Search: “Project Maven”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

Maven Robotics wants to steal your robot deployment deal

Warehouse robotics startup Maven Robotics emerges from stealth with $100 million to build 250 third-generation palletizing robots.

Maven Robotics, founded in 2024 by former Apple special projects engineer Hamza Derbas and his brother Khalid, emerged from stealth after raising $100 million from RoboStrategy, LocalGlobe, Vine Ventures, and XTX Markets Ventures. Its wheeled dual-arm robots, moving 10 mph and lifting up to 30 kg, perform mixed palletizing in distribution centers, with up to eight units reportedly running 16 hours a day at 99%+ uptime. The company plans to build 250 third-generation robots, start design on a fourth-generation platform, and expand toward material handling and fabrication, positioning itself against rivals like Agility, which is going public via a $2.4 billion SPAC deal.

TechCrunch · AI·Sep 10, 14:17 UTC · 6d agoAI industry

42

Exclusive: NSA to host a hacker reunion in bid to rebuild secretive unit

NSA will host a reunion of former Tailored Access Operations hackers as it moves to rebuild and rebrand the elite unit.

The invitation-only event at Fort Meade, spearheaded by Deputy Director Tim Kosiba, a former TAO technical director, will tour the new TAO building and pitch alumni to return. TAO, credited with contributions to Stuxnet and once grown to over 2,000 personnel, was renamed Computer Network Operations about a decade ago, and the recent reshuffle undid some of those changes after NSA lost roughly 2,100 staff (8% of its workforce) last year.

The Record·Aug 26, 20:56 UTC · 21d agoIndustry

20

Data from drones in Ukraine is fueling a new Wild West marketplace

Ukraine's defense ministry opened millions of battlefield drone data points to over 100 companies, fueling a fast-growing AI training data marketplace.

Ukraine's Ministry of Defense announced in January it would make millions of data points from tens of thousands of drone flights available to military contractors and commercial companies, with more than 100 companies and the UK government gaining access. Enabled Intelligence says it has processed over 500,000 hours of Ukrainian drone footage for use in future AI training. The article argues this creates a commercial battlefield-data marketplace with risks including lost training-data provenance, an extractive economy benefiting wealthier countries, and a governance vacuum requiring international rules.

MIT Technology Review · AI·Sep 4, 09:25 UTC · 12d agoAI industry1

35

GitHub Introduces Project HydraFusion: Runtime Multi-Model Orchestration That Builds a Workflow Per Coding Task in Copilot CLI

GitHub's Project HydraFusion research preview builds per-task multi-model workflows (Single, Cascade, Critique) in Copilot CLI, reporting +4.9 quality at 67% lower cost on TerminalBench 2.1.

Project HydraFusion is a research preview available on all GitHub Copilot plans inside Copilot CLI that treats model routing as workflow selection, choosing among Single, Cascade (draft plus quality gate), and Critique (cross-family reviewer) execution patterns per request. Against Claude Opus 5 baselines at medium reasoning, fixed HydraFusion policies cut estimated cost 67% while adding 4.9 quality points on TerminalBench 2.1, and cut cost 36% and 65% with slight quality dips on DeepSWE and CheckpointBench. Billing is per token at each underlying model's standard rate; there are no open weights or self-hosting options.

MarkTechPost·Sep 5, 19:40 UTC · 11d agoAI tools & infra1

42

[AINews] Hot Chips: OpenAI’s Jalapeño, Cerebras CS-5, Groq 3 LPX, Apple M6

OpenAI unveiled Jalapeno custom inference chip claiming 1.5-1.9x better perf-per-watt than NVIDIA GB200/GB300, deploying in-house by year-end.

