300 papers recorded in this category. Newest first.
- Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation
Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way now operate robot…
2026-09-17
- Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision
Complex robotic manipulation tasks frequently require a long-term memory of past events and actions. As conditioning on full histories renders policies prone to spurious correlatio…
2026-09-17
- FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence. Most feed-forward methods infer …
2026-09-17
- Paint-Anything: Unified Any-Color Control for Image Generation and Editing
Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored …
2026-09-17
- ERCPMP-Gx: Endoscopic Image and Video Dataset for Morphological, Histopathological, and Genomic Characterization of Colorectal Polyposis
Hereditary polyposis syndromes can be precursor lesions to colorectal cancer and are associated with a broad spectrum of extracolonic tumors. Early identification and accurate clas…
2026-09-17
- Quantifying Overclaiming Propensity in Frontier LLM Agents
Frontier coding agents are increasingly trusted to work autonomously for long periods, yet an agent's final response is often the only account of that work a user sees. We quantify…
2026-09-17
- An Empirical Study of Harness Design for Coding Agents
Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses…
2026-09-17
- RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-le…
2026-09-17
- Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations
Safety evaluations for large language models rely on surface-form classifiers that report declining harm scores across model generations. We provide evidence that this methodology …
2026-09-17
- GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies
Action chunking is widely used for action generation and execution in Vision-Language-Action (VLA) policies, yet existing approaches commonly use a fixed action horizon. During a r…
2026-09-17
- Semantic Action Graph: A Shared Representation for Agent Grounding and Human Interpretation of Sports Highlights
Generative agents are increasingly used to select and narrate video highlights, but they typically operate over unstructured or frame-level representations. Their output is consequ…
2026-09-17
- Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation
Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in deployed agents. Exhaustive te…
2026-09-17
- RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents
Effective troubleshooting agents in enterprise customer support depend on retrieving actionable guidance from similar historical cases, yet existing retrieval-augmented generation …
2026-09-17
- Large Language Models as Falsifiers for Cyber-Physical Systems
Falsification searches for counterexamples to formal specifications in cyber-physical systems (CPS). With specifications written in Signal Temporal Logic (STL), falsification can b…
2026-09-17
- Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure
Semantic cell annotation improves chunking interpretability for spreadsheets in LLM-driven RAG systems, aiding answer generation through enriched context rather than improved retri…
2026-09-17
- Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models
Activation steering modifies LLM behavior at inference time, but identifying where and how strongly to steer remains manual. We introduce Deep Noir, a framework that uses Logit Len…
2026-09-17
- Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies loss only to agent-authored action tokens, using environment o…
2026-09-17
- HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface
Large-scale vision-language-action (VLA) models provide powerful priors for robot manipulation, yet adapting them to a specific deployment remains challenging. Supervised fine-tuni…
2026-09-17
- Ownership in AI-Assisted Everyday Tasks
When does work done with AI still feel like ours? As AI becomes woven into everyday tasks, we must examine what happens to our sense of ownership and contribution when a machine sh…
2026-09-17
- PAA: The Probabilistic Allen Algebra: A Generative and Complete Probabilistic Extension of Allen's Interval Relations
Allen's interval algebra is a qualitative calculus for temporal relations, but its thirteen base relations are crisp predicates over exact interval boundaries. This is inadequate f…
2026-09-17
- Objective vs. Search: Decomposing What Makes a Good Tokeniser
Two dominant tokenisation algorithms are used by modern language models: byte-pair encoding (BPE) and UnigramLM. These differ along two orthogonal axes: their optimisation objectiv…
