cs.AI · 2026-07-13 · No. 52
Artificial Intelligence, 2026-07-13.
32 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
32 entries-
01
ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI
Mohadeseh Mollapour, Koorosh Aslansefat, Zeinab Dehghani, Bhupesh Kumar Mishra, Tejal Shah, Zhibao Mian
cs.AI
Concept-based explainable artificial intelligence (AI) can make model reasoning more human-understandable, but concept-level outputs are not automatically trustworthy. We introduce ConceptSMILE, a model-agnostic perturbation-based auditing framework for evaluating the reliability of concept-based explanations. Rather than replacing SMILE, ConceptSMILE extends its perturbation-based logic from feature- or region-level attribution to the...
-
02
Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation
Kaiji Zhou, Ales Leonardis, Yue Feng
cs.AI · cs.CL
Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. However, existing frameworks typically call APIs based on coarse-grained matching between tasks and the functions of expert models or tools, while overlooking critical factors such as performance variability and cost efficiency among functionally similar alternatives. To address this, we propose Agora,...
-
03
TrustX Agent Risk Classification Framework (ARC): Risk-Tiering Internally Created Agentic AI Systems
Hannah M. Liu, Rhea Saxena, Shiv Asthana
cs.AI
The proliferation of agentic AI systems across enterprise and public-sector contexts has outpaced the capacity of general-purpose AI risk frameworks to classify and govern them. In this paper, we introduce the TrustX Agent Risk Classification Framework, a structured, repeatable instrument that can be applied to seven types of agentic AI systems and is grounded in foundational pre-existing AI governance frameworks. At the core of the framework...
-
04
Knowledge Graphs and Explainable AI as Complementary Resources for Urban Mining
Jan Gronewald, Andreas Emrich, Nijat Mehdiyev
cs.AI
Pre-demolition assessment, the regulated audit process at the heart of urban mining, is an information process in which AI support must serve qualified auditors who remain accountable for the decisions taken. The relevant unit of value is not prediction accuracy alone, but the defensibility of the supported decisions: their legibility, plausibility, sourcing, and contestability. Explainable AI techniques and domain knowledge graphs each...
-
05
Beyond Fixed Representations: The Vocabulary and Verifier Gaps in Open-Ended AI
Yuan Cao, Haiqian Yang
cs.AI · cs.LG
Modern AI systems are increasingly being evaluated for their ability to reason, code, prove theorems, use tools, and long-horizon research tasks. These are powerful capabilities, but they share a structural limitation: the representational frame within which the model operates, including its conceptual vocabulary, the space of admissible solutions it can search, and the criteria by which success is evaluated, is typically fixed and supplied...
-
06
SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction
Chongyu Qu, Can Cui, Zhengyi Lu, Junchao Zhu, Tianyuan Yao, Junlin Guo, Juming Xiong, Yanfan Zhu, Yuechen Yang,...
cs.AI
Does every cancer patient truly need a complete diagnostic workup for accurate survival prediction? In multimodal clinical oncology, diagnostic modalities follow a clinically mandated order of escalating burden -- from demographics collected at intake to genomic profiling requiring specialized tissue analysis. Current multimodal survival methods either assume all modalities are available or passively handle missing data, but none actively...
-
07
Shared Selective Persistent Memory for Agentic LLM Systems
Sanjana Pedada, Aditya Dhavala, Neelraj Patil
cs.AI · cs.MA · cs.SE
Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive. Naively persisting entire conversation histories is token-inefficient and counterproductive: irrelevant context degrades generation quality. We introduce shared selective...
-
08
Multimodal Reward Hacking in Reinforcement Learning
Jiayu Yao, Yiwei Wang, Anmeng Zhang, Zhe Sun, Songsong Wang, Lingrui Mei, Yuyao Ge, Shenghua Liu
cs.AI
Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance. This risk is amplified when visual evidence is evaluated by text-only or weakly grounded rewards. We study reward hacking in MLLM RL across safety VQA, chart VQA, and stress-test settings, varying reward design, data ambiguity, model scale (2B-32B), and RL algorithm (GRPO, RLOO,...
