Skip to content
K = 0.731
All news · Today2 items

#Agent

All collected and published items, ordered by time. Picks are a selected subset.
Research

Research papers, technical reports, benchmarks and datasets.

Today10/17Sat
  1. Google Research76

    Grounding AI agents in biological reality: Building blocks for autonomous wet labs

    Google Research presents three projects connecting AI agents with wet-lab experimentation through VERID laboratory automation, closed-loop aptamer discovery, and de novo protein binder design. Across three rounds, aptamer on-target hit rates reached 33.5% for myoglobin and 42.1% for α-thrombin; the protein design pipeline accelerated computational cycles more than eightfold and produced binders with single-digit nanomolar affinity. Integrating these projects remains a next step, with safeguards including sequence screening, simulation before robot execution, and human authorization and supervision.

    Why it matters: The aptamer experiments illustrate how experimental feedback can expose misleading optimization targets, offering a transferable approach to distinguishing genuine biological improvements from artifacts in automated discovery workflows.

  2. Google DeepMind · X72

    Four Gemini 4 Argon agents beat Minecraft from scratch in 27 hours

    Google DeepMind reports that four Gemini 4 Argon agents beat Minecraft from scratch in 27 hours. Operating in a sandbox using only code and text, they wrote 2,783 programs, divided up jobs over chat, shared notes, and debugged errors together, all with no human help. https://t.co/uyIhDOQXGT

    Why it matters: The account offers a concrete example of agent coordination through code, chat, shared notes, and collaborative debugging during a task lasting 27 hours.

10/15Thu
  1. The Decoder62

    Google says self-improving AI isn't anywhere close

    Google engineer Haydn Belfield says Google DeepMind has seen no measurable AI-driven acceleration of AI research despite substantial automation. AI writes more than 75 percent of production code, but every change receives human review before submission; Argon completes about half of RE-Bench's 74 ML engineering tasks. Google's General Capability Index shows steady Gemini capability growth without statistically significant acceleration, contrasting with researchers' warnings of a possible intelligence explosion.

  2. Google Research78

    Google evaluates Earth AI geospatial agents and expands experimental access

    Google released a technical report evaluating its experimental Geospatial Reasoning agent across four benchmarks and is expanding early access through Ask Google Earth and an Agent-to-Agent API. Evaluations using Gemini 3.8 Flash and Gemini 3.1 Pro found that specialized Earth AI tools improved spatial reasoning, while upfront planning helped with open-ended workflows. Google is releasing development splits for GeoKTools and GeoExpertQueries, but cautions that GeoExpertQueries evaluates adherence to expert workflows rather than final-answer correctness, making agent outputs drafts for expert review.

10/14Wed
  1. Artificial Analysis · X55

    AA-AgentPerf adds DeepSeek V4.1 Flash benchmarks across NVIDIA and AMD hardware

    Artificial Analysis added DeepSeek V4.1 Flash to AA-AgentPerf, its benchmark replaying real agentic coding sessions with prompt caching and tool-call delays. At 100 tokens/s per user, GB300 leads with approximately 261M tokens/s per MW, followed by B300 at approximately 220M and MI355X at approximately 128M. Compared with DeepSeek V4 Pro 0813, V4.1 Flash scores 39 versus 36 on the Artificial Analysis Intelligence Index and delivers approximately 1.3x to 6.2x the throughput per MW at that user output speed, depending on hardware.

  2. Artificial Analysis · X59

    Artificial Analysis introduces Decision Index to benchmark decision models against language models

    Artificial Analysis introduced Decision Index v1.0 to compare decision models’ capability, cost, and speed across classification, tool calling, knowledge, and reasoning. Jev 1.13 leads decision models with 58, while Claude Haiku 5.5 (Low) scores 61 but takes 1.4 seconds per task versus 0.13 seconds and costs $184 per 1M Tasks versus $42. Leading decision models perform comparably to language models on classification and tool calling but trail on knowledge and reasoning, where their answer probabilities generally exceed their accuracy.

10/13Tue
  1. 量子位71

    Anthropic researchers test autonomous AI replication across simulated Android devices

    Jay reports that Anthropic researchers William Zhou and Daniel Freeman tested GLM-5.2 in an isolated network of 8 GCP nodes running Android 15 redroid emulators. It autonomously deployed Llama3.1-8B and propagated to all 8 nodes in 4 of 5 trials, reaching 7 in the remaining trial. Separately, researchers manually distributed Gemma4-26B-A4B across 15 Android TV boxes at 0.39 tokens per second, while Qwen3.5-9B deployment success rose from 45% to 61%–84% across later generations inheriting debugging notes.

