Category
9,049 papers
AIBuildAI-2.5 is introduced, an agentic system that carries out the tree search with LLM agents and proposes a novel LLM-guided tree search, in which a judge scores each candidate on its expected improvement, grounding, and feasibility, and a selector ranks the pool of candidates from these scores and the state of the...
It is shown that the chat template works like a switch - when present, it turns this disclaimer voice up and experiential voice like"I feel"down, across 8 popular open-source instruct models up to 9B parameters in size, and there is a direction they can use to steer this voice.
Findings indicate that explicit, reversible context management in LLM-based agents can improve the efficiency of long-horizon agent reasoning without degrading task performance.
Language-model agents often reach a working solution and then fail to consistently deliver it. We study runtime policies: targeted natural-language instructions and action denials applied by the agent harness at states that preceded observed failures, without changing model weights or the user prompt. With this, keepin...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Across three models, two reasoning regimes, and two domains, four findings hold without per-turn reasoning: displaying accurate state is unreliable, an unverified ledger the agent writes itself beats an accurate checklist it is shown, directives help in proportion to the model's obedience, and enforcement needs no obed...
Orthrus is a serving system that performs heterogeneous batching within a unified inference loop that addresses the primary challenge lies in unifying embedding and generation workloads with conflicting computational patterns while optimizing batch composition for high performance.
For predicting aggregate engagement, a plain LLM ranker beats persona simulation - synthetic personas are not merely a weak predictor, they are worse than not using them.
It is shown that preference alignment preserves the human response distribution only under a restrictive condition, and no consistent evidence that real human preferences satisfy it, and human-likeness is established as an explicit dimension of alignment rather than something assumed to follow from preference alignment...
Retrieval-Augmented Generation (RAG) aims to enhance the trustworthiness of Large Language Models (LLMs) by grounding their outputs in external documents, often using inline citations for verifiability. However, the faithfulness of these citations -- whether the model genuinely uses a source to generate an answer -- re...
The adversarial robustness of three frontier large language models developed by Anthropic, Opus 4.8, Fable 5 and its successor Fable 5.1 is evaluated against four families of automated jailbreak attack across 7,826 harmful intents spanning a ten-category harm taxonomy.
Building a lexicon from discovered word-like units is a central goal in zero-resource speech processing. But do our evaluations provide a trustworthy indication of lexicon quality? A common metric, normalized edit distance, averages the phoneme edit distances between discovered units in each cluster. We show that this...
Ro is proposed, a rubric-guided process reward framework for stepwise model routing that consistently outperforms strong baselines and achieves better accuracy and cost trade-offs.
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.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
