AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
8,786 papers
Retrospection-Only Fine-Tuning (ROFT), a minimal online procedure designed to isolate the effect of explanation-only training on subsequent behavior, is studied, showing that learning to explain can also improve learning to do and motivating further study of explanation-to-action transfer.
AI Night-Scientist is introduced, an agentic framework that uses reinforcement learning to teach models when and how to depart from predictable reasoning to suggest creativity is a learnable, multi-level ability that can be shaped to help researchers reach ideas beyond those typically explored by LLMs.
TCSAlgBench provides a refreshable testbed for measuring progress in model reasoning and studying how agent workflows support research-level proof discovery, and evaluates ten model configurations from four families under direct inference and prover-verifier discussion, and compares four agent workflows under matched m...
This work introduces artifact-mediated propagation, where adversarial content introduced through an artifact is stored in an assistant's persistent memory, reproduced in a subsequently created artifact, and acquired by another assistant that later reads it.
Reach audiences
Advertise in front of researchers, engineers, and readers.
While LLMs show promise in general reasoning, symbolic planning in chemistry remains a bottleneck. Direct ''SMILES-to-PDDL'' attempts fail because they force models to juggle chemical analysis and planning-language structuring simultaneously. We hypothesize that this failure stems from a lack of intermediate abstractio...
This work introduces SAGE (Self-Adapting Group of Experts), a training-free framework that uses answer agreement, prefix consistency, and reciprocal peer review to select a strategy donor and transfers the selected donor's reasoning strategy to the other agents while preserving their original roles.
While Large Reasoning Models (LRMs) excel at complex reasoning, alignment through reinforcement learning often induces systemic overconfidence. In production environments, where logits may be unavailable, robust black-box uncertainty quantification (UQ) is essential for trustworthiness and safety. Focusing on question-...
EvoIn is an agent fine-tuning framework that bridges evolution and internalization, and consistently enables agents to learn stronger decision-making procedures, raising the pass rate by 10.9 points in-domain and by 9.2 points out-of-domain.
This work proposes 5W1H+Which, a semantic indexing design that separates content extraction from ontology binding, and distinguishes business valid time, system knowledge time, and operational traces, and uses dependency records to support binding revalidation and the maintenance of derived conclusions.
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.
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.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