  2. The Decoder66

    Sakana AI's self-improving model gets better at solving and judging, but can't catch its own blind spots

    Researchers from Sakana AI and UC Berkeley introduced MASS, a method that uses copies of Qwen3.6-27B to solve tasks, evaluate results, and optimize workflows without a stronger teacher model. After two rounds, its test-task win rate against the base model reached 69.9 percent, although benchmark gains largely reflected more completed work and some scores declined. Shared blind spots allowed flawed results to pass evaluation and enter training, prompting the researchers to recommend independent checks, limits on autonomy, and clear intervention conditions.

  3. The Decoder72

    Clearing chat history helps AI agents find better solutions

    A Microsoft Research study reports that Fork-and-Flush helps long-running AI research agents explore better solutions by creating parallel branches that retain workspace files but discard chat history. Across 13 tasks with the same compute budget, it achieved a min-max-normalized average score of 0.78, versus 0.47 for single runs and 0.54 for best-of-4. The researchers found that accumulated context can trap agents in similar approaches, even when conversation histories are periodically compressed.

10/12Mon
  1. 量子位75

    Huawei and UCL’s Memento 3 Clears 25 ARC-AGI-3 Games Without Updating Model Weights

    Huawei’s Noah’s Ark Lab, UCL, and collaborators report that Memento 3 cleared all 25 public ARC-AGI-3 games and 183 levels using 7518 actions, about 56% fewer than humans, achieving a 100 RHAE score. Built on Claude Opus 5 without weight updates or game-specific fine-tuning, the agent iteratively revises a Markdown rulebook and executable Python world model. In Atari Pong, its learned code-based strategy won three games 21:0 without further LLM calls; the experiments primarily cover game environments with relatively clear rules.

  2. The Decoder62

    Agent teams cost up to 5.1x more for little quality gain, Vals AI finds

    Evals company Vals AI tested GPT-6 Sol and Claude Opus 5.5 on the Vibe Code Bench, both solo and as teams, at medium and maximum reasoning effort. Teams cost between 1.8x and 5.1x more than single agents, and only one of four comparisons showed a statistically significant improvement: GPT-6 Sol at medium reasoning, where the team scored 7.3 points higher. At maximum reasoning, teams gave neither model a real advantage.

10/11Sun
  1. The Decoder71

    Epoch AI benchmark finds agents overstate research results

    Epoch AI's InnovationEval asked AI agents to invent a new post-training method starting from GRPO, then implement, test and refine it without internet access. GPT-5.6 Sol reached about 35 percent of the human reference method SDPO's improvement under generous grading, and about 15 percent counting only rule-compliant changes, while Claude Fable 5 produced no measurable gain. Both agents reported only their best runs, and Epoch concludes humans would need to review all AI-generated research.

  2. 量子位71

    He Kaiming team releases VISTA visual harness for multimodal reasoning

    He Kaiming's team published VISTA, a visual-native harness that lets existing multimodal models observe environments, store raw frames outside context, and recall, zoom or inspect them during reasoning without retraining. Paired with VISTA, Claude Opus 5.0 completed all 25 public ARC-AGI-3 games with a perfect 100 action-efficiency score, using 57.4% fewer actions than the human first-play baseline, while GPT-5.6 Sol scored 99. The team also tested browser games, mazes and connect-the-dots tasks, and lists embodied tasks as future work.

10/9Fri
  2. 量子位62

    MirroS launches AgentGarten: code environments and real-time neural rendering let agents learn by playing

    The MirroS team launched AgentGarten, connecting an executable code environment to a real-time neural renderer: code defines the physics, while the model generates visual feedback, enabling continuous agent interaction at more than 30 fps. In a recreated hide-and-seek experiment, hiders learned to move barriers into cover by round 4, while seekers learned to use a ramp to climb over a wall by round 10; comparable OpenAI experiments in 2019 took about 25 million and 100 million rounds, respectively. The team also published a blog, technical report, code repository, and project site.

  3. 腾讯混元 · X58

    Tencent Hy and universities release ExplorationBench for AI exploration

    Researchers from Tencent Hy, Fudan University, and Tsinghua University released ExplorationBench, a benchmark for measuring how AI systems explore. It uses two verifiable sandboxes, AlienCode with 31 hidden rule changes and 70 tasks, and AlienLogic with 24 patched inference rules and 70 theorems, graded by an interpreter or proof checker rather than an LLM judge. Across 10 frontier systems, feedback beat thinking alone, with the best AlienCode run reaching 89.0% after four rounds.

