, Bing Zhu, Peiyang He
cs.AI · cs.CL · cs.CR
A self-evolving agent retires its bad skills by watching them fail, so what happens when the judge cannot see the failures? Skill retirement is the structural constraint that keeps a growing library from drifting below the no-skill baseline, but its guarantee assumes an unbiased reward, which is false for the LLM judges that reference-free tasks force upon us. We show that a biased judge does not merely add noise; it \emph{silently switches...
-
09
InductWave: Inductive Multi-Hop Logical Query Answering on Knowledge Graphs
Mayank Kharbanda, Michael Cochez, Rajiv Ratn Shah, Raghava Mutharaju
cs.AI · cs.IR
Logical Multi-Hop Query Answering over Knowledge Graphs (KGs) can be formulated as querying, with an implicit completeness assumption. Current works mainly focus on Existential First Order Logic (EFO) queries. These EFO queries contain conjunction, disjunction, and negation operators. Most existing works employ transductive reasoning, meaning they are not capable of reasoning over entities unseen during training. In the real world, there is a...
-
10
Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents
Vikas Reddy, Sumanth Reddy Challaram, Abhishek Basu
cs.AI · cs.CR
Tool-using LLM agents can violate the very policies they are deployed to enforce while appearing to complete the task successfully. In policy-permissive environments, a tool may execute any well-formed call even when the corresponding state transition is forbidden by domain policy. The result is a silent wrong state (a booking cancelled, a passenger count changed, a claim acted on without verification) that neither the tool nor the agent's...
-
11
Agentic Data Environments
Elaine Ang, Chenxi Huang, Georgios Liargkovas, Jerry Liu, Jinhui Liu, Nikos Pagonas, Charlie Summers, Haonan Wang,...
cs.AI · cs.DB
Autonomous agents promise substantial gains in speed, scale, and labor efficiency, but their failures can impose abrupt and often irreversible costs. The central challenge for agentic automation is therefore to increase the benefits of automation while bounding the consequences of failure. While databases remain central to modern computing, agents operate over a broader data environment spanning files, APIs, applications, and system state. In...
-
12
MIRA-Math: A Benchmark for Minimal Information Requesting and Mathematical Reasoning
Charbel Al Bateh, Samer Saab
cs.AI
Mathematical reasoning benchmarks typically provide all facts needed to solve each problem, while interactive benchmarks often mix reasoning with tools, retrieval, and long-horizon dialogue. We introduce MIRA-Math, a benchmark for a narrower diagnostic capability: solving mathematical problems whose full latent state has a unique answer, but whose solver-facing view is missing exactly one necessary atomic fact. The solver must request the...
-
13
Physics-Audited Agentic Discovery in Scientific Machine Learning
Diab W. Abueidda, Bilal Ahmed, Panos Pantidis, Mostafa E. Mobasher
cs.AI · cs.LG
In agentic scientific machine learning (SciML), large language model (LLM) agents can discover surrogate models and select one by an automated score, typically an error metric. A low error, however, does not establish that the predicted fields satisfy the physics that matter for mechanics, such as boundary conditions, superposition, stiffness scaling, or causality. We introduce Physics-Audited Agentic SciML (PA-SciML), a verification-first...
-
14
From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents
Haipeng Ding, Yuexiang Xie, Zhewei Wei, Yaliang Li, Bolin Ding
cs.AI · cs.CL · cs.MA
Tool utilization enables Large Language Model (LLM) agents to interact with the real world and resolve complex tasks. However, existing agent frameworks predominantly rely on static toolsets composed of granular atomic actions (e.g., basic file I/O or single-turn search), which forces agents to reinvent low-level logic for every recurring workflow, leading to increased reasoning overhead and failure rates. In this study, we propose that...
-
15
Reasoning Consistency Scanning: A Framework for Auditing Chain-of-Thought Validity in AI Safety Evaluations
Silvia Santano
cs.AI
Prior work has shown that chain-of-thought (CoT) reasoning is often unfaithful: a model's stated reasoning does not reliably reflect the process that produced its output. Detecting unfaithfulness, though, requires controlled experimental interventions, which cannot be applied to evaluation transcripts after the fact. We turn instead to a more tractable question that has received less attention: whether the stated reasoning is logically...
-
16
Does AI Understand Imaging? A Systematic Benchmark of Agentic AI for Computational Imaging Tasks
Ethan Chung, Chuanjun Zheng, Jasper Tan, Jingxi Li, Haopeng Zhang, Huaijin Chen
cs.AI
Vision-language models (VLMs) and agentic AI have shown strong performance on semantic visual tasks, but it remains unclear whether they can handle the physics and inverse problems that underlie computational imaging. We present ImagingBench, a benchmark of 20 computational imaging tasks spanning five categories: ray and wave optics, image signal processing, inverse reconstruction, computational sensing, and calibration. ImagingBench...
-
17
Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety
Lifei Liu, Haoran Yu, Xiaochong Jiang, Su Wang, Pin Qian, Yihang Chen
cs.AI · cs.CR · cs.MA
Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single "pipeline effect." We argue that this aggregate is difficult to interpret because it conflates three mechanisms: harmful intent may be reframed as plausible operational work, the planner may refuse or transform the request, and the executor may act under delegation prompts implying prior approval....