-
09
Ceci n'est pas une pipe: AI systems as semantic abstractions
Jade Alglave, Patrick Cousot
cs.AI · cs.PL
An AI system's output is not the fact or world state it appears to describe, but rather an engineered representation. We propose a semantic framework to describe AI systems, to be able to examine the correctness of such representations. To do so, we distinguish what is justified by accepted domain knowledge, what reference sources say, and what the system can currently use. This allows us to give precise definitions to common failures:...
-
10
ProofCouncil: An LLM Agent for Solving Open Mathematical Problems
Johannes Schmitt, Tim Gehrunger, Jasper Dekoninck, Gergely Bérczi, Uri Kreitner, Liam Price, David Holmes
cs.AI
Large language models (LLMs) have shown increasing promise in solving open problems in mathematics. However, their performance can be further improved through agentic workflows tailored to real-world mathematical practice. To this end, we introduce ProofCouncil, a mathematical agent that is designed to tackle open problems using an author-critic architecture. ProofCouncil served as a submission to the second batch of FirstProof, a challenge...
-
11
How Does Bayesian Causal Discovery Fail? Characterising Structural Consequences in Linear Gaussian Networks under Latent Confounding
Debargha Ghosh, Silja Renooij, Anna Kononova
cs.AI
Bayesian causal discovery is widely used for its ability to quantify epistemic uncertainty over directed acyclic graphs (DAGs) through posterior inference. However, its behaviour under latent confounding remains poorly understood, as existing work typically notes that confounding breaks identifiability without characterising how the posterior distribution over DAGs responds. In this work, we analyse posterior behaviour under latent...
-
12
Fictional Worldbuilding: Multi-Agent LLM Collaboration with Hierarchical Context Compression and Iterative Review
Jingbo Chen, He Wang, Wei Yuan, Yuqiao Lai, Zhenyan Lu
cs.AI
Worldbuilding, the construction of coherent fictional worlds, is a foundational task in game design and literary creation. Large Language Models (LLMs) offer new possibilities for automated content generation, but their application to worldbuilding faces three challenges: context explosion that grows linearly with the building process, the tension between creative diversity and content consistency, and the absence of automated quality...
-
13
Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networks
Nuocheng Yang, Sihua Wang, Zihan Chen, Tony Q. S. Quek, Changchuan Yin
cs.AI · cs.MA
Embodied agent teams powered by heterogeneous large language models (LLMs) are being widely deployed in physical artificial intelligence such as smart factories, warehouses, and service robotics. To enable collaboration among such an agent team, efficient coordination mechanisms that operate reliably under limited network resources are required. However, existing heterogeneous LLM-agent coordination frameworks that rely on multi-round...
-
14
LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-Making
Yanzhen Chen, Zihan Xu, Xiaocheng Zhang, Zhiting Fan, Weiqi Zhai, Hongxia Xu, Zuozhu Liu
cs.AI
In this work, we introduce LongMedBench, a real-world EHR-based benchmark for long-horizon clinical decision-making. Prior evaluations of LLM-based medical agents have largely emphasized short-context knowledge QA and tool use. However, real-world medical care is inherently longitudinal, and clinicians must aggregate evidence across repeated visits, tests, and evolving treatments. Therefore, long-horizon interaction is essential for realistic...
-
15
OpenProver: Agentic and Interactive Theorem Proving with Lean 4
Matěj Kripner, Milan Straka
cs.AI · cs.MS
In this system paper, we present OpenProver, an open-source system for LLM-driven automated theorem proving (ATP) with integrated Lean 4 formal verification. OpenProver integrates a Planner-Worker-Verifier architecture inspired by recent ATP agentic systems such as Aletheia. A Planner agent maintains a compact Whiteboard scratchpad and an unbounded Repository of intermediate findings, and decomposes mathematical work into parallel Workers....
-
16
Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents
Izumi Takahara, Teruyasu Mizoguchi
cs.AI · cond-mat.mtrl-sci
Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scientific discovery. Equipped with broad knowledge, flexible reasoning, and tool use, they have the potential to autonomously explore and solve scientific problems by repeatedly proposing hypotheses, testing them, and revising their beliefs in the light of the evidence. In current agents, however, these hypotheses, tests, and belief updates are...