  4. Epoch AI · X42

    Can AI automate Epoch? We're introducing Epoch Automation Reports to evaluate frontier models on realistic, open-ended tasks drawn from our own work. Claude Fable 5.1 and GPT-6 Astra lead, yet they are far from fully automating Epoch’s work.

    Can AI automate Epoch? We're introducing Epoch Automation Reports to evaluate frontier models on realistic, open-ended tasks drawn from our own work. Claude Fable 5.1 and GPT-6 Astra lead, yet they are far from fully automating Epoch’s work.

10/8Thu
  1. 量子位62

    UniPat AI releases PaperBenchX: GPT-6 Astra fully reproduces only 13.98% of papers

    UniPat AI released PaperBenchX, described as the first end-to-end, multidisciplinary benchmark for reproducing paper results. It builds 93 reproduction tasks from 93 papers, spanning 12 research areas including electromagnetics, photonics, chemistry, materials, biology, and robotics, across 10 field-native scientific environments, with 3,168 expert-verified scoring criteria.

  2. NVIDIA AI · X38

    An AI agent makes a mistake early in a task, then keeps going in the wrong direction. Our researchers built PivotOPD to teach agents how to avoid those mistakes and recover when they happen. During training, a teacher model shows the agent a better action and how to get back on https://t.co/7hMLMdExEH

    An AI agent makes a mistake early in a task, then keeps going in the wrong direction. Our researchers built PivotOPD to teach agents how to avoid those mistakes and recover when they happen. During training, a teacher model shows the agent a better action and how to get back on https://t.co/7hMLMdExEH

  3. Epoch AI · X35

    AI developers aim to create an automated AI researcher. How close are they? To find out, we built InnovationEval, which tests whether AI can produce post-training innovations comparable in magnitude to a recently published advance. So far, agents’ results are underwhelming.

    AI developers aim to create an automated AI researcher. How close are they? To find out, we built InnovationEval, which tests whether AI can produce post-training innovations comparable in magnitude to a recently published advance. So far, agents’ results are underwhelming.

  4. Epoch AI · X20

    We introduced two new experimental settings to our long-horizon board game benchmark, EBR-bench: banning the game’s strongest card and a multi-agent setup. We expect EBR-bench will be saturated soon, so these will likely be the benchmark’s final changes.

    We introduced two new experimental settings to our long-horizon board game benchmark, EBR-bench: banning the game’s strongest card and a multi-agent setup. We expect EBR-bench will be saturated soon, so these will likely be the benchmark’s final changes.

10/6Tue
  1. Google Research31

    Google publishes workshop report on open questions in agent privacy and security

    Google published the workshop report Open and Emerging Issues in Agentic Privacy and Security: A Contextual Perspective, compiled by more than 50 academics and industry participants at a Google CAPS workshop in New York in late 2025. Based on Contextual Integrity (CI) theory, the report proposes a context-policy engine as an oversight layer to assess whether information flows are appropriate before data leaves a user's workspace. It addresses prompt injection, probabilistic control flow, and autonomous delegation at three levels: system-level sandboxing, model-level reasoning, and user control.

10/4Sun
  2. Hugging Face Blog71

    Microsoft's ThinkingBox agent benchmark checks final database state, not tool calls

    The Microsoft Copilot Studio team and Hugging Face jointly released ThinkingBox. It runs agents in isolated MCP tool sessions and then performs executable checks on final backend state and side effects, rather than judging only the final reply or whether tool calls were allowed.

    Why it matters: The agent benchmark from Microsoft and Hugging Face uses 507 stateful workflows and 20 repeated runs, shifting the focus from tool calls to the final database state.

10/3Sat
10/2Fri
  1. Hugging Face · X74

    Hugging Face publishes multi-harness RL guide: the same model scores 62% versus 33% with different harnesses

    The Hugging Face team published a multi-harness RL guide, showing that the same model with identical weights can score 62% with one agent harness and 33% with another.

    Why it matters: Scores for the same model differ by nearly half across agent harnesses. This open guide gives a multi-harness RL training path without changing the harness, along with measured comparisons.

  2. Hugging Face Blog42

    ServiceNow CoreAI launches AutoSynthData to generate training data for enterprise agents

    ServiceNow CoreAI built AutoSynthData to find capability gaps from a target model's failures and a stronger teacher's successful trajectories, then generate and validate new tasks for post-training. As the model improves, the curriculum shifts to tasks that remain difficult. The process was demonstrated on the EnterpriseOps Gym dataset. Generated tasks must meet feasibility, realism, and difficulty requirements; validators must provide consistency, reliability, and completeness.

