Explore tools, prompts, skills, news and resources related to AI 第17页.
Prompt works related to AI 第17页
Latest articles, prompts, use cases and editorial content about AI 第17页
This paper introduces Agentic Semi-Supervised Learning (AgentSSL), which frames semi-supervised learning as a program search problem and tests MLE agents under scarce labeled data and abundant unlabeled data. The agents...
This paper introduces a sketching algorithm that estimates leave-one-out (LOO) context attribution for language models, reducing the number of model evaluations from n to O(sqrt(log(1/epsilon))/epsilon) under a stability...
Researchers built a multi-sub-task coding setting to test whether LLMs encode goals as internal representations that guide action across different execution paths. They localized an encoding of the next sub-goal in the o...
Metal Sandbox is infrastructure for running Apple Metal kernel coding agents on Apple Silicon Macs, combining restricted per-instance file access, native command execution, and command-level scheduling across interconnec...
Researchers introduced GeoWorld, a controllable geographic environment platform for LLM agents, and LiveGeo, a benchmark for evaluating reliable decision-making as real-world geographic states evolve. LiveGeo requires ag...
Ballad is an online bandit algorithm that orchestrates a pool of LLMs during automated heuristic discovery, adaptively selecting which model to invoke at each step. The method uses a selection policy favoring rare high-s...
This paper examines how user adaptivity complicates evaluation of interactive LLM systems, since users change their prompts and tasks after observing model responses. It distinguishes between common-distribution and indu...
OpenAI announced a ChatGPT digital wallet that lets its "dot" assistant buy things online without directly accessing shoppers' card details. The company built the wallet in partnership with Visa, Mastercar...
This arXiv paper studies regret minimization in episodic Adversarial Markov Decision Processes with unknown transitions and bandit feedback. It proposes a technique called introduced feedback delays, which estimates the...
This arXiv paper compares three decision models and three general LLMs as actors and judges on ALFWorld, and also uses JEV as a teacher on ALFWorld and WebShop. As actors, all six models are pulled away from a subgoal th...
This arXiv paper measures whether citations in retrieval-augmented generation actually reflect retrieved context or instead come from a model's parametric memory. Using counterfactual value substitution, it finds th...
The paper introduces PECA, a method that adds a differentiable conciseness term to QLoRA supervised fine-tuning for smaller language models. Instead of relying on preference data, reward models, or proprietary teachers,...
The paper examines whether small language model agents can be trusted to write the security artifacts used by enforcement-based prompt-injection defenses. Across 15 open-weight models, it reports that model-written polic...
SALA introduces semantically aligned latent actions to improve cross-embodiment learning for embodied foundation models. Without paired data, it uses language descriptions of unpaired human and robot clips to estimate se...
Researchers compared grid-connected and off-grid power designs for AI data centers across the continental U.S., including AC- and DC-coupled solar-plus-storage, islanded natural gas, and grid interconnection. Using an op...
Researchers introduce MAPE, a framework that evolves complete agent memory programs from minimal seeds using a standardized lifecycle interface and an iterative diagnosis-proposal loop. On LoCoMo and LongMemEval, MAPE re...
Researchers introduce a benchmark that injects objective, localizable errors of four types at three severity levels into real papers and measures reviewer detection by error type and severity, along with false-positive r...