920 papers recorded in this category. Newest first.
- DreamX: Video Diffusion Model is a Universal Latent Action Learner
Learning a universal action representation from video requires modeling dynamics that are consistent across different executions of the same action yet invariant to changes in embo…
2026-11-03
- From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence
For a decade, progress in artificial intelligence has been measured by how much a machine can do on its own. Large foundation models now write code and run multistep tasks, and per…
2026-11-03
- Aligning Language Models with General Preferences: An Empirical Study of Direct Nash Optimization
Direct Nash Optimization (DNO) aligns a language model to a general preference function by approximating the Nash equilibrium of a two-player preference game. Its practical variant…
2026-11-03
- Suppressing Misaligned Behaviors in Language Models, Durably
Undesired model behaviors can emerge or re-emerge at any stage of training. Once observed, how effectively can we suppress them? To study this question, we first construct two mode…
2026-11-03
- Adversarial Speculative Reasoning Improves Long Horizon Agents
Speculative decoding has been treated purely as a systems optimization that speeds up large language model decoding without changing the model behavior. Under this view, the growin…
2026-11-03
- Weight-space programming for auditing clinical decision networks
Machine learning models in radiotherapy are commissioned by testing them on cases with known answers, which may not reveal a shortcut that the test cases share with the training da…
2026-11-03
- MedPhysBench: A Benchmark for Evaluating Language Models on Medical Physics Calculations and Error Detection
Medical physicists turn a prescription into a delivered dose and check one another's calculations, because one error in a beam calibration or a monitor-unit (MU) calculation can af…
2026-11-03
- A simple adaptive accelerated optimistic dual averaging method for unconstrained convex optimization in $p$-norm geometry
Efficient preconditioning plays an important role in large-scale first-order optimization. In this paper, we propose an adaptive accelerated optimistic dual averaging ($\text{A}^2$…
2026-11-03
- PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data
Teleoperation remains the default way to collect robot demonstrations, but every episode costs robot and operator time, and every new task starts from scratch. We ask whether a cod…
2026-11-03
- HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation
In LLM-based recommendation, memory acts as a user-level agent in a memory-augmented backbone. Yet users and items remain asymmetric: only the user is given a structured profile; i…
2026-11-03
- You don't need long context
Later tokens are costlier to generate than earlier tokens. On frontier open weight models, the disparity in cost may rise to as much as 7x. Through frequent compaction, we show acr…
2026-11-03
- LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers
Looped transformers are a parameter-efficient alternative to standard transformers for language modeling. By reapplying the same layers across multiple loop steps, recent looped la…
2026-11-03
- Personas Are Not People: Identity as State, Not Attribute
Synthetic populations, large sets of simulated people, are increasingly used in place of real people to pretest surveys, simulate users and communities, and evaluate AI systems. Ea…
2026-11-03
- False Reassurance in LLM Severe-Weather Guidance: A Replayable Evaluation Against Real NWS Alerts
An LLM assistant that cannot see official severe-weather alerts may tell users that conditions are calm while a warning is active. We call this false reassurance and measure it by …
2026-11-03
- Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce Misalignment
Fine-tuning a large language model (LLM) on harmful data in a narrow domain, such as bad medical advice, can make it broadly misaligned. How realistic this risk is remains unclear,…
2026-11-03
- Beyond Accuracy: What Language-Subspace Interventions Capture, Remove, and Improve
Language-subspace interventions aim to improve multilingual reasoning by suppressing language-related components in mid-layer activations. Using MATH and MGSM across four open-weig…
2026-11-03
- The Geometry of Ignorance: Detecting Suppressed Knowledge in LLMs through Activation Fragmentation
Evaluating whether a large language model (LLM) genuinely knows a concept remains a fundamental problem, since behavioral metrics can be fooled by suppression: a model that refuses…
2026-11-03
- JHiMA-WebRL: A Joint Hierarchical Multi-Agent Reinforcement Learning Framework for Long-Horizon Web Tasks
Multimodal web agents have shown promising capabilities for interacting with websites through graphical user interfaces (GUIs), yet realistic web tasks often require long-horizon, …
2026-11-03
- Going Deeper With Memories
Byte level language models avoid tokenizer dependence and provide universal coverage, but processing every byte at full resolution is expensive. We introduce DeepMem, a causal mult…
2026-11-03
- Fairness Metrics based on the AUC in Clinical Predictive AI
Fairness evaluation of clinical prediction models for binary outcomes often involves fairness metrics that compare the area under the receiver operating characteristic curve (AUC, …
2026-11-03
