TTHE: Test-Time Harness Evolution
arXiv:2607.08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context,
Knowledge catalogue
arXiv:2607.08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context,
arXiv:2607.08768v1 Announce Type: new Abstract: The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operati
arXiv:2607.07527v1 Announce Type: cross Abstract: Artificial intelligence (AI) is a double-edged sword: while it has achieved remarkable success across a wide range of domains, its deployment also cal
SpaceX's AI division has launched Grok 4.5, positioned as their first Opus-class model following the acquisition of Cursor. The release represents a significant capability upgrade in SpaceX's AI offer
>be stardust >float around the universe for billions of years >somehow become human >gain consciousness >immediately start asking 'WHY?' >never stop >discover fire >discover math >discover atoms >disc
arXiv:2607.06691v1 Announce Type: new Abstract: Human-human collaboration is a fundamental aspect of everyday life, essential to success in a wide range of goal-directed activities from household task
arXiv:2607.06940v1 Announce Type: cross Abstract: The remarkable performance of large language models (LLMs) in linguistic tasks underscores an urgent need for comprehensive evaluation of their respon
arXiv:2607.07026v1 Announce Type: new Abstract: Constrained decoding is essential for serving LLMs, ensuring that generated outputs follow specific structures such as JSON schema-formatted function ca
arXiv:2607.06603v1 Announce Type: cross Abstract: The notion of algorithmic fairness has been actively explored from various aspects of fairness, such as counterfactual fairness (CF) and group fairnes
arXiv:2607.06820v1 Announce Type: new Abstract: Recent advances in AI for Mathematics have focused largely on autoformalization and theorem proving, leaving the role of Computer Algebra Systems (CAS)
arXiv:2607.07321v1 Announce Type: new Abstract: Tool utilization enables Large Language Model (LLM) agents to interact with the real world and resolve complex tasks. However, existing agent frameworks
arXiv:2501.05711v4 Announce Type: replace Abstract: Vision Language Models (VLMs) have achieved strong performance across a wide range of video understanding tasks. However, their viewpoint-invariant
GPT-5.6 is OpenAI's advanced language model featuring improved scalability and performance capabilities. The model is designed to handle increasingly complex tasks and larger-scale applications, adapt
Grok 4.5 is an AI model developed by xAI, Elon Musk's artificial intelligence company, announced via his X platform. The model represents an advancement in xAI's Grok AI assistant line, likely featuri
Grok, Elon Musk's AI assistant developed by xAI, has integrated with Cursor, a popular AI-powered code editor, enabling developers to leverage Grok's capabilities for coding tasks and assistance. This
arXiv:2607.07357v1 Announce Type: cross Abstract: Effective social robot navigation requires sensitivity to human behavior, often revealed through subtle skeletal cues like gait and orientation. We pr
arXiv:2607.07695v1 Announce Type: new Abstract: We introduce institutional red-teaming, an evaluation methodology for testing deployment rules in multi-agent AI: hold the agents, objectives, and task
arXiv:2607.07383v1 Announce Type: new Abstract: Knowledge-based Visual Question Answering (KB-VQA) requires models to retrieve visual entities matching the query image from large-scale encyclopedic kn
Open source powers everything in America. We must fight any and all attempts to restrict it in the age of AI. We must never surrender to the short-sighted safetyists and hawks. Open source is the enti
@OpenAI released GPT 5.6 today and we ran a day 0 benchmark in ParseBench to test improvements in document understanding. The new family of models continues to excel at reading text and tables, but co
arXiv:2607.06618v1 Announce Type: cross Abstract: Following the CMIVQA, MMI-VQA, and M4IVQA challenges in NLPCC 2023--2025, we introduce the Difficulty-Aware Medical Instructional Video Question Answe
arXiv:2607.06655v1 Announce Type: cross Abstract: In this report, we present Pelican-VLA 0.5, a unified VLA model that integrates vision-language understanding, future-frame generation, and action pre
arXiv:2607.07076v1 Announce Type: new Abstract: Imitation learning has enabled remarkable progress in robotic manipulation, especially with diffusion and flow-based policies that generate complex visu
arXiv:2601.00086v3 Announce Type: replace Abstract: Large language models (LLMs) often struggle to use tools reliably in domain-specific settings, where APIs may be idiosyncratic, under-documented, or
arXiv:2607.07508v1 Announce Type: cross Abstract: Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs). Previous RL pipelines for LLMs were mos
Socialists imagine a class struggle. In their made-up fantasy the CEO is in competition with low level workers, the wealthy entrepreneur is stealing from the underpaid nurse. In reality, workers do no
arXiv:2607.07386v1 Announce Type: new Abstract: Linear attention models allow a fixed state size and a fixed amount of compute per token. However, due to their limited state size, linear attention mod
arXiv:2607.07089v1 Announce Type: new Abstract: Relational Deep Learning (RDL) has become a standard methodology for machine learning on relational databases: the database is encoded as a heterogeneou
arXiv:2607.07287v1 Announce Type: new Abstract: Dexterous manipulation in everyday environments requires both anticipation and reaction: a robot must predict how contact should evolve while rapidly co
arXiv:2607.06807v1 Announce Type: cross Abstract: While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities
