cs.AI Computer Science
Artificial Intelligence papers on arXiv
Browse reasoning, planning, knowledge representation, and other AI work in cs.AI. An explicit task keyword is a useful starting point when broad terms such as agent appear in many different settings.
6,636 papers indexed
Follow the whole category with the official cs.AI RSS feed, or use a personal filter to select keywords and authors. See the arXiv RSS feed guide for setup and the category guide for primary and cross-listed subjects.
Filter ideas for Artificial Intelligence
How filters workSeparate planning, reasoning, and agent workflows into individual filters if you want to judge their results independently. An AI category alone will not cover every relevant machine-learning or language paper.
- Try filter
Automated planning
Narrow planning matches with a setting such as multi-agent coordination or task execution.
Category cs.AI + abstract contains “planning” - Try filter
Reasoning systems
Add a qualifier such as symbolic, causal, or logical to follow a particular style of reasoning.
Category cs.AI + abstract contains “reasoning”
Examples are starting points. Preview them before saving; keyword matches do not assess a paper’s quality. Recent papers below use the primary category; saved category filters also match cross-listed categories.
LATEST SUBMISSIONS
Recent Artificial Intelligence papers
Changyu Lee, Yeonsoo Park, Abdullah Alfarrarjeh, Seon Ho Kim
Abstract
Large collections of street-view imagery provide rich visual information about urban environments, but extracting fine-grained geographic information from such data remains challenging. In particular, fine-grained regional geolocalization is challenging because nearby areas often share coarse geographic cues. We study regional geolocalization within a metropolitan area and ask whether pretrained CLIP features are sufficient for regional discrimination, and what visual information supports performance after adaptation. Using 9,085 street-view images from eight Greater Los Angeles regions, we compare zero-shot CLIP, frozen-encoder readouts, partial encoder updating, Low-Rank Adaptation (LoRA), and full fine-tuning. Frozen readouts remain near the 39.03% zero-shot accuracy, whereas encoder adaptation achieves 75.94-82.10%. Full fine-tuning also reduces the mean distance to the predicted region center from 12.30 km to 3.86 km. We probe these gains through semantic cue removal, appearance reduction using edge maps and blur, and scene-configuration disruption using patch scrambling. Adapted models achieve higher edge and blur accuracy and switch 42.92-45.56% of predictions after scrambling, compared with 10.79-14.60% for frozen methods. However, adaptation does not improve the fraction of performance retained after appearance reduction, while vegetation and sky remain influential. A Caltech101 control further shows that scrambling sensitivity is not unique to geolocalization. Overall, encoder adaptation substantially improves nearby-region discrimination and is associated with greater sensitivity to intact scene configuration, without evidence that coarse structure alone becomes sufficient for prediction. These conclusions concern viewpoint variation near known locations rather than geographically disjoint generalization.
Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R., Arun Prakash, S. Senthilkumar
Abstract
When an authorization policy blocks an agent's tool call, the audit log should name the facts that forced the decision and nothing more. For an executable policy over an enumerable context space this minimal sufficient reason can be computed exactly, so an explanation is scored against ground truth rather than a proxy for it. We use that exactness to ask what a model can learn from a verifier that has no error in it. The explainer sees one request and one decision, never the policy, and has thirty turns in which it may call the policy on altered requests and ask whether a candidate set of facts is sufficient. Frontier models find the exact reason about half the time with the tools alone, and one sentence telling them to shrink the answer lifts Haiku 4.5 from 58% to 75%. A 4B model fine-tuned on 2000 traces of the deletion algorithm reaches 92% on the policy it was trained on. Teacher kind is what moves this: at matched data size the algorithm-taught student leads the frontier-taught one in all three training seeds, and the two arms never overlap. What the student learns is a fixed schedule of sufficiency checks, and the schedule does not travel. On three public policies it never saw, its answers stay sufficient (94%) and stop being minimal (48%), while Haiku under the same sentence is exact on all 47 episodes. Reinforcement learning from the exact reward leaves held-out accuracy where it was and inverts the strategy, from probing the policy to spending the entire budget on sufficiency checks. The oracle made the effect of training legible, but it did not make training better.