- Pixel-UMI: Learning Environment-Aware Whole-Body Manipulation from Sensorized Human Demonstrations
Sensorized human demonstrations offer scalable data for mobile manipulation, but embodiment differences complicate policy learning. We present Pixel-UMI, a pipeline for learning en…
2026-11-02
- Pixel: A Co-Designed Full-Stack Robot System for Learning General-Purpose Mobile Manipulation
General-purpose mobile manipulation requires a combination of capable robot hardware, scalable demonstration collection, expressive whole-body control, and effective policy learnin…
2026-11-02
- From Natural Language to Exact Cover: A Neuro-Symbolic Approach to Zebra Puzzles
Chain-of-Thought (CoT) generation has substantially improved the performance of Large Language Models (LLMs) on complex reasoning tasks, including code generation, data analysis, a…
2026-11-02
- WebHarbor: Docking Real Websites for Evolving GUI Agent Environments
GUI web agents require realistic and interactive environments that remain stable during both evaluation and training. Live website evaluation suffers from changing content, access …
2026-11-02
- D&A: Decoupling Description and Assessment Enables VLMs as Zero-Shot Robotic Reward Models
Vision-Language Models (VLMs) hold promise for zero-shot video task-progress estimation in robot learning, yet existing frameworks frequently suffer from confirmation bias, halluci…
2026-11-02
- Strategist: Evolving Reasoning with Agents
A model is only half of an AI agent system. The other half is the inference strategy: the reasoning procedure that turns model calls into a response. Today that second half is writ…
2026-11-02
- Tracing the Scientific Discovery Capacity of LLMs to Their Training Data
Large language models (LLMs) show growing promise for scientific discovery, yet basic questions remain about what enables reliable discovery. How can we trace the scientific discov…
2026-11-02
- DiabAgent: Toward Agentic Physiological Control
As pretraining scales, medical language models have advanced rapidly in clinical question answering. Their ability to achieve effective physiological control through sustained inte…
2026-11-02
- Four Bridges: Measuring Deception Propensity in a Multi-Agent Game
AI agents are increasingly deployed in settings where they interact and coordinate with other agents, yet honesty is mostly measured in single-turn, single-agent benchmarks that pr…
2026-11-02
- Spacetime Emergence in the Memory of a Learning Agent
We show that the causal structure of spacetime can emerge within the memory of a learning agent performing a quantum information task. We train a model-based reinforcement-learning…
2026-11-02
- Evaluating Uncertainty Calibration in Probabilistic Time Series Foundation Models
Time series foundation models (TSFMs) are increasingly used for probabilistic forecasting across diverse domains, yet the reliability of their uncertainty estimates remains poorly …
2026-11-02
- FedReady: Bounded Agents for Federation Formation
Federated learning (FL) runtimes standardize aggregation and deployment, but each new study still requires federation formation: selecting task-eligible sites and preparing their l…
2026-11-02
- Sonar-MoE: In-Backward Expert Updates for Memory-Efficient Mixture-of-Experts Training
Most parameters of a Mixture-of-Experts (MoE) model belong to its experts, and standard training keeps every expert gradient in GPU memory until the optimizer step. This memory gro…
2026-11-02
- PlantVLM-Edge: Quantized Vision-Language Models for On-Device Crop Health Diagnosis
Timely and accurate crop health diagnosis is essential for sustainable agricultural production, yet accurate diagnosis often requires expert knowledge that is not readily available…
2026-11-02
- MCP Tool Poisoning in Agentic AI Frameworks: A Cross-Framework Measurement Study
The Model Context Protocol (MCP) lets agentic AI frameworks connect language models to external tool providers, but it carries attacker-controlled content (tool descriptions, schem…
2026-11-02
- Can LLM Agents Be Forward-Deployed Engineers? Requirement Discovery and Delivery for Enterprise Text-to-SQL
LLM coding agents can increasingly automate model post-training, but whether they can act as forward-deployed engineer (FDE) agents, discovering customer requirements and turning t…
2026-11-02
- An Agentic Framework for Automated Power System Studies and Grid Connection Assessment
Connecting new generation and demand to the grid depends on two scarce skills: checking applications against a large, changing body of regulation, and running the network studies t…
2026-11-02
- Contrastive Adapter Training and Consensus Knowledge Distillation for Multi-Source-Free Domain Adaptation in Skin Cancer Diagnosis
Skin cancer diagnosis, particularly differentiating melanoma from benign nevi, is challenging due to the visual similarity between lesions. Although convolutional neural networks (…
2026-11-02
- Library of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime
Computer programmers chain together the same reusable computational primitives, for example, conditional statements or loops, but in different orders to implement different algorit…
2026-11-02
- Grading the Unannotated: Insights from the WorkRB Skill Extraction Challenge at RecSys-HR 2026
Skill extraction benchmarks score models against a few human-annotated positives and treat every other skill in the vocabulary as equally wrong. At the scale of ESCO (13,939 skills…
