cs.AI · 2026-06-08 · No. 17
Artificial Intelligence, 2026-06-08.
21 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
21 entries-
01
How AI Agents Reshape Knowledge Work: Autonomy, Efficiency, and Scope
Jeremy Yang, Kate Zyskowski, Noah Yonack, Jerry Ma
cs.AI · econ.GN
Frontier AI systems are bridging the gap between intelligence and utility by shifting from conversational assistants to autonomous agents that execute tasks end to end. Using production data from Perplexity's Search and Computer products, we study this transition by examining how AI agents accelerate and reshape knowledge work. Three key empirical findings emerge. First, using sessions with near-identical initial query pairs as natural...
-
02
Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle
Jiayu Wang, Weijiang Lv, Bowen Fu, Jing Fu, Jiayi Song, Lingyu Zhang, Lanxuan Xue, Luodi Chen, Zepeng Xin, Kaiyu Li,...
cs.AI
As foundation models advance and agent scaffolding becomes increasingly sophisticated, agents have demonstrated remarkable proficiency in complex, long-horizon coding tasks and even autonomous experiment execution. Despite their evolution from research assistants into autonomous research agents, these systems still exhibit significant limitations in field sensitivity, research ethics, and nuanced scientific judgment. Consequently, frontier...
-
03
Online Pandora's Box for Contextual LLM Cascading
Alexandre Belloni, Yan Chen, Yehua Wei
cs.AI · cs.LG · econ.EM · stat.ML
Motivated by Large Language Model (LLM) cascading, we propose an online contextual Pandora's Box model for adaptively querying and selecting LLM APIs. In each period, a decision-maker observes a request context and faces a two-phase decision problem. In the query phase, the decision-maker sequentially queries APIs, where each query reveals a generated output and the decision-maker incurs an (output-dependent) cost. In the selection phase, the...
-
04
Off-Policy Evaluation with Strategic Agents via Local Disclosure
Kiet Q. H. Vo, Abbavaram Gowtham Reddy, Julian Rodemann, Siu Lun Chau, Krikamol Muandet
cs.AI
We study off-policy evaluation (OPE) under strategic behavior where decision subjects (or agents) respond to a decision maker's policy by strategically modifying their covariates. Such behavior induces a policy-dependent covariate shift, breaking the standard assumption in existing methods that covariates are exogenous to the policy. Related work addresses this challenge by imposing strong assumptions such as repeated interactions or full...
-
05
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning
Lingyong Yan, Can Xu, Yukun Zhao, Wenxuan Li, Qingyang Chen, Jiulong Wu, Wenli Song, Xiangnan Li, Weixian Shi, Yiqun...
cs.AI
Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks, demanding systems that can iteratively frame problems, acquire evidence, verify sources, and synthesize long-form reports. In practice, however, current DR systems are constrained by four interrelated limitations: long-horizon planning over an underspecified scope, the bottleneck of decomposing and scheduling such tasks within a single...
-
06
TOPSIS-RAD: Ranking According to Desires
Leonardo Fernandes Costa, Helder Gomes Costa, Diogo Lima, Brunno Rodrigues
cs.AI · econ.EM
Traditional TOPSIS derives its reference points -- the Positive Ideal Solution ($PIS$) and Negative Ideal Solution ($NIS$) -- from the observed alternative set, making rankings susceptible to misalignment with decision-maker (DM) requirements, sensitivity to outlier performances, and rank reversal. This paper proposes TOPSIS-RAD, which addresses these issues by incorporating two arrays of DM-defined reference levels. Vetoed Performance Levels...
-
07
Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models
Dewi Gould, Francis Rhys Ward, Anders Cairns Woodruff, Rauno Arike, Josh Hills, Alex Serrano, Ida Caspary, Jason...
cs.AI
Many efforts to ensure frontier AI models are safe rely on monitoring their chain-of-thought (CoT) reasoning. If models become able to perform sufficiently complex reasoning internally, without explicit thinking tokens, this would undermine such oversight. We measure how well frontier models reason without CoT across a suite of over 30,000 questions spanning 43 benchmarks in domains including math, coding, puzzles, causality, theory-of-mind,...