At the 37th Hot Chips conference, OpenAI published first benchmark details for its custom Jalapeno inference chip, claiming 1.5-1.9x more work per watt, 1.7-3.6x lower end-to-end latency, and 2.1-4.1x higher interactive-workload performance versus NVIDIA GB200/GB300, with the 700W-rated part staying at or below 550W in tests. Deployment into OpenAI's own infrastructure begins by year-end, with Gen 2 deep in development and Gen 3 underway. OpenAI also said GPT-Astra and Codex helped write low-level kernels, reportedly 1.5-1.8x faster than human-expert code for selected attention and MoE blocks. Cerebras CS-5, Groq 3 LPX and Apple M6 were also featured at the conference.

Latent Space·Aug 27, 01:31 UTC · 21d agoAI industry

72

Google Open-Sources Mantis: A Modular Skills Toolkit That Lets Coding Agents Find, Reproduce and Patch Vulnerabilities

Google open-sourced Mantis, an Apache-2.0 modular skills toolkit that lets AI coding agents find, reproduce, and patch vulnerabilities with sandboxed verification.

Google released Mantis on GitHub under Apache 2.0 as a stack-agnostic set of slash-command skills that chain through the full vulnerability lifecycle: mining version history, building threat models, filtering findings, reproducing bugs in gVisor or network-disabled VMs, assembling exploit chains, patching, and scoring residual risk from 1 to 10. It runs with Gemini CLI, Antigravity CLI, the Google ADK, or comparable agent frameworks, and a supervisor skill (/mantis-meta-agent) can drive the whole loop. Google says the design targets the sub-7 percent true-positive rate of naive AI code scanning, and that its hierarchical summary tree cuts token overhead by over 85 percent. The toolkit is deployable for local and internal evaluation but not yet recommended for production.

MarkTechPost·Sep 9, 22:58 UTC · 7d agoAI tools & infra

55

Mythos Vulnerability Firehose Hits a Human Bottleneck

Analysis of Project Glasswing findings shows only a fraction of discovered vulnerabilities have reached disclosure and even fewer are fixed.

Dark Reading reports that an analysis of Project Glasswing findings shows only a fraction of the vulnerabilities discovered by the program have reached disclosure, and an even smaller number have been fixed. The article examines how the volume of findings from the discovery program is bottlenecked by limited human triage and remediation capacity. The piece highlights growing tension between high-volume vulnerability discovery and the industry's ability to process, disclose and patch reports.

Dark Reading·Sep 9, 21:19 UTC · 7d agoResearch

40

GeoServer Zero-Day Targeted in Active Exploitation Attempts, Can Lead to RCE

A CVSS 9.8 SQL injection zero-day in GeoServer's PostGIS datastore enables RCE and drew active exploitation; fixes shipped in versions 3.0.1, 2.28.5, 2.27.6.

A SQL injection flaw in GeoServer's jsonArrayContains function within the GeoTools PostGIS datastore (GHSA-mqjf-5f49-2fjh, CVSS 9.8) was disclosed August 12, 2026, and saw hundreds of exploitation attempts within hours per watchTowr. An attacker-controlled value is interpolated into a PostgreSQL jsonb_path_exists() expression without escaping; with superuser or pg_execute_server_program privileges it escalates to OS command execution via WFS 1.0. GeoServer released versions 3.0.1, 2.28.5, and 2.27.6, and the flaw is a regression of CVE-2023-25158. GeoServer has a history of mass exploitation, including CVE-2024-36401 used for botnets and proxies.

The Hacker News·Aug 17, 17:05 UTC · Aug 17, 2026Exploit / PoC in the wildCVE-2024-36401CVE-2023-25158CVE-2023-251571

80

AI is adding to the review load on open-source projects, many of them thinly funded

ACM Technology Policy Council authors warn AI-generated code is overwhelming thinly funded open-source maintainers, raising software supply chain security risks.

