cs.AI · 2026-06-15 · No. 24
Artificial Intelligence, 2026-06-15.
26 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
26 entries-
01
Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
Shikun Liu, Mufei Li, Dongqi Fu, Haoyu Wang, Yinglong Xia, Hong Li, Hong Yan, Pan Li
cs.AI · cs.CL
Large language models increasingly serve as execution engines for agentic systems, yet they still consume context through a sequential text interface. This creates a mismatch with modern structured agent workflows, in which independent branches explore subtasks, retrieve evidence, or generate candidate solutions before a final synthesis step. Existing systems typically merge these branches by concatenating their textual outputs, which...
-
02
Abstracting Cross-Domain Action Sequences into Interpretable Workflows
Gaurav Verma, Scott Counts
cs.AI · cs.CL · cs.LG
Sequential or time-stamped interaction logs provide objective records of digital application usage, yet their granularity and noise often obscure meaningful insights into people's work. Such insights are essential for improving digital products in ways grounded in real-world user interactions. Prior research has applied deep learning models to cluster user actions into high-level activities, but these approaches are highly sensitive to noise...
-
03
A Temporal Planning Framework for Disruption Aware Dynamic Route Optimization in Heterogeneous Railway Systems
Pollob Chandra Ray, Sabah Binte Noor, Fazlul Hasan Siddiqui
cs.AI
Efficient route optimization play a vital role in ensuring both safety and punctuality in railway operations. It is very crucial particularly in heterogeneous multi-gauge railway networks with varying train speed, stopping pattern, infrastructure compatibility constraints increase coordination complexity. In single-track systems these challenges are further intensify due to all trains to share the same track and requires frequent track...
-
04
VISTA: View-Consistent Self-Verified Training for GUI Grounding
Xinyu Qiu, Yunzhu Zhang, Heng Jia, Shuheng Shen, Changhua Meng, Linchao Zhu
cs.AI
When applying Group Relative Policy Optimization (GRPO) for GUI Grounding, rollouts are sampled from a single screenshot view; groups often become either all failures on difficult instances or all successes on easy ones, yielding no useful relative advantage. We propose VISTA (View-Consistent Self-Verified Training), a GRPO-based training framework that constructs each comparison group from multiple target-preserving views of the same GUI...
-
05
StreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistance
Guanming Liu, Yuqi Ren, Hansu Gu, Peng Zhang, Weihang Wang, Jiahao Liu, Ning Gu, Tun Lu
cs.AI
A central role of personal-agent memory is to turn stored information and prior interactions into future-oriented assistance. In daily use, useful cues come from what the agent observes and how the user interacts with the agent, and the agent must carry them forward from the current request to similar future tasks. Existing memory benchmarks usually test dialogue recall or task improvement in isolation, leaving the trajectory from streaming...
-
06
Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results
Jan Batzner, Sree Harsha Nelaturu, Anastassia Kornilova, Jon Crall, Tommaso Cerruti, Yanan Long, Yifan Mai, Sanchit...
cs.AI · cs.CL · cs.CY
AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical...
-
07
Dense Coordinate-List Fine-Tuning Induces a Controllable Interference Surface in Vision-Language Models
Chenyu Zhou, Qiliang Jiang, Boguang Pan
cs.AI
Fine-tuning vision-language models to emit dense coordinate lists improves visual grounding but also changes how models serialize, repeat, and terminate structured outputs. We study this behavior as a generation and control surface. In Gemma 4 12B, high-capacity q/k/v/o LoRA raises class-aware F1@0.3 from 0.007 to 0.448 while inducing repeated-tail pressure (duplicate rate 0.080, max repeat 23). A q/v rank sweep keeps max repeat at 21-22...
-
08
From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI
Yongheng Zhang, Ziang Liu, Jiaxuan Zhu, Shuai Wang, Xiangqi Chen, Haojing Huang, Jiayi Kuang, Siyu Chen, Ao Shen,...
cs.AI
Large Language Models (LLMs) are undergoing a fundamental transformation from conversational generators into integrated AI systems capable of reasoning, action, memory, and self-improvement. We conceptualize this transition as a shift from Chatbot to Digital Colleague: from conversational answers to persistent work. We organize this transition along two tightly coupled dimensions. First, at the cognitive core level, LLMs are advancing from...
