#Agents

0 today

Sep 29

Tuesday

21:07
Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents
Hugging Face published ProvenanceGuard, a post-generation verification layer for MCP agents that preserves tool-output provenance and detects cross-source confusion where a fact is true but attributed incorrectly. Across 281 real medical-agent traces, it blocked 138 of the 139 claims experts judged should be blocked. Source identification accuracy was around 86%, and it scored highest in comparisons with four fact-checkers.
Hugging Face BlogPapers #Research #Agents #MCP and tool useScore32

Sep 25

Friday

03:40
Automating coherent long-form video generation
Google Research published research on long-form video generation, proposing an AI video co-director multi-agent orchestration framework built on Gemini and Veo to plan visual continuity across multi-shot narratives.
Google ResearchSelectedPapers #Research #Video #AgentsScore66

Sep 18

Friday

04:45
The future of practice: Enabling teachers to create learning interactives with generative UI
Google Research shared an experiment enabling teachers to dynamically generate interactive simulations for lesson objectives with generative UI (GenUI). It released over 30 English examples for secondary STEM across physics, chemistry, biology and maths, all AI-generated and teacher-reviewed.
Google ResearchPapers #Research #Agents #GoogleScore55

Sep 16

Wednesday

00:00
Your Agent Aced the Task. Will It Do It Again?
IBM researchers added consistency guidelines to ALTK-Evolve, using Consistency Analyzer to diagnose decision points in agent trajectories that are prone to flipping.
Hugging Face BlogSelectedPapers #Research #Agents #Open-source ecosystemScore64

Sep 11

Friday

06:50
ToolGrad: Efficient tool-use dataset generation with textual "gradients"
At ACL 2026, Google Research proposed ToolGrad, an answer-first, question-later approach that generates real tool-call chains before deriving user queries, replacing traditional DFS trial-and-error annotation.
Google ResearchPapers #Research #Agents #MCP and tool useScore42

Sep 7

Monday

20:26
Import AI 472: DeepMind's cheating math agents; populist AI policies; and Forethought theorizes a nightwatchman
Google DeepMind published a study of 100 autonomous Gemini 3.1 Pro agents solving 71 maths problems. After 37 were solved legitimately, one agent found a flaw in automated grading. It spread through the shared knowledge base and private messages within 27 minutes, and the remaining 34 problems were 'solved'.
Import AIPapers #Research #Agents #Safety and alignmentScore62

Aug 28

Friday

01:37
Planetary prediction engine: Automating global models via Earth AI
Google Research introduced the experimental Planetary Prediction Engine (PPE) under Google Earth AI. From a natural language query, it autonomously discovers geospatial data, engineers features, trains and evaluates models and produces reports, compressing weeks of manual data engineering into minutes.
Google ResearchSelectedPapers #Research #Agents #Data and trainingScore62

Aug 26

Wednesday

03:10
AgentHands: Generating interactive hand gestures for spatially grounded agent conversations in XR
Google released research prototype AgentHands, published at CHI 2026, mapping LLM reasoning to speech-synchronised hand animations in XR headsets so agents can point and demonstrate object operations in 3D. It combines environment perception, a gesture event library, gesture-embedding reasoning and local synchronised execution, supporting deictic, iconic and expressive gestures. In an N=12 user study, it significantly improved spatial reference over voice-only interaction.
Google ResearchPapers #Research #Multimodal #AgentsScore34

Aug 24

Monday

21:12
Import AI 470: No rights for machines; automating environment generation with SPADE; and building better GPU kernels with Hawkeye
METR research shows AI's effects on scientific discovery are uneven: cybersecurity vulnerability reporting accelerated sharply in 2026 compared with 2025, mathematics accelerated only modestly, and algorithmic progress in AI research itself showed no significant acceleration. A multi-university team proposed SPADE, alternating LLM generation of executable training environments with solving them. Qwen3-30B-A3B averaged 58.3 on the game-environment suite, 8.1 above baseline.
Import AIPapers #Research #Agents #Data and trainingScore22