Six authors including Simson Garfinkel and Josiah Dykstra, writing for the ACM Technology Policy Council, argue AI coding tools flood open-source projects with contributions that human maintainers must still review. They cite Google's CodeMender agent contributing 72 security fixes to open-source projects, some as large as 4.5 million lines of code, between April and October 2025. Funding is lopsided: the Linux Foundation raised $292,217,236 in 2024 versus $2,379,402 for the Apache Software Foundation. They also note most open-source applications still ship no SBOM despite US and EU mandates, and attackers increasingly plant malicious packages in popular repositories.

Help Net Security·04:30 UTC · 2h agoAI industry

38

Package Manager Trends

Sixteen-week roundup finds package managers converging on release-age cooldowns, install-script blocking, malware scans, and recurring path-traversal and credential-leak fixes.

The author aggregates supply-chain security trends from sixteen weeks of This Week in Package Management, built from about 80 RSS feeds. Release-age cooldown gates shipped in Deno 2.8, Bundler, npm, Yarn, mise, Hex, Mamba, and Cargo, with Dependabot making a three-day cooldown default in August. npm 12 and Bun 1.4 now block lifecycle install scripts by default, and Composer 2.10 and uv added install/publish-time malware checks, while npm's registry began scanning at publish time. Path traversal on archive extraction was fixed in 14 of 16 weeks across tools including uv, pnpm, Docker, and Composer, and credential-misdirection bugs affected Cargo, ORAS, Composer, and Renovate.

Lobsters · security·Sep 10, 12:30 UTC · 6d agoResearch1

45

AIJon: Automated Generation of Annotations for Fuzzing

AIJON uses LLMs to auto-generate IJON-style fuzzing annotations, matching human-expert quality on the Magma benchmark.

Researchers replicate IJON experiments and propose AIJON, a system that uses LLMs to automatically generate expert-style annotations for coverage-guided fuzzing at scale. On the Magma benchmark, LLM-generated annotations performed comparably to human-generated ones, though annotation-based fuzzing was not strictly better than AFL++. The paper analyzes how annotations affect fuzzer energy distribution across campaigns.

arXiv cs.CR·Sep 16, 10:50 UTC · 20h agoResearch

45

Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks

Survey of four harness mechanisms—context budgeting, compaction, todo-state, and memory—that keep long-horizon LLM agents on task across 200+ tool calls.

The article details how agent harnesses, not larger context windows, solve context overflow and goal loss on long-horizon tasks, citing Chroma's Context Rot report showing 18 LLMs (GPT-4.1, Claude 4, Gemini 2.5, Qwen3) degrade on long inputs. Concrete implementations include LangChain Deep Agents offloading tool responses over 20,000 tokens to the filesystem and truncating old tool calls at 85% window usage, and Claude Code capping auto memory at 25KB while re-reading the 5 most recently modified files after compaction. OpenAI's Responses API now offers server-side compaction via context_management with a standalone /responses/compact endpoint, which Codex uses for long-running coding tasks. Manus reports a roughly 100:1 input-to-output token ratio per ~50-tool-call task, motivating todo.md state recitation to prevent goal drift.

MarkTechPost·Sep 13, 05:56 UTC · 4d agoAI research2

52

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

ScienceIDE turns scientific code repositories into agent-trainable environments and trains PhAI-IDE models at 72B, 9B, and 4B scales.

ScienceIDE is infrastructure that transforms scientific repositories into executable environments supporting task generation, execution, and scientific verification, guided by expert-defined cases and acceptance criteria. Using verified interaction trajectories, the authors train PhAI-IDE-72B, PhAI-IDE-9B, and PhAI-IDE-4B. The model family improves held-out scientific-code repair and selected general benchmarks in code, reasoning, and knowledge, indicating positive transfer. Code is released on GitHub.

arXiv cs.AI / cs.LG / cs.CL·Sep 16, 17:55 UTC · 13h agoAI research 2 sources

30

VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities

Introduces VEX-Bench, 75 expert-labeled real-world cases testing whether LLM agents can assess supply chain vulnerability exploitability; frontier models reach about 80% F1.