-
17
Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift
Dan C. Hsu, Luke Lu
cs.AI · cs.CL
Deployed LLM agents rely on agentic context, the model-external textual control content assembled by an operational harness. In this work, the mutable component of that context is a persistent system-level instruction that is updated from operational experience while the model, tools, and harness remain fixed. Over long evolution horizons, flat-text maintenance makes verification increasingly difficult as accumulated instructions grow and...
-
18
KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling
Peng Kuang, Haibo Jin, Xiaoyu Han, Yanli Wang, Xiaopeng Yuan, Ye Yu, Kaidi Xu, Haohan Wang
cs.AI
Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly boost the capabilities of LLM-based multi-agent systems. However, existing PRMs are text-based: they re-encode the entire trajectory text from scratch. In long multi-agent rollouts, the scoring cost, growing quadratically with respect to sequence length L, creates a severe computational bottleneck, severely...
-
19
MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation
Runhan Shi, Quan Zhou, Yuqian Xu, Shuai Yang, Xin Wu, Zitong Zhou, Hui Liu, Bin Cha, Zheming Wang, Liya Li, Wei Wei,...
cs.AI · cs.CL · cs.CV
Large language models (LLMs) are increasingly deployed in online medical consultation, yet existing benchmarks remain poorly aligned with real clinical practice. Many rely on synthetic conversations or patient simulators, omit patient-uploaded medical images, or evaluate open-ended clinical responses using multiple-choice or lexical-overlap metrics that poorly reflect clinical quality. We introduce \textbf{MedRealMM}, a large-scale benchmark...
-
20
L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal Reasoning
Tan-Minh Nguyen, Hoang-Trung Nguyen, Huu-Dong Nguyen, Dinh-Truong Do, Thi-Hai-Yen Vuong, Le-Minh Nguyen
cs.AI
While multi-agent debate (MAD) frameworks have shown significant potential in general reasoning, their effectiveness in highly structured, knowledge-heavy legal domains remains under-explored. In this work, we introduce the Legal Multi-Agent Debate (L-MAD) framework to systematically evaluate different debate structures and aggregation methods within Legal Textual Entailment. By assigning distinct expert personas to multiple agents, L-MAD...
-
21
Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Controlling Security Controls
Saroj Gopali, Bipin Chhetri, Deepika Giri, Sima Siami-Namini, Akbar Siami Namin
cs.AI
Cyberattacks on operational technology are increasingly causing costly downtime and physical damage, exposing the limitations of traditional rule-based monitoring in industrial IoT environments. While Large Language Models (LLMs) have strong semantic reasoning abilities to assist in decision support, their hallucinatory nature presents unacceptable safety liabilities for closed-loop control. This paper introduces a neuro-agentic control...
-
22
ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning
Kunbo Zhang, Lei Fu, Zeyu Wang, Zijing Liu, Kejian Tong
cs.AI
We present ARCANA, a collaborative multi agent framework for solving ARC AGI 2 tasks under strict test time and hardware constraints. ARCANA decomposes each task into iterative perception, hypothesis generation, symbolic execution, and reflective refinement. A perceptual grounding agent builds object centric scene graphs from raw grids, a latent program policy proposes diverse DSL programs, a symbolic executor verifies candidates on...
-
23
A Formalization of the Mean-Field Derivation of the Vlasov Equation: AI-Assisted Lean Formalization as a Strategy Game
Joseph K. Miller
cs.AI · cs.LO · math-ph · math.AP
We formalize a research result in the Lean 4 proof assistant by having a mathematician direct an AI system, and frame the activity as a formalization game. The objective is to turn a LaTeX document into Lean. The game is won when the development compiles, contains no sorry, and a machine check shows the target theorems rest on Lean's foundational axioms alone. Reuse is a second check, by a definition we introduce: whether the development...
