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 12 October 2026 to 6 November 2026: 4,992 arXiv preprints and 8 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 242
ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models
Reinforcement learning (RL) post-training improves robot foundation models (RFMs) beyond their demonstrations, but real-world deployment demands more: learning new tasks efficiently while retaining…PhysicsSliders: Learning Physical Controls for Audio Foley Generation
Physical properties provide intuitive controls for sounds made by interacting objects.Rethinking Projector Training in Multimodal LLMs
Multimodal LLMs are typically trained by first aligning a vision encoder with a language model via projector training on large image-caption datasets, followed by joint training of the full…Auditing Future-Memory Use in Point-in-Time Language Agents
Point-in-time (PIT) agents can recall post-cutoff facts even when their external evidence respects a historical cutoff.AgentStripes: An Evidence-Graded Maturity Model for AI Agents
Benchmarks report what an Artificial Intelligence (AI) agent can do on a task suite, but not whether one released version has been engineered with the controls that make it reliable, safe and…LLM2R: From Large Language Models to 3D Reassemblers
3D part assembly aims to reconstruct a complete shape from a set of unassembled parts by predicting a rigid SE(3) transformation for each part.Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces
Large language models increasingly tackle tasks that require multi-step reasoning, where errors in intermediate claims can affect the final answer.DPOison-VL: Clean Preference Poisoning in Vision-Language Direct Preference Optimization
Direct Preference Optimization (DPO) has become a widely adopted approach for aligning vision-language models (VLMs), yet the security of multimodal preference data remains largely unexplored.Jev-ToM: Evaluating Theory of Mind in Typed Decision Models
Dialogue and collaborative assistants repeatedly judge what a partner knows, believes, or intends.Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications
System One models such as Jev change how software makes decisions by mapping open-ended semantic contexts into structured judgments that directly drive program execution.Does self-distillation improve reasoning?
Self-distillation is an emerging approach that trains a model to imitate its own predictions when conditioned on privileged information, such as correct answers or environmental feedback.Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents
Controlling an acting LLM agent means deciding, at each step of a long-horizon task, whether to trust its next action, abstain, or hand off to a human.Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve
Searching text-rich knowledge graphs requires following relations while examining textual evidence.Two Routes to Interoceptive Prioritisation: Dissociating Likelihood Precision and Preference Reweighting in Active Inference
An embodied agent must prioritise among competing bodily needs.Falsification-proof non-market allocation mechanisms
Relying on manipulable characteristics to target the allocation of resources is fraught with difficulties.Geometric Calibration of Supervised Fine-Tuning
Recent studies investigate the weight geometry through its spectral structure, which characterizes how the weights transform different input directions.DTScribe: Generating Models for Digital Twin Reporting using Local Large Language Models
The development of a digital twin brings together many stakeholders and technical components.To Align or Not To Align: Check Your COMPASS Before You Train
Combining pretrained models is a common strategy for building AI systems, whether by aligning a vision encoder with a language model or merging fine-tuned checkpoints.ST-GRU PredRNN-V2: A GRU-Based Reformulation of PredRNN-V2 for Video Prediction
Video prediction requires models to capture complex spatiotemporal dependencies and to retain relevant information over long sequences.Tiny Recursive Message Passing
Message passing neural networks have shown remarkable performance in algorithmic and constraint reasoning, due to their ability to encode the structure of the task directly in the architecture.