-
09
When the Tool Decides: LLM Agents Defer Blindly to Graph Neural Network Tools, and Stronger Backbones Defer More
Zhongyuan Wang, Pratyusha Vemuri
cs.AI · cs.LG
A growing line of work equips large language model (LLM) agents with graph neural networks (GNNs) as callable tools, assuming the agent exercises judgment over when and how much to rely on such a tool. We test this directly. We expose a frozen GNN to a ReAct-style LLM agent as an explicit tool and measure, on node classification over a text-attributed graph (ogbn-arxiv, replicated on WikiCS), whether the agent uses the tool or merely obeys...
-
10
GitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Merge
Pavan C Shekar, Abhishek H S, Aswanth Krishnan
cs.AI · cs.CL · cs.LG
Large language model (LLM) reasoning is ephemeral: chains of thought vanish with the context window, pruned search branches leave no record, and memory buffers cannot be diffed, merged, or audited. Every other complex software process (code, infrastructure, data, experiments) is version-controlled; reasoning is not. We introduce GitOfThoughts, which stores an agent's reasoning tree as a git repository: every scored thought is a commit, scores...
-
11
Causal Object-Centric Models for Planning with Monte Carlo Tree Search
Rodion Vakhitov, Leonid Ugadiarov, Alexey Skrynnik, Aleksandr Panov
cs.AI · cs.LG · cs.RO
We introduce COMET (Causal Object-centric Model for Efficient Tree search), a model-based reinforcement learning algorithm that performs Monte Carlo Tree Search in a slot-structured latent space. COMET pairs a frozen unsupervised object-centric encoder with a transformer-based world model, in which actions are bound to objects through a novel action-slot fusion mechanism that is used in slot transition prediction. Policy and value heads use...
-
12
CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement Learning
Ayoub Belouadah, Sylvain Kubler, Yves Le Traon
cs.AI
Safe reinforcement learning (Safe RL) aims to maximize expected return while satisfying safety constraints, typically modeled as Constrained Markov Decision Processes (CMDPs). While primal-dual methods scale well to deep RL, they often suffer from delayed constraint correction, leading to oscillatory behavior and prolonged safety violations. In this paper, we propose Constraint-Sensitive Policy Optimization (CSPO), a first-order primal-dual...
-
13
Communication Policy Evolution for Proactive LLM Agents
Xinbei Ma, Jiyang Qiu, Yao Yao, Zheng Wu, Yijie Lu, Xiangmou Qu, Jiaxin Yin, Xingyu Lou, Jun Wang, Weiwen Liu,...
cs.AI
LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferences further limit information exchange. To investigate how agents should communicate across modalities, this paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments,...
-
14
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
Tingyang Chen, Shuo Lu, Kang Zhao, Weicheng Meng, Hanlin Teng, Tianhao Li, Chao Li, Xule Liu, Jian Liang, Zhizhong...
cs.AI
AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces produced during execution are rarely distilled back into systematic improvement. We introduce HarnessX, a foundry for composable,...
-
15
AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties
Yifan Jiang, Meige Yang, Zitong Li, Jay Pujara
cs.AI
Affordance reasoning, the inference of an object's action possibilities from its physical properties (e.g., shape and material), is fundamental to human physical understanding and increasingly critical for Large Language Models (LLMs). However, existing affordance benchmarks largely expose explicit object identities in the evaluation setup, allowing models to rely on memorized object-affordance mappings rather than reasoning over physical...
-
16
SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing
Haowen Gao, Haoran Chen, Can Wang, Shasha Guo, Liang Pang, Zhaoyang Liu, Huawei Shen, Xueqi Cheng
cs.AI
Agent skills are structured procedural packages that guide frozen LLM agents in specialized workflows. Skills rarely remain sufficient after deployment: edge cases, API changes, and deployment constraints become visible only through use, making skill evolution a practical necessity. Existing methods depend on privileged feedback such as held-out validation scores, hidden test outcomes, or environment rewards -- signals often unavailable when...
-
17
Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL
Yinglun Zhu
cs.AI · cs.LG
LLMs are increasingly deployed as agents that interact with external environments and observe feedback such as execution results, error messages, and tool outputs. A well-functioning agent should be able to leverage this feedback to accurately assess its own performance. Yet we find a persistent reflection gap: LLM agents tend to mis-assess their own outputs after observing concrete environment feedback -- even for questions they correctly...
-
18
When Should Agent Trust Be Conditional? Characterizing and Attacking Skill-Conditional Reputation in Agent Swarms
Yihan Xia, Taotao Wang
cs.AI · cs.LG
Open platforms increasingly route tasks among heterogeneous LLM agents--differing in base model, scaffold, and tool stack--whose competence varies sharply by skill: an agent excellent at one skill may be useless at another. The standard reputation approach summarizes each agent by a single global trust score, but that scalar is the wrong object here, because routing every task to the globally most-trusted agent leaves the value of...
