arXiv AI
Jul 2
GameDevBench: Evaluating Agentic Capabilities Through Game Development
arXiv:2602. 11103v2 Announce Type: replace Abstract: Despite rapid progress on coding agents, progress on their multimodal counterparts has lagged behind.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv Machine Learning
Jul 2
Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization
arXiv:2607. 00479v1 Announce Type: new Abstract: Transformer-based large models have demonstrated remarkable generalization abilities across different tasks by leveraging a context-aware attention module for in-context learning.
arXiv AI
Jul 2
EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards
arXiv:2607. 00218v1 Announce Type: cross Abstract: Vision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories.
arXiv AI
Jul 2
ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis
arXiv:2607. 00041v1 Announce Type: cross Abstract: Multi-agent LLM systems can decompose software-engineering work into planning, generation, validation, and repair, but a narrower systems problem remains: before any governed shared mutation is applied, a system must decide which concurrently formed write intents may proceed in parallel, which require deterministic composition or serialization, and which must take a fail-closed path.
arXiv Machine Learning
Jul 2
Zero-Shot Distracted Driver Detection via Vision Language Models with Double Decoupling
arXiv:2601. 08467v2 Announce Type: replace-cross Abstract: Distracted driving is a major cause of traffic collisions, calling for robust and scalable detection methods.
arXiv AI
Jul 2
Mapping the Evaluation Frontier: An Empirical Survey of the Bias-Reliability Tradeoff Across Eleven Evaluator-Agent Conditions
arXiv:2607. 00304v1 Announce Type: cross Abstract: The bias-reliability tradeoff conjectures that LLM evaluation systems are constrained in (gamma, H, CV) space, where evaluator coupling (gamma), strategy diversity (H), and small-sample measurement reliability (CV(N)) cannot be simultaneously optimized at fixed sample size N.
arXiv Machine Learning
Jul 2
Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers
arXiv:2601. 11641v3 Announce Type: replace-cross Abstract: While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers to practical deployment.
arXiv AI
Jul 2
Structural Enforcement of Statistical Rigor in AI-Driven Discovery: A Functional Architecture
arXiv:2511. 06701v3 Announce Type: replace-cross Abstract: AI-Scientist systems risk manufacturing spurious discoveries through uncontrolled multiple testing.
arXiv AI
Jul 2
Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows
arXiv:2607. 00828v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate queries, invoke tools, and construct analytical workflows.
arXiv AI
Jul 2
A Two-stage Transformer Framework for Temporal Localization of Distracted Driver Behaviors
arXiv:2603. 21048v2 Announce Type: replace-cross Abstract: The identification of hazardous driving behaviors from in-cabin video streams is essential for enhancing road safety and supporting the detection of traffic violations and unsafe driver actions.
arXiv AI
Jul 2
Self-conditioned Flow Map Language Models via Fixed-point Flows
arXiv:2607. 00714v1 Announce Type: cross Abstract: Self-conditioning is a core technique that enhances continuous flow-based language models, where the model learns to denoise generated text by conditioning on its own denoising estimate.
arXiv AI
Jul 2
Recovering Input Text from Hidden States: Study of Gradient-Based Inversion of Decoder-Only Language Models
arXiv:2607. 00852v1 Announce Type: cross Abstract: This work studies the hidden-state inversion problem: recovering the original input token sequence of a decoder-only language model from its last-layer hidden states.
arXiv AI
Jul 2
LLMs in the Real World: Evaluating "AI" in Emergency Contexts
arXiv:2607. 00019v1 Announce Type: cross Abstract: This paper offers a call to action.
arXiv AI
Jul 2
Text Over Image: Auditing Multimodal Robustness in Synthetic Medical Image Detection
arXiv:2606. 25375v2 Announce Type: replace-cross Abstract: With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud.
arXiv AI
Jul 2
SkillSelect-Serve: Budget-Controllable and QoS-Aware Skill Service Recommendation and Composition for Small LLM Agents
arXiv:2607. 00011v1 Announce Type: cross Abstract: Reusable skill libraries are becoming important infrastructure for large language model (LLM) agents, yet existing selection methods often treat skills as retrievable documents and return fixed top-k lists.
arXiv AI
Jul 2
Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework
arXiv:2607. 00010v1 Announce Type: cross Abstract: Conversational recommender systems (CRSs) are a core component of next-generation intelligent recommender systems because they enable users to actively elicit preferences, clarify intentions, and adapt recommendations in real time.
arXiv AI
Jul 2
SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests
arXiv:2607. 00990v1 Announce Type: cross Abstract: Large language model (LLM)-based software engineering agents are increasingly developed to resolve software issues by generating patches from issue reports and code repositories.
arXiv AI
Jul 2
Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use
arXiv:2607. 01084v1 Announce Type: new Abstract: While Large Language Model (LLM) agents demonstrate proficiency in static benchmarks, their deployment in real-world scenarios is hindered by the dynamic nature of user queries, tool sets, and interaction dynamics.
arXiv AI
Jul 2
Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique
arXiv:2407. 10887v4 Announce Type: replace-cross Abstract: Growing concerns over the theft and misuse of Large Language Models (LLMs) underscore the need for effective fingerprinting to link a model to its original version and detect misuse.
arXiv AI
Jul 2
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
arXiv:2607. 01002v1 Announce Type: cross Abstract: In long-context use, large language models frequently synthesize answers from the meaning of a relevant context span rather than literally copy-pasting them.