2026-09-16
- A Zeroth-Order Paradigm for LLM Preference Alignment
Direct preference alignment methods are widely used to align large language models (LLMs) with human preferences because of their computational and memory efficiency. However, like…
2026-09-16
- Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation
Recent advances in video generation allow robots to learn manipulation trajectories from generated videos. However, these approaches produce purely kinematic trajectories that lack…
2026-09-16
- Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments
Language agents remain brittle in interactive environments, where success requires long-horizon state tracking, valid action execution, and recovery from failed steps. We extend Sw…
2026-09-16
- Affora: A Design System for Agent-Friendly Interfaces
Computer-use agents increasingly operate software designed for people, but interfaces often leave actions or task state unclear to machine readers. We present Affora, a design syst…
2026-09-16
- Flag Game: A Toy Model for Mechanistic Swarm Interpretability
Emergent coordinated behaviors of AI agents are starting to present critical safety risks. A key phenomenon driving these behaviors is the rapid formation and spread of beliefs abo…
2026-09-16
- rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference
Factory work is a promising early scenario for embodied AI: assigning repetitive manual jobs to robots has clear economic payoff, and a structured station keeps the jobs tractable …
2026-09-16
- Prepared Or Unprepared? Evaluating Healthcare Workforce Readiness for Clinical Adoption of Artificial Intelligence in Nigeria
Artificial intelligence (AI) is increasingly integrated into healthcare systems worldwide, yet its successful clinical adoption depends critically on workforce readiness, particula…
2026-09-16
- Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation
Radiologists follow heterogeneous reporting practices. Two radiologists examining the same image and identifying the same clinical findings might nevertheless compose superficially…
2026-09-16
- Securing quantum error correction against misleading advice from AI agents
Can an attacker turn influence over an artificial intelligence (AI) adviser into a harmful quantum error-correction update? We identify an ambiguity in passive syndrome records tha…
2026-09-16
- MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Education
Large vision-language models have achieved remarkable progress in multi-modal understanding, yet their capabilities in educational settings remain insufficiently evaluated. In AI-a…
2026-09-16
- Probabilistic Linear Explanations
Formal explainability provides mathematically grounded justifications for individual predictions. However, abductive explanations often exceed human cognitive limits by involving t…
2026-09-16
- Double descent is the principle of least action
The test error of a model plotted against its number of parameters $d$ falls, peaks when the model can just fit the training data, and falls again, exhibiting the double descent ph…
2026-09-16
- RLLBC-Lib: An Educational Code Library for Reinforcement Learning and Learning-Based Control
Reinforcement learning (RL) is an exciting concept as well as a remarkable success story worth sharing. However, RL builds on rather complex interactions between different objects …
2026-09-16
- Social Laws for Multi-agent Coordination in Stochastic Environments
In multi-agent environments, coordinating agents to prevent interference and ensure robust individual performance is a critical challenge. Previous research on social laws for mult…
2026-09-16
- Higher-order pruning of experts in mixture-of-experts language models
Mixture-of-Experts (MoE) language models suffer from large parameter counts, which create a significant memory bottleneck. Expert pruning is the most direct approach for reducing t…
2026-09-16
- Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking
Agent benchmarks are substantially more costly to evaluate than conventional LLM benchmarks. Benchmark compression is therefore a natural solution, yet existing methods primarily m…
2026-09-16
- ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions
Privacy evaluations of tool-using LLM agents often inspect a designated action, final response, or attacker report. These local proxies can miss unauthorized exposure elsewhere in …
2026-09-16
- Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection
When a large vision-language model misclassifies a harmful meme, the failure may reflect missing internal evidence or an inability to route represented evidence to its output. We d…