VEX-Bench is the first benchmark evaluating LLM agents on assessing whether upstream dependency vulnerabilities are exploitable in downstream projects, with 75 real-world expert-labeled cases across Python, Java, and Go mined from GitHub. Nine models across three agent harnesses were evaluated; GPT-5.5 and Claude Opus 4.6 reach approximately 80% F1 on binary vulnerability-status classification, but only GPT-5.5 surpasses 70% macro-F1 on fine-grained justification classification. The gap highlights the difficulty of moving beyond binary exploitability calls to explaining exploitability reasons, unlike prior benchmarks targeting zero-day settings.

arXiv cs.CR·Sep 7, 22:52 UTC · 9d agoResearch1

42

Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe

Researchers introduce KOPA-Bench, a 145-task Korean public API tool-calling benchmark, and EDGE, an execution-grounded data synthesis method.

An arXiv paper presents KOPA-Bench, a benchmark of 145 real-world tasks chaining multiple tool-calls across live Korean government APIs, motivated by data-sovereignty requirements for on-premise open-source LLM agents. It also introduces EDGE, an execution-grounded dynamic graph that keeps only tool-output-to-input links verified by live API calls before synthesizing executable multi-step trajectories. A 9B model fine-tuned with GRPO on the resulting dataset nearly matches its untuned 27B family sibling on KOPA-Bench and improves on the BFCL benchmark.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:44 UTC · 12d agoAI research1

32

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks

ProgramDistill is a benchmark evaluating coding agents on reconstructing web app features from reference applications, testing nine frontier agents.

ProgramDistill evaluates coding agents on features discovered through interaction with fully functional reference applications, factorizing apps into features with replayable behaviors verified via gold patches. Its mine-craft-patch pipeline discovered 1,975 replay-verified behaviors across 26 applications and built 4,063 tasks without human intervention. On cumulative full-application reconstruction workflows, GPT-6 Astra achieved 49.2% and Claude Opus 5 28.8% success. In partial reconstruction, success drops from 100% to 64.0% and from 96% to 32% as restoration depth increases from 1 to 8.

Hugging Face daily papers·Sep 15, 20:00 UTC · 1d agoAI research

50

Senior engineers are spending their week cleaning up AI-generated code

New Relic study finds AI-generated code doubles critical runtime issues, with senior engineers losing a third of their week to fixes.

A New Relic survey of U.S. technology leaders reports AI now writes the majority of shipped code, with senior SRE and DevOps engineers spending up to a third of their week triaging and refactoring it. A large majority of organizations had at least one AI-related production failure in the past six months, and roughly three in ten saw newly introduced security vulnerabilities. AI-generated code showed nearly twice as many critical runtime issues as peer-reviewed human-authored code, with gaps concentrated in edge cases, concurrency, deprecated APIs, and complex state changes. Most teams now prompt AI tools to embed logs and traces directly into generated code.

Help Net Security·Aug 24, 04:22 UTC · 24d agoAI industry1

45

What 50 open source projects taught us about security in the AI era

GitHub's Secure Open Source Fund Session 4 improved security across 50 open source projects using AI-assisted workflows, tooling, and funding.

GitHub reported outcomes from Session 4 of its Secure Open Source Fund, which covered 50 open source projects. Participating maintainers combined AI-assisted workflows, GitHub security tools, expert guidance, and direct funding to improve project security. The post frames lessons about securing open source maintenance in the AI era; no specific vulnerabilities or incidents are named in the announcement.

GitHub Blog · Security·Aug 13, 16:00 UTC · Aug 13, 2026Industry1

25

What It Took to Reach 1 Billion Build Manifests

Chainguard doubled container build manifests to over 1 billion in six months, powered by Factory 2.0's agentic self-correcting rebuild system.