-
19
VeriGeo: Controllable Geometry Question Generation with Numerical and Analytical Verification
Xiaoxian Duan, Zequn Liu, Yingce Xia
cs.AI
Geometry problem generation is useful for AI-assisted education and multimodal mathematical reasoning, but reliable synthesis remains difficult because the problem statement, diagram, constraints, and solution should be mutually consistent. Existing methods often trade off controllability and reliability: seed-based rewriting is flexible but weakly verifiable, whereas diagram-first construction improves validity but is less suited to...
-
20
FactoryLLM: A Safe and Open-Source AI Playground for Evaluating LLMs in Smart Factories
Yash Pulse, Yong-Bin Kang, Abhik Banerjee, Abdur Forkan, Prem Prakash Jayaraman
cs.AI
Fault diagnostics and recovery in smart factories is challenging because critical information is dispersed across manuals of multiple machines which are interconnected through the manufacturing process. Large Language Models (LLMs) can provide a promising approach. In this paper, we propose FactoryLLM, a safe and open-source AI playground designed for evaluating different LLM-based retrieval-augmented generation (RAG) models by analysing...
-
21
Applicability Condition Extraction for Therapeutic Drug-Disease Relations
Guanting Luo, Noriki Nishida, Yuji Matsumoto, Yuki Arase
cs.AI
Identifying conditions that a certain drug takes therapeutic effect on a target disease is crucial for clinical decision-making support. However, most existing biomedical information extraction methods have focused on identifying only relations between drugs and diseases, while largely overlooking the context-specific conditions where such relations can apply. To address this problem, we introduce the task of applicability condition...
-
22
Formalizing Numerical Analysis: An Agent Pipeline and Quality Audit Beyond Kernel Acceptance
Theodore Meek, Siyuan Ge, Di Qiu Xiang, Simon Chess, Vasily Ilin
cs.AI
Recent work has demonstrated that coding agents can formalize entire advanced mathematics textbooks in Lean 4, yet existing efforts concentrate on branches of mathematics already well-represented in mathlib and measure success solely through kernel acceptance. We address both limitations by applying a coding agent to formalize Numerical Methods for Ordinary Differential Equations, a textbook in numerical analysis that is largely absent from...
-
23
Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization
Hexuan Yu, Chaoyu Zhang, Heng Jin, Shanghao Shi, Ning Zhang, Y. Thomas Hou, Wenjing Lou
cs.AI
Modern LLM-powered autonomous agents increasingly rely on rich user interface (UI) state observations to achieve reliable action grounding in complex digital environments. However, many deployments transmit the full UI state to remote inference servers even when most elements are irrelevant to the current task, which can leak sensitive but unnecessary context such as authentication codes, private notifications, and background application...
-
24
Adversarial Concept Search: Predicting Compositional Errors From Feature Geometry
Jennifer Meng Lu, Ruochen Zhang, Isabelle Lee, David Alvarez-Melis, Ellie Pavlick, Naomi Saphra
cs.AI
Humans cannot always intuit what scenarios are most challenging to LLMs. Hoping to capture challenging edge cases, developers either design problems to be difficult for humans or curate extensive benchmarks. What if we could instead anticipate which scenarios a model will fail on? In this paper, we use an LLM's representational geometry to predict which concept combinations it will fail on. We attribute this compositional failure to...
-
25
Sorries Are Not the Hard Part: An Expert-Review Case Study of a Semi-Autonomous Formalization
Vasily Ilin, Brian Nugent
cs.AI · math.AG
Large language models can often close proof gaps in interactive theorem provers, but a verified theorem is not the same thing as a reusable library contribution. We study this distinction through a detailed case study: a semi-autonomous formalization of Grothendieck's vanishing theorem. The initial version compiles with no sorries, but an expert review found serious problems in definitions, theorem generality, file organization, and the API....
-
26
A Multi-Agent AI System for Automated High School Transcript Processing: Collaborative Document Analysis at Scale
Ben Torkian, Jun Zhou
cs.AI
Each year, college admissions offices face an overwhelming challenge: processing millions of high school transcripts, each with unique formats, grading systems, and layouts. This manual process creates operational bottlenecks that delay admissions decisions and consume valuable resources. We present a transformative solution through a multi-agent AI system where specialized agents collaborate to automatically process diverse transcript...
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.