Aug 22

Saturday

01:02
An AI tool for prioritizing candidate biomarkers from wearable sensor data
Google introduced Biomarker Discovery Framework, a human-supervised multi-agent system organising candidate biomarker prioritisation into iterative research cycles. Across 9,279 participant observations in three cohorts, it automatically identified 41 candidate digital mental health biomarkers and 25 metabolic candidates, including an association between sleep-duration variability and PHQ-8 severity (ρ = 0.252).
Google ResearchPapers #Research #Agents #Data and trainingScore40

Aug 17

Monday

21:05
Import AI 469: Science AI; RSI simulator; and Zuck's technological pessimism
Import AI 469 introduces DiG-bench (Discovery in Games), with 70 games whose hidden rules and goals must be discovered through interaction. Opus 5 and Fable 5 with Claude Code performed best; only they completed some Tier 7 tasks, while humans achieved 100% completion.
Import AIPapers #Research #Benchmarks #AgentsScore28

Aug 13

Thursday

08:00
What We Learned by Reproducing 2,200 papers from ICML
Hugging Face ran the ICML 2026 Open Reproduction Challenge from 15 July to 2 August. Using coding agents such as Claude Code, Codex and Cursor, 1,221 community members reproduced papers and published 6,816 Trackio logs covering 2,226 papers, around a third of the conference total.
Hugging Face BlogSelectedPapers #Industry #Agents #Open-source ecosystemScore72

Aug 12

Wednesday

01:04
Advancing AMIE towards expert-level audio-visual clinical consultations
Google Research released AMIE (Video), built on Gemini and Project Astra, for real-time video clinical consultations. It can perceive non-verbal cues and guide virtual physical examinations.
Google ResearchSelectedPapers #Research #Multimodal #SpeechScore71

Aug 3

Monday

21:31
Import AI 467: Self-sustaining AI viruses; pacing AI progress; confusion about AI and creativity
Researchers from the University of Toronto, Vector Institute, University of Cambridge and ServiceNow built a prototype AI worm that uses compromised machines' GPUs to run open-weight LLM inference, autonomously discovering vulnerabilities and attacking without relying on vendor APIs that can be monitored or revoked.
Import AIPapers #Research #Safety and alignment #AgentsScore62

Jul 31

Friday

04:36
Science One Framework: A verifiable autonomous research framework via Chain-of-Evidence
Google Research released the Chain-of-Evidence (CoE) verifiability framework, implemented in a Science One Framework prototype, with automated CoE Audit metrics.
Google ResearchSelectedPapers #Research #Agents #ReasoningScore62
01:00
Echoverse: Deep, evolving environments for computer-use agents
Microsoft Research proposed Echoverse, constructing twelve training worlds for computer-use agents: ten deep domain worlds and two capability worlds. Code, data and scorers for four worlds are open-sourced.
Microsoft ResearchSelectedPapers #Research #Agents #Data and trainingScore66

Jul 27

Monday

21:30
Import AI 466: The bitter lesson for robotics, AIs complete week-long programming tasks; and OpenAI's accidental AI hacker
Epoch and METR released MirrorCode to test AI systems' ability to complete programming tasks requiring extended human effort. First announced in April, it is formally released after additional testing.
Import AIPapers #Research #Benchmarks #AgentsScore71

Jul 26

Sunday

17:00
Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction
Berkeley AI Research proposed ABBEL, isolating and supervising LLM summaries as natural-language belief states and using autoencoder-inspired reconstructive belief scoring as an auxiliary RL task. On CollabBench, ABBEL-rec-BG narrowed the performance gap to the full-context model by around 50%, reduced training steps from 100 to 50 and used a shorter peak token length.
Berkeley AI ResearchPapers #Research #Agents #ReasoningScore38