2026-11-02
- Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
Agentic workflows are increasingly shifting towards long-horizon tasks, such as open-ended scientific work, where models benefit from long context windows. However, at ultra-long c…
2026-10-30
- Hierarchical World Models with Implicit Dynamics
Planning with world models enables test-time adaptation for embodied agents, offering superior generalization over direct policy learning. However, long-horizon tasks remain hinder…
2026-10-30
- RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory
Recent work shows that a frozen robot policy performs far better inside an agent harness, where control code decides when to query the policy, consult vision tools, or command the …
2026-10-30
- ACCT: Asymmetric Cross-LLM Context Transfer
In real-world deployments, large language model (LLM) systems are increasingly evolving from single-model invocation toward heterogeneous deployments in which different models are …
2026-10-30
- Subquadratic Attention with a Hierarchical Tree-Structured Indexer
The quadratic scaling of attention is a fundamental bottleneck limiting the long-context capabilities of large language models (LLMs). A variety of approaches have attempted to cir…
2026-10-30
- CausalWAM: Learning the Causes of Actions in World Action Models
World action models (WAMs) learn latent variables from observations and use these to both predict the evolution of the scene and to generate actions. The prediction has to be of th…
2026-10-30
- The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results
AI answers require more than apparent correctness: reviewers need to inspect their recorded basis. We introduce the Knowledge Layer Model (KLM), an open, implementation-neutral spe…
2026-10-30
- CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness
Reinforcement learning with verifiable rewards (RLVR) has become the standard method for training language models to reason. However, RLVR typically relies solely on outcome correc…
2026-10-30
- Near-Optimal Second-Order Convex Finite-Sum Optimization under Individual Smoothness
We study the stochastic second-order oracle complexity of solving smooth convex finite-sum optimization with $n$ components. Very recently, Tsedenov \& Kovalev (2026) showed that t…
2026-10-30
- Same Question, Different Answers: Auditing Persona-Dependent Variation in Six LLMs on Smoking-Cessation Advice
Hundreds of millions of people now ask large language model (LLM) chatbots for health advice, which raises a question that is simple to pose and hard to answer: does everyone get t…
2026-10-30
- Learning Clean Generative Processes from Noisy Measurements
We study how to learn a generative model of clean images using only noisy observations. Diffusion processes and their generalizations to non-Gaussian noise require posterior predic…
2026-10-30
- There Is No Free Loop: When Does Looping a Trained Model Pay for Its Inference Compute?
Looping re-applies a block of layers so that each token passes through the block more than once. Adding a loop to a trained model is attractive because it leaves the parameter coun…
2026-10-30
- Know When the Equation Is Wrong: Structural Uncertainty for LLM-Guided Symbolic Regression under Extrapolation
Large language models (LLMs) can help discover mathematical equations from data, but most LLM-guided symbolic regression methods focus on a single best equation without quantifying…
2026-10-30
- TradeWar: A Benchmark for Execution-Grounded Trade Negotiation with Adaptive LLM Agents
Multi-turn negotiation remains a challenging problem for large language model (LLM) agents. While LLMs can conduct natural-language dialogue, existing benchmarks predominantly asse…
2026-10-30
- AutoAnalysis: An automated, self-updating meta-analysis of human-AI collaboration
As generative artificial intelligence (AI) becomes more capable and widely used, understanding when and how humans should work with these systems is becoming increasingly important…
2026-10-30
- SecPO: Principled Adversarial Training for Prompt Injection Security
Recognized as a top threat to AI agents, prompt injection allows instructions from untrusted data (email, documents, websites) to manipulate the agent's operation. The existing bes…
2026-10-30
- DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention
Linear attention scales linearly with sequence length, but its finite-state memory can limit long-context retrieval. In gated linear recurrences, memory retention depends on state …
2026-10-30
- ID2Pattern: Pretraining Generalizable Identity Behavior Patterns for Transaction Risk Foundation Models
Large-scale behavioral pretraining offers a promising route to generalizable representations in online payment systems. However, high-cardinality identity fields such as card, devi…
2026-10-30
- When Does Test-Time Search Help World Action Models? An Empirical Audit of Candidate Selection and Simulator Integrity
World-action models increasingly apply test-time scaling, spending extra inference computation on candidate selection and adaptive allocation to improve control. Such gains are cre…
2026-10-30
- Prune Gradually, Adapt Sparsely: Efficient Pruning of Large Language Models at Extreme Sparsity
Weight pruning can reduce the storage and inference cost of large language models (LLMs), but preserving quality at high sparsity levels remains challenging. Existing methods face …