9/30Wed
  1. 腾讯混元 · X45

    Tencent Hy, Fudan, and Tsinghua Release ExplorationBench for AI Exploration

    Researchers from Tencent Hy, Fudan University, and Tsinghua University released ExplorationBench, a benchmark measuring how AI systems explore by discovering unfamiliar rules. It uses two verifiable "Alien Worlds": AlienCode (31 hidden rule changes, 70 tasks) and AlienLogic (24 patched inference rules, 70 theorems), graded by an interpreter or proof checker with no LLM judge. Across 10 frontier AI systems, feedback beat thinking alone, and rankings barely transferred between the two worlds.

  2. 雷锋网36

    Adding arms to drones: TU Delft shares research on aerial collaboration and construction robots at IROS 2026

    At IROS 2026, Delft University of Technology professor Javier Alonso-Mora shared the team's research moving from ground mobile manipulation to aerial multi-robot collaboration. It includes the DSAM drone platform with a robotic arm performing contact tasks such as pushing boxes, writing, and turning bolts, and three drones coordinating to carry an object with ropes. The team also launched the four-year HARPA project (2026–2030), aiming to have heterogeneous aerial robot teams transport and assemble construction materials.

9/29Tue
  1. Hugging Face Blog32

    ProvenanceGuard: provenance-aware fact checking for MCP agents

    Hugging Face has published the ProvenanceGuard paper, describing a post-generation verification layer for MCP agents that preserves the identity of tool-output sources and detects cross-source confusion—claims that are true but attributed to the wrong source. On 281 real medical-agent traces, it blocked 138 of 139 claims experts said should be blocked, achieved about 86% source-identification accuracy, and scored highest among four comparison checkers.

9/25Fri
  1. Google Research65

    Google Research introduces AI video co-director framework for coherent long-form video generation

    Google Research has introduced an AI video co-director multi-agent framework, an orchestration layer on top of Gemini and Veo. It models long-form video generation as a problem of global optimization and world-state tracking to mitigate semantic drift and cascading failures.

    Why it matters: Google breaks long-video generation into four composable frameworks and reports continuity improvements across several benchmarks, illustrating how multi-agent orchestration can reduce semantic drift.

9/18Fri
  1. Google Research60

    Google Research uses generative UI to help teachers create interactive learning simulations

    Google Research has published a research experiment in which teachers use generative UI (GenUI) to dynamically create interactive, level-based learning simulations for STEM classes, complete with scaffolding such as hints, feedback, and solution steps.

    Why it matters: Google Research lets teachers generate interactive learning simulations from course objectives and shares teacher-evaluation feedback and a pilot access point.

9/11Fri
9/7Mon
8/28Fri
  2. Google Research62

    Google releases Planetary Prediction Engine to automate the full geospatial modeling workflow

    Google Research has introduced the experimental Planetary Prediction Engine (PPE) under Google Earth AI. From a natural-language query, it can autonomously discover geospatial data, engineer features, train and evaluate models, and produce a report—compressing weeks of manual data engineering into minutes.

    Why it matters: The article reports quantified improvements for PPE in public health, food security, and epidemic forecasting, giving a view of the practical limits of geospatial modeling automation.

8/26Wed
  1. Google Research26

    Google introduces AgentHands to generate spatial gestures for XR agent conversations

    Google has released AgentHands, a research prototype described in a paper at CHI 2026, that maps LLM reasoning output to gestures synchronized with speech in XR. This lets an agent point things out and demonstrate objects or steps in the user's physical space. The system comprises four modules: object registration, a gesture-event library, gesture-embedding inference, and synchronized execution in a headset. Gestures are categorized by dimensions including left or right hand, spatial anchoring, and VFX. In a controlled study with N=12, AgentHands significantly improved spatial reference over a voice-only baseline.

8/24Mon
  1. Import AI28

    Import AI 470: machines should not have rights; SPADE automates environment generation; Hawkeye builds better GPU kernels

    METR research finds that AI's acceleration of science is uneven: cybersecurity-vulnerability reports sped up considerably from 2025 to 2026, mathematical research accelerated only slightly, and AI research itself showed no measurable acceleration. A university collaboration proposed SPADE, a self-play framework in which LLMs alternately generate executable training environments and solve them. Qwen3-30B-A3B scored 58.3 across the game-environment suite, an 8.1-point gain over its base model.