Category
9,049 papers
C3M is presented, a cross-session multimodal memory organization that maintains a bounded active index over persistent source text-image evidence in a bounded, query-blind memory budget for cross-session long-horizon tasks.
The results chart an engineering path toward recursive self-improvement, in which humans distill the principles of model building, agents operationalize them through evidence-driven experimentation, and each generation of AI becomes a more capable architect of the next.
PartHackBench provides a certified control for testing whether evaluator credit changes while all benchmark-defined task-relevant progress remains fixed, and provides a certified control for testing whether evaluator credit changes while all benchmark-defined task-relevant progress remains fixed.
Large language models (LLMs) are increasingly deployed as multi-turn agents that must sustain goals, use tools, and adapt to other agents over extended interactions. However, existing research lacks auditable, multi-turn, multi-factorial experiments that quantify LLM behavior under explicit constraints, with time-resol...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Together, the survival and rationale analyses reveal distinct temporal reliability regimes and model-specific"failure fingerprints", offering an evaluation lens for diagnosing inconsistency in multi-turn agent behavior.
RLCDAlignBench is presented, which benchmarks Jev on ten alignment failures: sycophancy, jailbreaks, deception, prompt injection, hallucination, privacy violation, social bias, reward hacking, concealing uncertainty, and power seeking.
CAR-bench evaluates whether tool-using agents stay reliable under real-world uncertainty, executing every tool inside the evaluator so that each tool-result exchange is a separate agent round-trip. A conventional next-action agent can batch parallel tool calls, but a chain of dependent calls costs it one model call per...
Domain-specific RAG improved evidence grounding and response quality for cancer registry questions while enabling citation-supported assistance across complexity levels, and demonstrates the potential of human-centered, citation-grounded AI to support cancer registrars while preserving human oversight for final coding...
This work introduces MeshHeal, a fully decentralized self-healing framework that couples ability-matched peer review across two timescales and introduces Model-Backed MAS Evaluation, which ties ability assignments to execution models, since prompt-based ability assignments alone can leave routing errors hidden.
A behavioral stress test showing that more reasoning is not always better; forecasting agents should first estimate which evidence source deserves control, routing policies should themselves adapt under auditable constraints, and reproducibility artifacts are available at https://github.com/louiswang524/forcastagent.
WARP is introduced, a family of post-retrieval algorithms that calibrate retrieved evidence to the population's opinion distribution, and its domain-matched variants reduce distributional error by at least 43% with sub-second latency.
The limits of algorithmic safety verification for Turing-complete self-modifying systems, the class in which recursive self-improvement takes place, are established, both for a fixed system and across its own modification.
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.