-
08
Beyond Post-hoc Explanation: Toward Glassbox AI via Probabilistic Mediation
Manuele Leonelli
cs.AI
Large language models are rapidly becoming infrastructural components in high-stakes institutional settings, including public administration, legal reasoning, and healthcare, where opacity is not merely inconvenient but institutionally and legally untenable. Existing approaches to explainability are predominantly post-hoc, offering unstable, non-contestable accounts that have no formal relationship to the reasoning process that produced the...
-
09
DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling
Tengyao Tu, Yulin Li, Hui-Ling Zhen, Libo Qin, Zhoujun Wei, Jinghua Piao, Zhuotao Tian, Yong Li, Min Zhang
cs.AI
Recent advances in Large Reasoning Models (LRMs) demonstrate remarkable performance improvements by iteratively reflecting, exploring, and executing complex tasks, yet suffer from inefficiencies due to redundant reasoning, known as "overthinking". Existing methods to mitigate this issue either rely on static difficulty estimates or require task-specific training, and thus fail to adapt to the dynamic complexity during reasoning. In this work,...
-
10
Front-to-Attractors: Modifying the Front-to-Front Heuristic in Bidirectional Search
Alvin Zou, Muhammad Suhail Saleem, Maxim Likhachev
cs.AI
Heuristics play a central role in the performance of bidirectional search algorithms, which commonly rely on two main classes. Front-to-end (F2E) heuristics estimate the distance from a state s to the target of the search (the goal for forward search or the start for backward search). In contrast, front-to-front (F2F) heuristics estimate the distance from s to the opposite search frontier using a pairwise function h(s, s'), where s' ranges...
-
11
Hierarchical Semantic-Constrained Heterogeneous Graph for Audio-Visual Event Localization
Zhe Yang, Ruyi Zhang, Hongtao Chen, Wenrui Li, Hengyu Man, Wangmeng Zuo, Xiaopeng Fan
cs.AI · cs.CV
Open-vocabulary audio-visual event localization (OV-AVEL) jointly models audio-visual cues to recognize and temporally localize events, including categories unseen during training. Existing methods primarily learn joint audio-visual representations in Euclidean space, but still face two significant challenges. First, the lack of supervision signals for unseen categories makes it difficult to maintain audio-visual consistency across multiple...
-
12
StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents
Haojie Hao, Longkun Hao, Yihang Lou, Yan Bai, Zhenyang Li, Zhichao Yang, Dongshuo Huang, Hongyu Lin, Lanqing Hong,...
cs.AI
Reinforcement Learning (RL) has become a promising approach for improving GUI Agents in long-horizon, stochastic digital environments, but trajectory-level success feedback is too sparse to provide reliable credit assignment for intermediate exploration steps. To mitigate this issue, recent studies introduce Process Reward Models (PRMs), which provide finer-grained training feedback through global milestone verification or local step-level...
-
13
The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective
Xiaoou Liu, Tiejin Chen, Weibo Li, Xiyang Hu, Hua Wei
cs.AI · cs.CL · cs.ET
Foundation model agents are increasingly deployed for real-world decision-making, but suffer from the sim-to-real gap. While robotics and classical control have mature frameworks to address this gap, the foundation model community is treating agent robustness as an entirely novel phenomenon. Our paper proposes formalizing the foundation model agent evaluation and training gap as a classical sim-to-real problem structured entirely around the...
