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: 4,993 arXiv preprints and 7 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 17
Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration
Discovering cooperative behavior in multi-agent reinforcement learning (MARL) is challenging due to the combinatorial complexity of joint state-action spaces, which hinders the emergence of…Finite-Time Convergence and Regret Guarantees for Neural Reinforcement Learning in POMDPs
Reinforcement learning (RL) in Partially Observable Markov Decision Processes (POMDPs) is computationally challenging due to the curse of long-range dependence on history.Shaping & Monitoring Models through their Internal Representations
We propose Mechanistic Shaping, a unified framework for shaping models through their internal representations.When Verification Is Not Agreement: Cross-Agent LLM-to-Dafny Formalization
A verified Dafny postcondition certifies that a formula holds, but it does not guarantee that the result was reached through genuine independent reasoning.Synthesizing symbolic models of human and machine reasoning at scale
Symbolic models offer a powerful account of cognition, but their scope has historically been limited by the need for hand-engineering and computational tractability.Polynomial-Time Computation of Extensive-Form Proper Equilibria in Two-Player Zero-Sum Games
We give a deterministic polynomial-time algorithm for computing an exact extensive-form proper equilibrium in a finite two-player zero-sum extensive-form game with perfect recall and rational data.A Night at the LLM Zoo: Data Conditioned Flow Matching for Generating Pretrained LLM Weights
A challenge to Weight Space Learning as it expands from task specific and vision models to Large Language Models (LLMs) is the absence of a well curated and analyzed LLM population.PromptOps: Iterative Prompt Optimization for LLM-as-a-Judge Systems
Large language models (LLMs) are increasingly used as automated judges for evaluating the behavior of chatbots and other AI systems.Adapting LLM Judges to Observed Human Annotation Policy through Soft Prompt Tuning
Large Language Models (LLMs) are increasingly employed as automated judges for evaluating chatbot responses.More Agents, More Reliable? System-Level Reliability of Multi-Agent LLMs under Operational-Profile Uncertainty
Teams increasingly build software from cooperating large language model (LLM) agents, often assuming more agents mean more reliability.Depth or Description? When a One-Step Latent Score Replaces Lookahead in Proactive Information Acquisition
A proactive agent must decide what to ask before it acts.Multi-step SWE: Can Coding Agents Keep Building on Their Own Code Over Long Horizons?
Developers rarely give a coding agent a single request: they ask it to build a component and then to extend, upgrade, and optimize it, each time on code the agent itself wrote.SeVerus: Context-Aware, Gamified Benchmarking for Rust Verification
Coding agents achieve high success rates on existing benchmarks for Verus, a verifier for Rust programs.Compositional Unalignment: Auditing Safety in Large Vision-Language Models
Large vision-language models (LVLMs) are vulnerable to compositional harm: an image and a prompt that are benign in isolation become harmful through the model's cross-modal reasoning.TileQuant: Tile as the Precision-Allocation Unit for LLM Mixed-Precision Post-Training Quantization
Post-training quantization (PTQ) reduces large language model (LLM) deployment costs, but preserving quality requires accounting for uneven weight sensitivity.SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection
Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money to an attacker.Archetypal contexts in the neurons of language models: an architecture for intelligence?
We validate our previous hypothesis that a language model holds relational patterns apart from the subject domains that instantiate them (Nordfors, 2026).MAC-v2: Long-horizon model-based value expansion from pixels
We study whether \emph{long-horizon model-based value expansion} can serve as an effective framework in pixel-based offline reinforcement learning (RL).KG-Neighbor: Knowledge-Guided Neighborhood Construction for Embedding Visualization
In embedding visualizations, nearby instances are interpreted as semantically related, although neighborhoods derived from input embeddings may not reflect content relationships.Goal Revelation as a Bridge Between Information-Theoretic Empowerment and Capability-Based Human Power
Power matters for AI safety.