Category
9,568 papers
CUA-Recovery is introduced, a benchmark comprising test and training suites across multiple desktop applications using ReRail, a framework for synthesizing long-horizon tasks and trajectories in a persistent desktop environment that shows that agents struggle both to recognize inherited errors and to complete the task.
Large language models (LLMs) can influence user trust and decision-making through subtle linguistic cues, yet the behavioral effects of manipulative outputs remain poorly quantified. We introduce a behavioral computing framework for measuring \textit{behavioral vulnerability}, defined as users'susceptibility to manipul...
Agent platforms are starting to improve their own agents: they read a deployed agent's execution traces, derive a change, have an automated verifier approve it, and release it with no human author. How much of this loop can safely run without a human? We propose two quantities a platform can measure. Verifier strength...
On-policy distillation (OPD) can succeed with surprisingly few training questions, motivating a view of questions as carriers of distributional knowledge transfer. How can we assess whether a newly generated question is valuable for distillation, and learn to generate better questions---without access to its correct an...
Reach audiences
Advertise in front of researchers, engineers, and readers.
RiseHarness is a framework for iteratively improving agent harnesses with model weights fixed that treats a specific model as the unit of harness adaptation, studying how changes to shared interaction mechanisms can make existing capabilities more reliable across tasks.
LLM agents can improve across tasks without updating model parameters by storing experience from their own executions in external memory and reusing it to guide later decisions. A central design question is whether to retain only observed trajectories and outcomes or also the rules, summaries, and skills inferred from...
TEX, a collaborative test-time scaling framework based on execution-driven cross-validation that parallelizes agents to generate tests and patches, cross-executing each test against every patch to form a feedback matrix, enabling objective validation without verbose trace sharing.
Analyzing merchant transaction histories requires dynamic temporal filtering, entity resolution, and aggregation over irregular event streams--operations poorly captured by static tabular or time-series forecasting benchmarks. We introduce TxnQA, an analytical QA benchmark comprising 27 task families (81 templates) alo...
OWP is proposed, a training-free framework that shifts hallucination mitigation from output-level manipulation to conflict-conditioned representation rebalancing and adaptively rebalances fused representations by suppressing misleading priors and restoring ignored evidence before decoding.
ReuF2F is introduced, a Lean 4 benchmark of 244 formalized open problems drawn from Research Experiences for Undergraduates (REU), spanning entry-level open research problems across a broad range of mathematical subfields and adopts a standard coding-agent evaluation setting.
Results provide preliminary evidence that strategic preference optimization can improve strategic quality while preserving teacher-consistent behavior and compare it with SFT, DPO, GRPO, and GSPO.
Pre-trained language models have significantly improved sentence representation learning, yet their embeddings remain sensitive to textual perturbations such as synonym substitution, masking, and word dropout. This work proposes a lightweight Contrastive Denoising Autoencoder (CDAE) that refines pre-trained BERT embedd...
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.