-
14
Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization
Shizhe Xiang, Ke An, Wenlong Yu, Yue Liu, Jian Luan, Pei Fu, Qilong Wang
cs.AI
Recent post-training methods, particularly Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced the reasoning ability of Large Vision-Language Models (LVLMs). However, the sparse nature of verifiable rewards provides little token-level supervision for failed rollouts, often leading to inefficient exploration in complex multimodal reasoning tasks. Although policy distillation can offer dense guidance, external...
-
15
Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning
Yijin Zhou, Linqian Zeng, Xiaoya Lu, Wenyuan Xie, Dongrui Liu, Junchi Yan, Jing Shao
cs.AI
Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct responses, which may accumulate errors throughout multi-step interactions. Existing approaches mainly improve these behaviors through inference-time correction or coarse-grained reward signals based on decision outcomes and structured checklists, leaving the uncertainty characteristics of agent...
-
16
Accounting for Context: Shaping Moral Credences for Value Alignment
Jazon Szabo, Sanjay Modgil
cs.AI
Ensuring that agent behaviours are aligned with human moral values inevitably raises the problem of how to account for the plurality of moral perspectives that societies -- and even individuals -- typically adopt. Work on moral uncertainty proposes mechanisms to fairly and democratically aggregate evaluations of actions across different moral theories. However, this paper argues that one needs to account for contextual factors when...
-
17
Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces
Laura Wynter, Nirvik Sahoo, Paul Griffin
cs.AI
Large language models (LLMs) now solve a wide range of expert-level exams at or above human level, yet remain brittle on specialised, evidence-intensive domains such as law. On these tasks, errors arise not only from gaps in world knowledge but also from subtle distinctions between pieces of evidence and inconsistent use of supporting evidence. The most common aggregator over sampled chain-of-thought (CoT) traces, majority vote, returns the...
-
18
Declarative Skills for AI Agents in Knowledge-Grounded Tool-Use Workflows
M. Danish Lim, I. Danial Bin Sharudin, Wen Han Chen, Cedric Lim, Laura Wynter
cs.AI · cs.SE
We study orchestration mechanisms for tool-using AI agents in realistic customer-service workflows over an unstructured knowledge base. We argue that declarative agents -- AI agents equipped with natural-language skill files appended to the system prompt -- are an effective orchestration paradigm. Concretely, we compare (i) a DeclarativeAgent that reads three domain-specific skill files at inference time and decides its own control flow, (ii)...
-
19
Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition
Yuyang Zhang, Xinyuan Han, Xudong Jiang, Run Wang
cs.AI
Large language model agents increasingly rely on Skills to encode procedural knowledge, yet high-quality Skills remain costly to hand-write. This paper studies automatic Skill construction from heterogeneous interaction evidence, including demonstrations, agent trajectories, tool traces, and execution logs. We argue that trace-to-skill construction is not simple summarization tasks, because traces are fragmented, redundant, and may miss rare...
-
20
Evidence-Based Intelligent Diagnostic and Therapeutic Visualization System with Large Language Models: Multi-Turn Interaction and Multimodal Treatment Plan Generation
Yunhan Wang, Yuda Wang, Zhiying Tu, Mingqiang Song, Li Song, Kun Li, Dianhui Chu, Bolin Zhang
cs.AI
Aim: Existing AI-assisted traditional Chinese medicine diagnostic tools suffer from opaque reasoning processes, passive interaction, and limited treatment plan presentation. This study proposes a knowledge-enhanced visual diagnostic system to improve the transparency and interpretability of syndrome differentiation and treatment. Methods: The system is built upon a Neo4j knowledge graph comprising 241 syndromes, 1,263 symptoms, and 2,485...
-
21
AdMem: Advanced Memory for Task-solving Agents
Runzhe Wang, Huilin Lu, Shengjie Liu, Li Dong, Jason Zhu
cs.AI
Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusing knowledge. Prior memory approaches aim to resolve the situation, but mainly focus on storing factual information. Recent work on procedural memory improves task reuse, yet often reduces to replaying past successes without addressing failure cases or online scalability. We introduce a unified...
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.