2026-09-16
- Taming the Agentic RAN: Stability-Guaranteed Arbitration of Autonomous AI Agents in O-RAN
The O-RAN control plane is becoming agentic: autonomous AI agents, deployed as rApps by different vendors, independently close control loops over shared radio resources. We demonst…
2026-09-16
- Agentic Societies Need a Social Harness
An agentic society is a collection of AI agents that coordinate autonomously across trust boundaries, on behalf of different principals whose objectives may only partially align. W…
2026-09-15
- ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. Scienc…
2026-09-15
- PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
Interactive control for video generation is moving from coarse prompts toward fine-grained, physically meaningful manipulation of dynamic scenes. Yet existing controllable methods …
2026-09-15
- When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control
Large language models can produce fluent answers when their factual support is weak. This paper introduces Chain-of-Self-Questioning (CoSQ), a prompt-only framework that makes answ…
2026-09-15
- LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs
Neural audio codecs are a key component in speech language modeling. However, their high frame rates lead to long sequence lengths, increasing computational costs. Dynamic frame ra…
2026-09-15
- ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation
Uncertainty estimation for Vision-Language-Navigation (VLN) models is a critical task since it can help identify ambiguous and unreliable predictions, enabling agents to make safer…
2026-09-15
- Verifiable Social Reasoning for LLM Assistants
LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (i) it requires setups where t…
2026-09-15
- LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX-2 adopts the Contextual Mec…
2026-09-15
- Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection
Despite the rapid uptake of black-box object detectors in marine mammal research and monitoring, explainability techniques are rarely integrated into conservation workflows. Furthe…
2026-09-15
- JustFit: 200K-Token LLM Serving on a 24 GiB Laptop with Just-in-Time State Management
Capable open-weight models make local coding and reasoning attractive, but their context and execution state strain laptop memory. We present JustFit, an MLX-based inference runtim…
2026-09-15
- Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback
Large language model (LLM) distillation aims to transfer the capabilities of a powerful teacher to a smaller student. Direct imitation, however, can also transfer the teacher's sys…
2026-09-15
- Decomposition Buys Integrity, Not Yield
Multi-agent systems split a task across a tree of agents and justify the split with folklore: smaller contexts, cleaner separation, parallelism. We ask what the split does to how m…
2026-09-15
- Evaluating Verified Autonomy in Quantum Engineering
Reliable quantum engineering is essential for turning quantum phenomena into practical technologies. As quantum platforms grow in scale and complexity, their characterization and o…
2026-09-15
- CareMirror: Bringing Caregiver Wellbeing into the Dementia Care Ecosystem
Family caregivers of people living with dementia shoulder emotional and practical responsibilities, yet their own wellbeing often remains peripheral to dementia care. We built Care…
2026-09-15
- Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging
Many learned sequential decision systems map the current state directly to an action. That shortcut becomes brittle when candidate actions are numerous, geometrically structured, a…
2026-09-15
- Tracking the Unseen: An Occlusion-Robust Framework for Target Tracking Under Full and Long-Term Occlusion
Real-time multi-object tracking systems remain highly vulnerable to full and long-term occlusion, where targets temporarily or completely disappear from the camera's field of view.…
2026-09-15
- Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure Instead
Small differences on coding-agent leaderboards are often read as an ordering of systems. We audit whether the published verdicts support this reading, using 254 SWE-bench submissio…
2026-09-15
- FlashVector: Agent for Hierarchical Model Serving Stack Optimization
Model serving is one of the largest cost drivers in production recommender systems. Maximizing its throughput requires navigating a deeply layered hierarchy: GPU kernels, the ML fr…
2026-09-15
- Where Should a Document Live: Context, Representations, or Parameters?