-
18
Measuring Intelligence Beyond Human Scale
Jerry Han, Rafael Moschopoulos, Ella Colby, Vishrut Goyal, Andrew Tu, Kia Ghods, Mark Braverman, Elad Hazan
cs.AI
How can we measure intelligence beyond human capability? Human-authored benchmarks saturate, and above human capability, examiners may not know which tasks are both hard and verifiable. We argue that this difficulty is inherent to absolute-scale evaluation and propose a new paradigm based on relative measurement in which models generate public challenges that separate other systems. Aggregating these outcomes yields an adversarial...
-
19
Learning social norms enhances compatibility in dynamic human-AI coordination
Yi Yang, Siyuan Liu, Xin Gao, Huamu Sun, Chao Liu, Qing Zhou, Bingbing Nie
cs.AI · cs.HC
Humans continuously coordinate with others in dynamic interactions, often through implicit, hard-to-quantify social norms that act as shared tacit expectations among interacting agents. As AI agents, including large language models (LLMs), become embedded in daily life, they increasingly participate in such interactions and reshape social interaction structures. Yet they often fail to coordinate with humans in an effective, considerate, and...
-
20
Large Behavior Model: A Promptable Digital Twin of the Retail Customer
Wachiravit Modecrua, Krittin Pachtrachai, Touchapon Kraisingkorn
cs.AI
Customer behavior modeling underpins recommendation, marketing, and decision support, yet existing approaches either optimize predictive accuracy without explaining decisions or simulate users without grounding them in real behavioral data. We present the Large Behavioral Model (LBM) that learns customer decision making directly from large-scale retail transactions through a unified Person-Environment formulation. Customer state is...
-
21
Grounding Spatial Relations in a Compact World Model: Instruction Leakage and a Goal-Free Dynamics Fix
Yufeng Wang, Lu Wei, Haibin Ling
cs.AI
Compact world models that condition on a language goal promise to ground relations such as ``put the red block left of the blue block'' using a sparse set of explicit \emph{reference anchors}. We ask when such references actually ground a relation, and identify a trap: a goal-conditioned predictor reaches a striking $0.90$ relation-readout accuracy, yet this is \emph{instruction transcription}, not perception. Withholding the goal collapses...
-
22
The Harness Effect: How Orchestration Design Sets the Token Economics of Enterprise Agentic AI
Muayad Sayed Ali, Aliaksandra Novik, Anji Boddupally, Artem Yavorskyi, Chris Nickerson, Daniel Rica, Emily...
cs.AI
Agentic AI development today runs on token maxing: buying capability with tokens -- longer reasoning traces, more turns, wider tool payloads, bigger replayed contexts -- so tokens per task grow faster than task value. Falling per-token prices mask the pattern; total spend rises anyway. We argue the decisive lever against token maxing is the harness: the orchestration layer that assembles context, exposes tools, sequences turns, delegates...
-
23
Evaluating SageMath-Augmented LLM Agents for Computational and Experimental Mathematics
Pavel Snopov, German Magai
cs.AI
Recent advances in AI for Mathematics have focused largely on autoformalization and theorem proving, leaving the role of Computer Algebra Systems (CAS) in agentic LLM workflows underexplored. We propose a ReAct-style agentic setup that combines LLM reasoning with verifiable feedback from SageMath, together with Context7 for the up-to-date documentation. We evaluate this agentic setup across frontier models for solving research-level...
-
24
Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1
Kabir Moghe, Peter Chin
cs.AI
Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary search, exhaustive sampling, extended chain-of-thought), or benchmark-specific training in which small models are fine-tuned on ARC data, often with task-specialized architectures. We study a third regime: an open-weight model in non-thinking mode (DeepSeek V3.2) under a strict budget, with no...
-
25
QANTIS: Hardware-Calibrated Sequential POMDP Belief Updates on IBM Heron
Bayram Yuksel Eker, Suayb S. Arslan, Ozgur Nazli, Mustafa Serhat Demirgil, Furkan Deligoz
cs.AI · quant-ph
Autonomous systems under partial observability act on beliefs, not raw sensor events. QANTIS treats the quantum processor as a calibrated belief-update service in that loop: it receives a prior and an observation model, estimates the rare-event evidence term, and returns an ordinary posterior to a classical planner. This paper asks whether that service can be reused across a sequential Tiger POMDP horizon on present IBM Heron hardware without...
-
26
LLM-powered reasoning in agent-based modeling
Sifat Afroj Moon, Dakotah Maguire, Adam Spannaus, Joe Tuccillo, Maksudul Alam, Sudip K. Seal, John Gounley, Heidi Hanson
cs.AI · cs.MA
Agent-based modeling (ABM) has the capability to model millions of individuals and their interactions, which is useful for policy making. However, ABMs have traditionally relied on static prior, which prevents the models from adapting to real-time changes. Our research provides a novel approach to addressing this information gap. Large language models (LLMs) offer new opportunities to predict human decision-making. Here, we introduce a...
-
27
When Does In-Context Search Help? A Sampling-Complexity Theory of Reflection-Driven Reasoning
Yotam Wolf, Noam Wies, Amnon Shashua
cs.AI · cs.CL
Training large language models (LLMs) with extended reasoning has enabled in-context search, in which models iteratively generate, critique, and revise solution attempts. We provide a theoretical analysis of in-context search by modeling it as approximate inference over reasoning traces, where the base model defines a prior and self-reflection provides feedback for posterior updates, and study the resulting inference-time sampling complexity...
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.