Zi Wang, Mahima Pushkarna
Abstract
AI systems for creative media generation expand human capabilities yet risk diminishing human agency. A core problem is anchoring, where the user's thinking becomes anchored to a polished, generated artifact, shifting the user's role from active authoring to reactive editing. We propose pre-generation belief controls that can empower creators to inspect, revise, and steer the AI's interpretation before any media is generated, so that the initial anchor is set by the human. We formalize four design principles and instantiate them in the Proactive Co-Creator (PaCC), a system for early-stage conceptual ideation and prototyping that proactively surfaces its assumptions and uncertainty through clarifications, belief graphs, and media attributes, inviting users to shape the AI's beliefs before generating the final outcome. Using PaCC as a design probe in a small-scale, single-arm exploratory user study, we observed that participants reported directionally positive sense of agency and process control relative to their familiar prompt-based AI tools, noting that surfaced assumptions helped them think through details they had overlooked, whereas their feelings about ownership and authorship diverged
Shuyi Ouyang, Xiaojun Tang, Zijian Zou, Xintong Zhang, Mingli Song, Guannan Zhang, Hongwei Xue
Abstract
Visual artifact tasks test agents' ability to translate task specifications and source materials into outputs that meet practical needs. Evaluation across artifact families helps distinguish broadly applicable authoring capabilities from strengths confined to a particular medium. We introduce VisualArtifactSpec 1.0 (VAS), a benchmark of 211 creation and modification tasks spanning presentations, static graphics, animations and videos, and web interfaces. Each task specifies authoring objectives, source materials, constraints, and deliverables. Existing benchmarks provide limited support for systematically evaluating how authoring choices suit different audiences, purposes, and media across artifact families. VAS evaluates two aspects separately: Task Fulfillment verifies explicit requirements and applicable functionality, while Artifact Performance assesses Content, Organization, Visuals, and Delivery. Task-specific rating anchors instantiate shared criteria for the intended audience, purpose, and medium, with judgments grounded in source materials and artifact inspection records. We evaluate nine model-harness configurations on all 211 tasks. Overall scores range from 42.12 to 70.52, with Artifact Performance accounting for 73.4% of the gap between the highest- and lowest-scoring configurations.
Sven Jacobs, Lukas Berning, Natalie Kiesler
Abstract
Children using Scratch to learn programming can struggle with text-heavy, lengthy explanations and hints during debugging. Verbal interactions based on screen sharing or camera data may be an interesting alternative for supporting learners. We therefore explore the quality, use, and perceptions of fifth- and sixth-graders' verbal interactions with a GenAI tutor. The goal is to investigate the quality and use of the multimodal GenAI tutor in the given context. First of all, a pilot study of eight tasks conducted without students helped inform the process of the tutor's classroom evaluation. The classroom study was realized after fifth- and sixth-graders had participated in six Scratch classroom lessons. Then 23 students were introduced to the tutor, worked on the eight tasks with the GenAI tutor, and completed a questionnaire. The analysis of the pilot and classroom study shows that the tutor's responses were intelligible and actionable, and no single turn revealed a complete solution. However, the tutor missed existing errors in 61.5% of 603 error-related classroom turns, compared to 15.7% in the pilot study. Children's voice prompts were brief and mostly responded to the tutor. Although a video had explained that responses could be incorrect, 39.1% of the children trusted the tutor's answers to always be correct. These findings have implications for educators and learners using multimodal GenAI tutors, as they need to be aware that an intelligible and human-like voice does not ensure correct support. For developers, our results suggest that screen sharing alone does not ensure responses that match the program state.
Frequently asked questions
How do I get alerts for new Artificial Intelligence papers on arXiv?
Create a filter for the cs.AI category — add keywords or authors to narrow it further if you like. Matching papers are delivered to a personal RSS feed, and optionally by immediate, daily, or weekly email digest.
Where does this Artificial Intelligence paper data come from?
Paper metadata comes directly from arXiv through its official OAI-PMH feed, checked roughly every 15 minutes for new submissions in cs.AI and every other arXiv category.