arXiv:2607.06838v1 Announce Type: new Abstract: Humans can navigate an unfamiliar city and gradually form a coherent spatial mental map spanning tens of square kilometers. Can AI build spatial represe
arXiv:2602.13213v2 Announce Type: replace Abstract: Commercial insurance underwriting is a labor-intensive process that requires manual review of extensive documentation to assess risk and determine p
arXiv:2607.06101v1 Announce Type: cross Abstract: AI coding agents are rapidly reshaping how software is built, with developers increasingly delegating substantial coding tasks to autonomous agents in
arXiv:2607.06445v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly utilized as the conditioning backbone for diffusion-based image editing due to their remarkable multimo
arXiv:2607.05614v1 Announce Type: cross Abstract: Document comprehension is a challenging yet impactful task for Multimodal Large Language Models, especially as these systems see growing adoption in r
arXiv:2510.19771v4 Announce Type: replace Abstract: LLM-based agents are increasingly moving towards proactivity: rather than awaiting instruction, they exercise agency to anticipate user needs and so
arXiv:2607.05790v1 Announce Type: new Abstract: Tool-augmented large language models extend their capabilities beyond parametric knowledge through external tools, but tend to invoke them unnecessarily
arXiv:2607.05625v1 Announce Type: new Abstract: Wound monitoring is a critical yet underserved clinical challenge, where timely identification of severe adverse events (SAEs) such as infection, tissue
arXiv:2607.06233v1 Announce Type: new Abstract: LLM-powered data agents are playing an increasingly important role in data-driven decision making. However, existing data agents struggle to generalize
arXiv:2606.08048v1 Announce Type: cross Abstract: Diffusion language models (DLMs) offer substantial speed advantages through parallel decoding, but the lack of token dependencies limits generation qu
Finally can share that I have been testing GPT-5.6 early and oooo boy. It is an execution beast. So much so that I think 5.6 is the absolute wrong name considering how big of a leap this felt to me. T
arXiv:2607.05573v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) enable the automatic generation of parametric 3D designs from natural-
arXiv:2607.06519v1 Announce Type: new Abstract: Long-context LLM inference is increasingly limited by the memory and bandwidth cost of KV caches, yet aggressive compression can remove the layer-specif
arXiv:2607.06403v1 Announce Type: new Abstract: Despite recent progress of VLA foundation models, the disparity between laboratory conditions and real-world applications continues to impede their prac
arXiv:2607.05563v1 Announce Type: new Abstract: Interpretable explanation methods in Artificial Intelligence aim to uncover the underlying causes and their effects, enabling a deeper understanding of
arXiv:2607.05794v1 Announce Type: new Abstract: Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfa
arXiv:2607.06452v1 Announce Type: cross Abstract: Biomedical question answering requires not only accurate extraction of information from scientific literature but also reliable integration of evidenc
arXiv:2607.05543v1 Announce Type: cross Abstract: Semantic occupancy provides a structured spatial memory for embodied indoor agents by jointly representing occupied regions, observed free space, unkn
arXiv:2607.06001v1 Announce Type: new Abstract: We report a pre-registered, two-part experiment on small economies of frontier language-model agents (Claude Opus 4.8), testing two quantitative predict
Introducing GPT‑Live OpenAI finally upgraded the model used by ChatGPT voice mode! I've had preview access for a few weeks in the iPhone app, and the new model is very impressive. It also has the abil
arXiv:2607.06157v1 Announce Type: cross Abstract: Deliberation plays a crucial role in collaboration; when humans work together, they naturally engage in communication to align information and reach a
arXiv:2607.06160v1 Announce Type: cross Abstract: Synthesizing long-context supervised fine-tuning (SFT) data is a scalable way to enhance the long-context understanding of large language models (LLMs
arXiv:2607.06127v1 Announce Type: new Abstract: We present LLM4SDM, the first study of open-source smaller language models (OS-sLLMs) for automated assessment of shared decision making (SDM) using the
// Memory becomes an action space // Great paper on long-term memory for agents. (bookmark it) In short, it's discusses the use of a learned policy for using memory at the right granularity. Most memo
arXiv:2607.05438v1 Announce Type: cross Abstract: Multimodal retrieval-augmented generation (RAG) grounds a generator in evidence drawn from heterogeneous modalities -- text, tables, and images. The d
arXiv:2512.23020v3 Announce Type: replace-cross Abstract: 3D visual grounding aims to locate objects based on natural language descriptions in 3D scenes. Existing supervised methods are limited by gen
arXiv:2607.06544v1 Announce Type: new Abstract: As Artificial Intelligence (AI) makes inroads into different parts of the Indian subcontinent, there is significant interest in studying how AI impacts
arXiv:2607.06411v1 Announce Type: cross Abstract: Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of
Salesforce Inc. today announced new updates for Slackbot, the company’s personal artificial intelligence agent in Slack, giving it full access to every part of the Salesforce ecosystem. “Slackbot can
arXiv:2607.05541v1 Announce Type: cross Abstract: Reinforcement Learning is commonly used to train large language models using environmental feedback. In applied settings, the environment usually prov