AI & Machine Learning · Computer Science & AI
Artificial Intelligence
The newest papers in Artificial Intelligence that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 11 October 2026 to 5 November 2026: 4,998 arXiv preprints and 2 OpenAlex records.
Get the few papers worth your time in Artificial Intelligence every morning.
Follow Artificial Intelligence and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 81
From Grind to Grasp
Discussions of complexity, knowledge and intelligence often overlook the work involved.AtomTree: A Hierarchical Framework for State-Aware Embodied Instruction Following with LLMs
Embodied instruction following in interactive environments requires agents to interpret natural language commands and complete long-horizon tasks.Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations
Gardening in the backyard implies living there, while checking into an Airbnb more likely means staying for a few days.CopyLoop: Fast Looped Transformer Decoding via Context Copying and Shallow Screening
Looped Transformers increase computational capacity through the repeated application of shared blocks, but their recurrent depth makes conventional full-depth decoding expensive.Evaluating Visual Realism of AI-Generated Videos with Eye Tracking
Human evaluation of AI-generated videos has so far relied on explicit human feedback, such as judgments or ratings.Discovering Jailbreaks via Curriculum of Models
Automated jailbreak discovery aims to find prompts that elicit prohibited behaviors from safety-trained language models, helping developers identify vulnerabilities before deployment.Autonomous Quantum Measurement with Agentic AI
Quantum materials exhibit diverse electronic and functional phenomena, but their characterization requires extensive experimental expertise, iterative decision-making and accumulated laboratory…Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training
In many settings where LLM post-training is desirable, high-quality answers are recognizable but difficult to score with explicit rewards.Where You Inject Matters: The Trust Region Effect in LLM Agents
LLM agents are increasingly adopted in long-horizon tasks and interact with diverse external environments.Auditable Belief Updates as a Missing Safety Layer for LLM-Powered Multi-Agent Systems
Large Language Models (LLMs) are increasingly being used as cognitive interfaces that shape how users interpret evidence, communicate, and make decisions.Aligning Autoresearch: Co-Improvement between Agents and Humans
Autoresearch agents can now attempt long-horizon AI research end-to-end, i.e., self-improvement.FlipJev: Fast Black-Box Red Teaming Finds Universal Adversarial Suffixes for Typed Decision Models
Typed decision models are an emerging class of language models that make decisions instead of generating free-text responses.Interventional Training Reduces Causal Bypass in In-Context Introspection
Introspection, the ability of a system to access and reason about its internal signals, is crucial for language model (LM) self-consistency and scalable interpretability.Lev-3B: A Data Recipe for Compact Probabilistic Log Decision Models
Many log-analysis tasks involve choosing among known options, such as detecting anomalous sessions or identifying attack techniques, and benefit from calibrated probabilities.TrussTutor-Bench: Benchmarking large language models on solution accuracy, sycophancy, and error detection in statics
Large language models (LLMs) have rapidly become a default source of help for students in science and engineering courses.TreasuryQA Bench: Can AI Agents Work an Archive of Scanned Financial Records?
Organisations keep decades of financial records as scanned PDFs on shared drives, and AI agents can now reach those drives through Model Context Protocol (MCP) servers.MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems
Training-time multi-agent system (MAS) design seeks to learn reusable orchestration policies, yet prevailing approaches remain largely one-shot: an Orchestrator generates a system but only observes…Efficient Agentic Audio-Visual Question Answering through Toolset Pruning and Modality Consolidation
Fine-grained audio-visual question answering (AVQA) requires models to resolve complex cross-modal correspondences and temporally grounding from sparsely distributed evidence.TableTune: Measured, Self-Correcting Draft-Length Tables for Dynamic Speculative Decoding
Speculative decoding speeds up large language model (LLM) serving only while the GPU has spare compute, so the best draft length, the number of tokens a small drafter guesses per step, shrinks as…Dungeons & Dragons Encounter Analysis with Semi-Random Simulation in Foundry VTT
Dungeons & Dragons (D&D) is a tabletop roleplaying game (TTRPG) in which a group of players, guided by a Game Master, roleplay a fantasy adventure with simulated combat and improvisational narrative.