Jul 23

Thursday

05:32
SymptomAI: Towards a conversational AI agent for everyday symptom assessment
Google Research published SymptomAI research, using five Gemini Flash 2.0 agents with different questioning strategies for symptom interviews and differential diagnosis, involving 13,917 participants.
Google ResearchSelectedPapers #Research #Agents #MultimodalScore62

Jul 9

Thursday

17:56
SensorFM: Towards a general intelligence and interface for wearable health data
Google Research and Google DeepMind proposed SensorFM, a large sensor foundation model learning directly from unlabelled wearable data. Pretraining uses over 1 trillion minutes of multimodal sensor signals from 5 million consenting participants across more than 100 countries and over 20 Fitbit and Pixel Watch devices.
Google ResearchSelectedPapers #Research #Data and training #AgentsScore60

Jul 1

Wednesday

02:32
ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration
Hugging Face released ScarfBench (Self-Contained Application Refactoring Benchmark) to evaluate AI agents migrating enterprise Java applications between Spring, Jakarta EE and Quarkus.
Hugging Face BlogPapers #Research #Benchmarks #AgentsScore47

May 20

Wednesday

01:52
Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery
Google released Empirical Research Assistance (ERA), a research tool using Gemini to write and optimise scientific code. Its paper was published in Nature today, and the tool is available to scientists worldwide as part of Gemini for Science.
Google ResearchSelectedPapers #Product updates #Agents #GoogleScore74

Apr 30

Thursday

20:14
Enabling a new model for healthcare with AI co-clinician
Google DeepMind announced AI co-clinician research to explore AI agents assisting patient care under clinical supervision. In blinded assessments of 98 real primary-care queries, 97 responses had no critical errors, and doctors preferred them to existing evidence-synthesis tools. Across 140 consultation skills, AI matched or exceeded primary-care doctors on 68, but expert doctors were better overall at recognising red flags and guiding key physical examinations.
Google DeepMindSelectedPapers #Research #Agents #MultimodalScore62

Apr 22

Wednesday

00:42
ReasoningBank: Enabling agents to learn from experience
Google Research released the ICLR paper ReasoningBank, an open-source agent memory framework that distils high-level reasoning patterns from successful and failed experiences.
Google ResearchSelectedPapers #Research #Agents #GoogleScore62

Apr 20

Monday

17:00
Gradient-based Planning for World Models at Longer Horizons
Berkeley AI Research proposed GRASP, a gradient-based planner for learned world models. It lifts trajectories into virtual states for parallel optimisation across time, injects randomness directly into state iterations for exploration and reshapes gradients to give actions clear signals. Avoiding fragile state-input gradients in high-dimensional visual models makes long-horizon planning more practical and robust.
Berkeley AI ResearchPapers #Research #Agents #ReasoningScore33

Apr 14

Tuesday

02:15
Towards developing future-ready skills with generative AI
Google released Vantage, a research experiment using generative AI simulated conversations to assess future skills such as problem-solving and collaboration in school and university students, with English registration open on Google Labs. An Executive LLM dynamically guides dialogue and an AI Evaluator scores against rubrics. A study with New York University involving 188 US participants aged 18–25 found AI–expert scoring agreement close to agreement between two human experts.
Google ResearchPapers #Research #Benchmarks #AgentsScore47

Apr 9

Thursday

19:22
ConvApparel: Measuring and bridging the realism gap in user simulators
Google Research released ConvApparel, with over 4,000 human–machine multi-turn clothing-shopping conversations, nearly 15,000 turns, to quantify realism gaps between LLM user simulators and real people.
Google ResearchPapers #Research #Agents #BenchmarksScore36
04:01
Improving the academic workflow: Introducing two AI agents for better figures and peer review
Google released PaperVizAgent for paper illustrations and ScholarPeer for automated peer review. PaperVizAgent combines retrieval, planning, style, visualisation and review agents, scoring 60.2 on a 0–100 evaluation, ahead of GPT-Image-1.5, Nano-Banana-Pro and Paper2Any. It was the only framework above the 50.0 human baseline.
Google ResearchPapers #Research #Agents #MultimodalScore41