To answer questions outside of their pre-training data, large language models (LLMs) need access to new information, which can be presented in the context window as documents, enco…
2026-09-15
- Self-Emergence Agent Architecture:Behavior-Inertia HMM, Reflexive Metacognition,and Social-Contrastive Self-Modeling
Large language model (LLM) agents exhibit strong language-generation and problem-solving capabilities, yet suffer from three structural limitations: personality drift, non-evolutio…
2026-09-15
- Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection
Chain-of-thought (CoT) monitoring is a safety strategy where the reasoning of a large language model "actor" is inspected by a "monitor" (often another language model) for signs of…
2026-09-14
- Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science
Language models can produce plausible short proofs, but may still be unreliable on long-horizon research problems, where progress depends on a sequence of uncertain and interdepend…
2026-09-14
- The Router Within: Eliciting Native Skill Routing from a Frozen LLM
Skills extend an LLM agent beyond its parametric knowledge, and the gain they promise rests on picking the right one. Deployed harnesses route by preloading every skill's metadata …
2026-09-14
- Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale
Language-model agents increasingly operate over complete software repositories, yet cybersecurity evaluations primarily measure whether they can detect, reproduce, or repair vulner…
2026-09-14
- Recurrent GraphNeural NetworkswithSet-BasedAggregation
Recurrent GNNs iterate message passing to convergence, and their logical characterizations to date rely on multi-set aggregation, graded (counting) logics, and halting or acceptanc…
2026-09-14
- Pilot Early, Commit Late: A Real-Options Model of Enterprise AI Adoption under Rapid Technological Progress
Artificial intelligence presents firms with an unusual timing problem. The technology frontier is improving rapidly, implementation is partly irreversible, and organization-specifi…
2026-09-14
- SlipSense: Multimodal Tactile Learning for Low-Latency and Generalized Slip Detection
Slip detection is fundamental to dexterous manipulation, yet existing systems often lack precise characterization of detection latency and cross-platform generalization. We present…
2026-09-14
- Anatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRI
Deep networks trained on structural MRI for Alzheimer's disease (AD) staging often reach reasonable accuracy while attending to anatomically irrelevant regions, and multimodal mode…
2026-09-14
- Privacy-enhanced federated learning via asynchronous aggregation and local differential perturbation
This study proposes a privacy-enhanced federated learning framework to address secure collaborative training in distributed data environments. The framework integrates Dynamic Diff…
2026-09-14
- Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport
Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions. Flow policies can naturally represent such mu…
2026-09-14
- LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys
Rising societal and lifestyle complexity has been linked to a growing prevalence of mental distress worldwide. Educational institutions, workplaces, clinics, etc. collect large vol…
2026-09-14
- LongAgent: History-Guided Agentic Search for Longitudinal Outcome Prediction
Extracting informative representations from longitudinal data that can predict future outcomes remains a critical challenge in medicine. Medical datasets are inherently heterogeneo…
2026-09-14
- K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations
% !TEX root = ../main.tex People increasingly use large language models (LLMs) for mental health support, yet their safety in evolving, high-risk conversations remains poorly chara…
2026-09-14
- Before You Poll with LLMs: A Deliberative Diagnostic Framework
Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for silicon sampling, where LLM personas simulate public opinion a…
2026-09-14
- Per-Matrix Optimality Is Not Enough: Three-Level Optimization for Low-Rank LLM Compression
Per-matrix singular value decomposition (SVD) truncation is Eckart-Young optimal in the whitened Frobenius norm, but errors from independently compressed matrices compound through …
2026-09-14
- CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering
Retrieval-augmented generation (RAG) can improve access to complex information; however, retrieving evidence alone does not ensure that answers are grounded, citation-valid, or app…
2026-09-14
- AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery
Large language models have advanced automated algorithm discovery by synthesizing executable code, but existing frameworks trap them in rigid search pipelines with pre-defined cont…
2026-09-14
- Atria Dawn: The Dawn of Agentic Superintelligence
As AI agents become participants in the development of their successors, they reshape both the production of intelligence and the role of human researchers. We introduce Atria Dawn…
2026-09-14
- Delegating Authorization to Misaligned Agents: Coalitional Alignment and Safe Control
Long-running AI agents create a control problem: each action they take changes the state, which in turn affects the trajectory of future actions. If the agent is not fully aligned,…
2026-09-14
- When Should a World Model Move? Loss-Conditioned State Execution
We introduce loss-conditioned state execution, a model-agnostic method that decides whether to execute a world model's fixed feasible proposal or retain the current state. Predicti…
2026-09-14