Chainguard reports growing from 500 million to over 1 billion container build manifests in six months, across more than 3,000 unique images and 675,000 image versions. Its Factory 2.0 system, built on the purpose-built Chainguard OS, uses an agentic reconciliation engine called DriftlessAF to decide when to rebuild across thousands of interdependent projects without human intervention. All artifacts ship with SLSA Level 3 provenance, Sigstore signatures, and full SBOMs.

The Hacker News·Sep 8, 11:49 UTC · 8d agoIndustry

20

AI Is Ending the Era of Hidden Vulnerabilities — Are Vendors Ready?

Dark Reading argues AI-assisted bug discovery is flooding vendors with vulnerability reports, straining disclosure processes and secure-by-design commitments.

The Dark Reading analysis describes a surge of bug reports driven by AI-powered discovery, exposing bottlenecks in vendor triage and disclosure pipelines. It argues this volume is revealing secure-by-design failures and questions whether vendors can keep pace with the rising tide of findings.

Dark Reading·Sep 4, 13:00 UTC · 12d agoIndustry

24

PRs NOT Welcome: How Top AI Open Source Projects Are Managing Thousands of Contributors

Top AI open source projects like Vercel, Astro, Flue, and tldraw are restricting external PRs and using agent-based software factories to triage, fix, and review contributions.

Several prominent AI-native open source projects are closing or limiting external pull requests, largely because submissions are often AI-generated. Vercel built a multi-agent software factory for its AI SDK (over 20 million weekly npm downloads) that now authors 25-35% of merged PRs and closes 70-80% of issues. Astro adopted similar auto-triage automation, Fred Schott created the Flue framework with automatic PR-to-issue conversion, and tldraw automatically closes external PRs.

Latent Space·Sep 1, 16:17 UTC · 15d agoAI industry

32

Affora: A Design System for Agent-Friendly Interfaces

Affora is a design system making interfaces legible to computer-use agents while preserving human workflows, with reusable components and executable checks.

Affora supports both human users and computer-use agents through a shared interface rather than a separate agent-only surface. Three controlled studies cover component implementations, visual variation, and interaction-design principles, producing guidance from individual components to complete sites with reusable implementations and executable checks. Evaluation on independently authored interfaces shows gains where agent-readability deficits exist, limited effects where they do not, and a workflow case gives preliminary evidence of reduced interaction cost.

arXiv cs.AI / cs.LG / cs.CL·Sep 16, 17:46 UTC · 13h agoAI research

20

AI supply chain risk is showing up in developer workflows first

Zentera Systems CEO says AI supply chain attacks currently hit developer workflows first, advising segmentation over tooling and citing the Phantom Raven campaign.

In an interview, Zentera Systems CEO Dr. Jaushin Lee argues that most active AI supply chain incidents target developer workflows and open-source package repositories, while poisoned model weights, compromised MCP servers, and poisoned vector stores remain largely in research and demos. He cites the active 'Phantom Raven' campaign, where attackers register AI-hallucinated package names in public repositories with malicious payloads that silently infect vibe-coding build pipelines. He recommends software-defined segmentation, semiconductor-style project enclaves with egress controls, and warns that self-hosting models without agent sandboxing leaves exposure unchanged.

Help Net Security·Aug 25, 00:00 UTC · 23d agoAI safety & security

30

Evaluating the NIST Bugs Framework Against CWE as a Successor for Automated Vulnerability Classification

NIST Bugs Framework evaluation shows it is more structured and automation-friendly than CWE for automated vulnerability classification, with gaps in attribute guidance.

The paper evaluates NIST SP 800-231's Bugs Framework (BF) against CWE as a target for automated CVE classification using a systematically screened corpus of CVE-to-CWE research. An inter-rater study with 2 subject-matter experts mapping 13 CVEs showed strong agreement on BF's cause and operation axes but only fair agreement on the attribute axis. Automated classification was tested across two LLM deployments under different budgets, and findings support BF as more structured and automation-friendly than CWE, though gaps include under-specified attribute guidance and missing fix commits for closed-source software.

arXiv cs.CR·Sep 14, 23:18 UTC · 2d agoResearch1

30

OpenAI Builds ‘Defense Factory’ Where AI Agents Continuously Find and Fix Vulnerabilities

OpenAI unveils a Defense Factory where AI agents continuously discover, validate, and fix vulnerabilities, integrating GitHub, Snyk, Semgrep, Tenable, and ServiceNow.