2026-10-30
- Rethinking Neural Thickets Without Weight Perturbations
The Neural Thickets hypothesis posits that pretrained language models lie in dense neighborhoods of task-specific experts in weight space, which random Gaussian perturbations can u…
2026-10-29
- Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers
Pixel-space generative Transformers typically use one token per image patch, so capturing finer detail requires more tokens and makes global attention increasingly expensive. We ob…
2026-10-29
- Luggage re-identification: A study of strategies towards a real-world application
Luggage re-identification (ReID) is a critical task in video surveillance for forensics, security or border management (suspicious or abandoned luggage recognition), as well as lug…
2026-10-29
- From extreme weather to agricultural consequences with agentic AI
Extreme weather is forecast days ahead, yet its consequences for agriculture remain hard to predict: a forecast says where a storm will strike, not which crops will suffer or how m…
2026-10-29
- Probing Spatial State Representations in Visual Foundation Models
An observer sees only part of the surrounding world, yet must keep track of what lies beyond the current view. Spatial perception therefore involves more than recognizing individua…
2026-10-29
- TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races
We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative decoding: tokens that replace rejected drafts remain watermarked…
2026-10-29
- When to Assist and What to Suggest: Joint Gating and Memory-Grounded Hint Generation in One Compact Decoder
Proactive assistants offer short, memory-grounded hints during a conversation, deciding when to assist and what to suggest. Current systems split this between a gate and a larger g…
2026-10-29
- Collaborative AI agents for autonomous experimental research with solid-state quantum spins
An autonomous research laboratory could conduct an entire study, from formulating questions to preparing manuscripts. Artificial intelligence (AI) offers one route towards this goa…
2026-10-29
- Pre-Crime for Agents, at the Last Second: Probing When a Recruited Agent Gives In
When AI agents share channels and credentials, one agent can press another to break its operator's rule, a first step towards collusion. Output filters check only what an agent has…
2026-10-29
- Multistatic ISAC with Deep Learning-Based Clutter Suppression for 5G and Beyond
Integrated sensing and communications (ISAC) systems using 5G and beyond signals of opportunity enable joint wireless sensing and communication using shared infrastructure and spec…
2026-10-29
- VeriCUA: Verification as Agentic Exploration for Computer-Using Agents
Building and scaling computer-using agents (CUAs) across desktop, mobile, and web environments requires reliable task-completion verification for data curation, evaluation, and rei…
2026-10-29
- Gym-Anything for Robotics: Scaling physical simulations with digital agents
Realistic, fast robotics simulations could enable large-scale training of embodied AI models that transfer to the real world. However, despite decades of progress, available simula…
2026-10-29
- Comparing Human Role-Players and LLM-Simulated Clients in Online Counselling Training: An Analysis of Counselling Patterns
This study investigates the capabilities of Large Language Models to simulate counselling clients in educational role-plays in comparison to human role-players. Initially, we recor…
2026-10-29
- FARMS: A Verifiable Foundation for Automated Computational Science
Automated computational science could accelerate discovery by selecting, adapting and developing numerical methods. This prospect requires mathematical knowledge that AI systems ca…
2026-10-29
- Advancing Clinical Genomic Analysis with a Skill-Centred Agent
Clinical genomic analysis requires experts to integrate evolving guidelines, databases, and computational evidence. As sequencing has become increasingly accessible, this complex a…
2026-10-29
- Ramanujan Challenge Results: AI-Assisted Evaluation Pipeline for Multi-Format Proofs
As AI's mathematical capabilities rapidly improve, meaningful benchmarks are shifting from university-level problems and math olympiads to research-level mathematics. The Ramanujan…
2026-10-29
- Retrieval as Traversal: Value-Indexed Memory for Stateful Long-Context Agents
Long-context models repeatedly solve closely related retrieval problems. Attention or global retrieval can retain large stores, but each forward pass again searches for what matter…
2026-10-29
- On the Fundamental Limits of Prefill-Based Decoding Length Prediction
Predicting how many tokens a large language model (LLM) will decode, using only prefill-phase hidden states, is a key primitive for inference scheduling. We show that current bench…
2026-10-29
- Efficient Scalable Oversight via Rewinding
Scalable oversight asks how a weak verifier can check the outputs of computations performed by more powerful AI systems. One proposed approach uses relativizing interactive proofs,…
2026-10-29
- BURGER: Benchmarking and Understanding Robotic Generalization via Embodied Drawing
How effectively can vision-language-action (VLA) models learn diverse language-conditioned behaviors as training data scales? Investigating this question requires large and varied …
2026-10-29