-
24
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Zongxia Li, Zhongzhi Li, Yucheng Shi, Ruhan Wang, Junyao Yang, Zhichao Liu, Xiyang Wu, Anhao Li, Yue Yu, Ninghao...
cs.AI
AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minutes and are evaluated only by their final outcome. This setup overlooks intermediate progress and partial solutions, yielding sparse reward signals and an incomplete picture of agent capability. We introduce Long-Horizon-Terminal-Bench, a terminal benchmark of 46...
-
25
GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
Maureese Williams, Dymitr Nowicki
cs.AI · cs.LG
Large Language Model (LLM) agents have shown promise in multi-step planning tasks, but existing approaches like LATS (Language Agent Tree Search) and ReAct rely heavily on LLM inference during planning, leading to high computational costs and stochastic behavior. We present \textbf{GATS} (Graph-Augmented Tree Search), a planning framework that combines systematic UCB1-based tree search with a layered world model to eliminate LLM calls during...
-
26
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
Yifan Zhou, Qihao Yang, Yan Li, Donggang Li, Xiru Hu, Hokin Deng, Ziyang Gong, Xuanyi Zhou, Huacan Wang, Xiangchao...
cs.AI
Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benchmarks still say little about whether AI systems can follow this inheritance structure. We present IdeaGene-Bench (IG-Bench), a benchmark for scientific lineage reasoning and lineage-grounded idea generation. IG-Bench is organized around the IdeaGene framework: each...
-
27
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysis
Kristina Schaaff, Quintus Stierstorfer, Valerie Heckel
cs.AI · cs.HC
In this study, we present a large-scale descriptive analysis of the use of an AI-based learning assistant (Syntea) in higher education. Based on objective log data from 77,543 students enrolled in distance studies, we examine usage patterns across gender, age group, study cluster, degree, and study mode. To date, existing research on educational chatbots has largely relied on comparatively small samples and self-reported survey data, while...
-
28
AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding
Siddharth Damodharan, Radhika Gupta, Ali Alshami, Ryan Rabinowitz, Jugal Kalita
cs.AI · cs.CV
Recent advances in Vision-Language Models, Large Language Models, and Multimodal Large Language Models have improved autonomous driving tasks such as scene understanding, decision making, trajectory prediction, and visual question answering. However, evaluating whether these models can reliably reason about safety-critical incidents remains challenging. To address this gap, we present AUTOPILOT-VQA, an incident-centric visual question...
-
29
Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows
Emanuele Quinto, Carlo Andrea Rozzi, Francesco Zanitti
cs.AI · cs.PL · cs.SE
Large language model (LLM) applications increasingly use explicit workflows for tool use, retrieval, branching, checkpointing, and human approval. Existing workflow systems already address many execution concerns. This paper proposes a Lisp-inspired but language-independent conceptual model: symbolic forms, object identity, and live-image thinking are used as explanatory lenses, not implementation commitments. In this model, workflow...
-
30
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
Baha Rababah, Cuneyt Gurcan Akcora, Carson K. Leung
cs.AI
Post-training quantization is widely used to deploy large language models in resource-constrained settings, yet its evaluation relies almost exclusively on accuracy and perplexity. We show that these metrics fail to capture behavioral changes induced by quantization. We introduce correctness agreement, a decision-level metric that measures overlap in correct predictions between a base model and its quantized variants, independent of absolute...
-
31
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
Yifan Wu, Lizhu Zhang, Yuhang Zhou, Mingyi Wang, Bo Peng, Serena Li, Xiangjun Fan, Zhuokai Zhao
cs.AI · cs.CL
In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context window or pushed beyond it, failing to influence decisions when needed. We call this failure mode "behavioral state decay". We study memory as an active intervention...
-
32
SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets
Shilin Ou, Yifan Xu, Luyao Zhang
cs.AI · cs.ET · cs.LG · cs.MA · econ.GN
As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustworthiness. In decentralized energy markets, autonomous agents may improve market utility, but may also exploit invalid physical data, create artificial liquidity, and produce unstable governance decisions. Therefore, we propose SolarChain-Eval, a physics-constrained benchmark for evaluating...
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.