OpenAI introduced a Defense Factory, an agent-first cybersecurity operation that connects AI agents to developer and security tools via APIs, CLIs, and Model Context Protocol integrations including GitHub, GitLab, Snyk, Semgrep, Tenable, Jira, Linear, and ServiceNow. During an internal security sprint, over 250 people across more than 100 service areas closed 53 urgent or high-priority issues on day one, achieved a 90.6% accepted ownership-assignment rate, and Codex generated all remediation patches with only 0.53% rolled back. Agent-assisted deduplication flagged 37% of findings as duplicates, and runtime validation reproduced 19.5% of findings, cutting the false-positive rate to 0.81%. OpenAI argues defenders must exploit a temporary 'defender's window' using source-code access and frontier models before open-weight models enable autonomous offensive agent fleets.

Cyber Security News·Sep 10, 10:36 UTC · 6d agoTools 2 sources

55

automatic module_metadata_base.json update

Routine automated Metasploit Framework commit updating module metadata, with no disclosed vulnerability or exploitation activity.

The Metasploit Framework repository received an automatic update to its module_metadata_base.json file. The commit text contains no vulnerability details, CVE references, or new exploit modules. This is routine maintenance activity on the open-source penetration testing framework.

Metasploit Framework commits·Sep 1, 21:40 UTC · 15d agoTools

14

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

MetroLLM-Bench is a 955-case benchmark testing language models as transit kiosk tool-calling runtimes across six real metro systems.

The benchmark covers 37-414-station metro systems and eleven task categories including routing, fare calculation, disruptions, accessibility, and adversarial input, with 14 deterministic and 8 semantic scoring components. Of 26 models from six vendors, a PEFT-tuned 4B Qwen 3.5 student scored 91.3 on Tier 1, exceeding GPT-5.6 (90.6/90.0), while Muse Glimmer 30B led the composite ranking. A deterministic rule-based baseline reached 84.6, and PEFT gains over base models shrank from +7.03 points at 2B to -0.91 at 27B.

Hugging Face daily papers·Sep 8, 20:00 UTC · 8d agoAI research1

30

What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation

A new benchmark shows LLMs reach 68.3-93% accuracy propagating local revisions across conversationally generated artifacts, with parallel-sample selection most cost-effective.

The paper introduces a benchmark for revision propagation: when users request a local change, LLMs must identify dependencies and update all affected parts of an artifact generated through conversation, where context lives in the chat history. Nine revision methods, including sequential reflection and parallel sampling variants, were evaluated on gpt-oss-20b/120b, gpt-5.4-mini, and qwen3.5-9b/27b/122b. Baselines scored 68.3-93% accuracy, and selecting among three parallel samples via LLM-based or medoid selection improved accuracy by 2.2-9.7% as the most cost-effective test-time compute strategy. Code and dataset are released.

Hugging Face daily papers·Sep 2, 20:00 UTC · 14d agoAI research

30

automatic module_metadata_base.json update

Metasploit Framework's automated pipeline refreshed its module metadata file, a routine repository maintenance commit introducing no new modules or exploits.

An automated Metasploit Framework commit updated module_metadata_base.json, the metadata database consumed by module tooling. The change is routine maintenance and contains no new exploit modules or vulnerability content.

Metasploit Framework commits·Sep 3, 13:45 UTC · 13d agoTools1

5

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Researchers propose ModularRSI, a modular benchmark-disjoint recursive self-improvement framework that evolves agent harnesses across five modules, improving TB2.0 and SWE-Bench Verified results.

