Category
9,568 papers
WebPageBench is an open framework for evaluating web agents in which every task is verified from the interface's own event log, and sensitivity to interface form can be measured under a fixed task specification.
Tool agents use large language models to act through external tools, yet successfully executed calls can still leave user requests unfulfilled. Tool-agent repair seeks alternative call sequences that execute successfully and fulfill the original requests. However, repair requires exploring both operation choices and th...
Block Verification-aware loss (BV loss), a training objective designed to maximize the expected acceptance length of a drafted sequence, outperforms tokenwise acceptance objectives such as TV loss and LK loss, and its gains extend to token verification and greedy decoding.
Overall, representation engineering does not generally replace behavioral safeguards, but offers practical advantages under specific conditions and can provide complementary safety benefits.
Reach audiences
Advertise in front of researchers, engineers, and readers.
SeLMRoute is introduced, a routing framework that separates the extraction of candidate-independent semantic evidence from the learning of candidate performance and the application of deployment objectives and achieves the highest mean performance among the evaluated semantic, dense, lexical, and domain-level represent...
This work transfers the same failed source before and after accepted repair to a fixed target, alongside independent execution, alongside independent execution in the ThinkingBox and APEX regimes to establish comparable aggregate correction benefits.
Nudgeability offers a simple, post-training-free way to evaluate both sensitivity and targeting as endogenous self-reflection mechanisms mature as endogenous self-reflection mechanisms mature.
FlyBy is introduced, a selective querying framework, and 4B and 8B variants are trained to reason first, diagnose what remains unresolved, and, at a knowledge bottleneck, query stronger models whose parametric knowledge extends beyond its own.
ControlScope compares continuing generated code, editing the next tool call's data arguments, and replacing the unfinished workflow from the same public execution state to evaluate one-time and repeated reviews across filesystem tasks, ALFWorld, and AppWorld.
Artificial-intelligence (AI) agents hold promise for automating bioimage analysis, yet no benchmark evaluates whether they can carry out real-world analyses end to end. Such analyses are hard for agents because 2D images, 3D volumes and time-lapse sequences are often too large to read as context, so an agent must choos...
A pre-registered study on held-out LoCoMo conversations and LongMemEval finds Jev selects as accurately as an LLM reranker at a third of the latency, and more accurately than a multi-call graph traversal.
PainterBench, a benchmark that ports the incomplete-drawing task to the agentic setting, is introduced and ViDrA-adapted, an automated scorer that predicts human creativity ratings of agent drawings, is presented.
Natural Language Processing
Our most capable vision-language-action model enhances robot dexterity, reliability, and safety
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
