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 95
Knowing When the Evidence Is Enough: Requirement-Directed Search with Horn-Closure Certificates
After each Web search, a search-augmented model must decide whether its evidence suffices: answer, search again, or abstain.From Speech Tokens to Stolen Voices: Attacker-Chosen-Text Speaker Impersonation via Representation Inversion
Speech interaction systems have gradually evolved from traditional cascaded systems that use text as intermediate information to end-to-end speech language models that directly process speech…Gangqinpu: A Multi-Genre, Multi-Task Piano Dataset with Aligned Audio, MIDI, and Musical Scores
Aligned audio, performance MIDI, and musical scores provide valuable supervision for music analysis and performance modeling, yet datasets that jointly align all three modalities remain scarce and…Movable-Element Multi-Functional RIS-Assisted Hybrid RSMA-NOMA: A Constrained Hybrid Reinforcement Learning Approach
In this work, we propose a movable-element (ME) multi-functional reconfigurable intelligent surface (MF-RIS) architecture, termed MM-RIS, which integrates element mobility with adaptive signal…Safe by Benchmark, Unsafe in Practice: Lessons from 1331 Child-Related AI Incidents
AI systems are increasingly present in children's everyday environments: education, entertainment, social networks, and toys.Intervene, Calibrate, Discover: Learning Causal Structure from Pixels
Learning high-level causal variables from low-level observations is a central problem for artificial intelligence.SearchHorizonBench: A Benchmark for Search Value in AI Agents
AI agents must decide when another search is worth its cost.VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware
Vision-language-action (VLA) models increasingly run on edge devices aboard robots, where inference latency constrains closed-loop robot control.Prefetch-Steered Routing: Deterministic Cache-Aware Expert Selection for Offloaded Mixture-of-Experts Decoding
When a Mixture-of-Experts (MoE) model does not fit in GPU memory, batch-1 decoding is dominated by copying expert weights from host memory.CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems
Multi-agent systems (MAS) require both effective coordination and specialized task execution.Harness-Model Collaboration for Long-Horizon Continual Learning
Long-horizon agents continuously encounter reusable procedural knowledge, yet existing systems typically rely either on model adaptation or external memory, trading persistent learning for rapid…SKALOS: Learning to Distinguish Similar Skills with Capability Graphs
Skills provide LLM agents with reusable procedural knowledge, making appropriate skill selection essential for reliable agent behavior.SceneAgent: An Agentic Pipeline from 3D and 4D Captures to Simulation Environments
Visual captures provide detailed scene appearance, but converting them into interactive simulation environments requires object reconstruction, physical modeling, and correction of intermediate…Query-Driven Learning for Lifted Reasoning
Learning and reasoning are both essential to intelligent agents, but have traditionally been treated as two separate stages: first learning a knowledge base from data (or taking one as given), and…Babysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures
Users are increasingly delegating tasks to AI agents, allowing agents to perform long-running, multi-step workflows on their behalf.The Physical Cost of Context: Quality-Constrained Resource Accounting for Coding Agents
Coding agents resend a growing context on every model call, and context policies are usually judged by the prompt tokens they save.The Right Fact, the Wrong Decision: SciValidityBench for Scientific Agent Memory
Most agent-memory benchmarks frame long-term memory as retrieval: can an agent recover the relevant record from a long and evolving history?DynEdit: Dynamic Entropy-Guided Sequential Editing for Large Language Models
Knowledge editing aims to update outdated or incorrect knowledge in large language models without full retraining.The Impact of Personalized AI Response Suggestions on Content Creators' Direct Messaging
Direct messaging is often employed by social media content creators to directly interact with followers.Scope-Gap Injection: Exploiting Evaluator Channel Blind Spots in the OpenClaw Agent Security Competition
This paper introduces Scope-Gap Injection (SGI), an indirect prompt injection method for multi-stage LLM-agent safety pipelines.