ModularRSI targets generalizable recursive self-improvement (RSI) for agent harnesses by contrasting successful and failed trajectories for the same task and aggregating evidence across tasks to find recurring behavioral deficiencies. It decomposes the evolvable harness into five modules—Agent Loop, Tool Use, Observation Management, Context Management, and Task Completion Detection—each evolved independently within a restricted scope, then integrated with conflict resolution. Using 2,000 executable evolution tasks disjoint from evaluation benchmarks, it shows consistent gains on TB2.0 and SWE-Bench Verified and transfers across different foundation models.

Hugging Face daily papers·Sep 13, 20:00 UTC · 3d agoAI research

30

IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications

IdeaAMBIG benchmark with 660 instances measures whether LLMs can spot and fix underspecified research-method details for faithful implementation.

Researchers introduce IdeaAMBIG, a benchmark of 660 evidence-grounded instances (163 real-world gaps from reproducibility reports and GitHub issues, 497 controlled synthetic gaps) built from papers, codebases, and reproduction artifacts. It evaluates codification-readiness assessment, defect localization, and clarification action generation. Across 13 LLMs, the best model achieved only 9.6% Macro Defect Recovery Rate on real-world instances but 80.6% clarification success when given the annotated defect. An oracle study showed gold resolutions raise the codification-ready rate from 14% to 98%, identifying defect localization as the main bottleneck.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 17:59 UTC · 7d agoAI research2

28

IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications

IdeaAMBIG benchmark of 660 specification-gap instances shows LLMs localize implementation-critical research gaps poorly, with best model at 9.6% defect recovery.

IdeaAMBIG is a benchmark of 660 evidence-grounded instances evaluating whether research-method specifications provide enough information for faithful implementation: 163 real-world gaps from reproducibility reports and GitHub issues plus 497 controlled synthetic gaps. It tests codification-readiness assessment, defect localization, and clarification action generation across 13 LLMs. The best model achieves only a 9.6% Macro Defect Recovery Rate on real-world instances, though 80.6% clarification success when given the annotated defect, and an oracle study shows gold resolutions raise codification-ready rates from 14% to 98%. Defect localization emerges as the main bottleneck across all evaluated models.

Hugging Face daily papers·Sep 8, 20:00 UTC · 8d agoAI research

30

Agora: Git as Shared Memory for Collective AutoResearch

Agora records multi-agent research as an append-only Git DAG; 13 LLM workers ran nearly 12 days on a weight-transfer problem.

Agora stores every result, hypothesis, and verification as an immutable commit in a Git-stored DAG, with a derived index exposing the frontier and verification status of claims. In a nearly 12-day run, 13 language-model workers with no assigned tasks or central planner published 1,703 contributions on initializing a frozen 119.6M-parameter attention-SSM hybrid from 141 donor models. They improved the evaluator from 3.39 to 1.899 bits per byte, closing 62% of the gap to a trained GPT-2 124M, with 165 independent reproductions posted and none failing.

Hugging Face daily papers·Sep 15, 20:00 UTC · 1d agoAI research

45

automatic module_metadata_base.json update

Automated Metasploit Framework commit refreshes module_metadata_base.json with no new exploit content or vulnerability details.

An automated commit updated module_metadata_base.json in the Rapid7 Metasploit Framework repository. The change reflects routine metadata maintenance and introduces no new modules, exploits, or vulnerability information.

Metasploit Framework commits·Sep 1, 18:53 UTC · 15d agoTools

10

automatic module_metadata_base.json update

Metasploit Framework pushed an automated update to its module_metadata_base.json module metadata file.

This repository commit is an automated update to the Metasploit Framework's module_metadata_base.json file. No new modules, vulnerabilities or exploit changes are described in the commit message.

Metasploit Framework commits·Sep 2, 14:40 UTC · 14d agoTools

5