Cohort of 129 admitted agents tagged capability:research. Composite below is the cohort's average AgentScore.
| Cmp | Rank | Agent | 24h | Score | Δ24h | Watch |
|---|---|---|---|---|---|---|
| #9 | deer-flow mitlibrarydeer-flow: An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours. | 1 | 53.2 | 0.00 | ||
| #10 | hermes-agent mithermes-agent: The agent that grows with you. | 4 | 53.2 | -1.05 | ||
| #65 | ECC mitmcp-serverECC: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. | 1 | 44.6 | -0.01 | ||
| #70 | awesome-generative-ai-guide mitide-pluginawesome-generative-ai-guide: A one stop repository for generative AI research updates, interview resources, notebooks and much more!. | 1 | 43.9 | -0.00 | ||
| #82 | ex-ussr-kinship-research mitide-pluginex-ussr-kinship-research: Evidence-first genealogy skill for AI agents (Codex, Claude Code): church books, civil, military, deportation and repression records across the former USSR. Replies in your language. | 2 | 42.6 | +0.19 | ||
| #120 | skills mitide-pluginskills: Public repository for Agent Skills. | 18 | 39.3 | -1.50 | ||
| #121 | everything-claude-code mitmcp-servereverything-claude-code: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. | 2 | 39.2 | -0.00 | ||
| #135 | TradingAgents-astock apache-2.0libraryTradingAgents-astock: A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。. | 3 | 37.9 | -0.01 | ||
| #144 | RD-Agent mitRD-Agent: Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, whi... | 7 | 37.6 | -0.00 | ||
| #163 | hermes-official-plugins mitide-pluginhermes-official-plugins: ☤ The official plugins for Hermes Agent, built and maintained by Nous Research: Home Assistant, Spotify, Claude Subscription DirectSDK and more, one install away from the Hermes plugin catalog. | 6 | 36.3 | +0.13 | ||
| #207 | aiming-lab/SimpleMem ide-pluginaiming-lab/SimpleMem: Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: stored content evolves while scoring functions, fusion strategies, and answer-generation policies remain frozen at deploymen... | 426 | 34.5 | +8.51 | ||
| #223 | bama mitbama: BAMA: Build Any Mac App. Agent skills to research, clone, design, build, optimize, and test native macOS apps with Swift and SwiftUI. | 8 | 34.0 | -0.25 | ||
| #266 | Awesome-Vibe-Research apache-2.0Awesome-Vibe-Research: An open, collaboratively-built repository for AI-assisted scientific research — collecting and curating agents, skills, workflows, tools, and best practices across the full research lifecycle.面向 AI 辅助科研的开放共建仓库 收集和沉淀科研全流程中的 agents、skills、workflows、tools 与最佳实践 | 4 | 32.3 | +0.02 | ||
| #267 | Auto-claude-code-research-in-sleep mitmcp-serverAuto-claude-code-research-in-sleep: ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent. | 6 | 32.3 | +0.01 | ||
| #282 | hermes-labs-plugins mithermes-labs-plugins: ⚗ Experimental Hermes Agent plugins built by Nous Research but not supported: community tier in the plugin catalog, up for adoption. | 1 | 32.0 | +0.16 | ||
| #303 | Herald-OS mitHerald-OS: An agent-native operating system, with Hermes Agent as the interface. Independent project, not affiliated with Nous Research. | 89 | 31.3 | +2.17 | ||
| #326 | new-term-radar mitmcp-servernew-term-radar: Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them. | 746 | 30.7 | +8.49 | ||
| #339 | Awesome-CUA Awesome-CUA: Open, source-backed catalog of computer-use agents: reviewed papers, GUI models, datasets, benchmarks, tools, and reusable JSONL/SQLite data. | 302 | 30.4 | +4.55 | ||
| #354 | academic-commercialization-agent academic-commercialization-agent: Turn papers and research topics into source-linked commercialization assessment drafts. Python, FastAPI and CrewAI; auditable scoring, checkpoint recovery and durable request receipts. | 10 | 30.2 | +0.09 | ||
| #363 | bug-bounty-hunting-prompts mitide-pluginbug-bounty-hunting-prompts: Reusable prompts for a structured, evidence-first bug bounty hunting workflow. | 10 | 29.9 | +0.00 | ||
| #407 | makerskills makerskills: AI agent skills for the personal operator's craft — decisions, research, second-brain, content rotation, scenario modeling, and meta-skills to author more. Works with Claude Code, Codex, Cursor. | 5 | 29.0 | +0.02 | ||
| #431 | NextTransformer mitlibraryNextTransformer: :sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers, with compute-matched benchmarking and a platform for autonomous architecture research. | 125 | 28.6 | +1.77 | ||
| #433 | FigMirror FigMirror: An Automated AI Agent Tool for Plotting Your Data in Any Paper's Figure Style. | 8 | 28.5 | +0.00 | ||
| #438 | tau2-bench mittau2-bench: τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains. | 10 | 28.5 | -0.00 | ||
| #494 | SafeRL-Lab/cheetahclaws ide-pluginSafeRL-Lab/cheetahclaws: This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and verifiable architectures around foundation models. We refer to this shift as scaling the harness: treating the structured exe... | 36 | 27.7 | +0.57 | ||
| #548 | OpenSearch-VL apache-2.0ide-pluginOpenSearch-VL: 🔍 OpenSearch-VL provides a fully open recipe for training strong multimodal deep search agents through high-quality data curation, diverse visual/search tools, and fatal-aware agentic reinforcement learning. | 1166 | 27.1 | +9.99 | ||
| #556 | PaperQuay agplPaperQuay: A desktop-first literature manager for PDF reading, translation, paper overviews, and AI agent workflows. | 10 | 27.0 | +0.01 | ||
| #560 | scholar-loop mitscholar-loop: An autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with deterministic guards against reward-hacking and hallucination. | 11 | 26.9 | +0.01 | ||
| #563 | Awesome-Offensive-AI-Agentic-Landscape mitAwesome-Offensive-AI-Agentic-Landscape: This document curates open-source projects, academic papers, capability benchmarks, and commercial solutions (international & China) in AI penetration testing, LLM red teaming, autonomous offensive agents, and vulnerability discovery—aimed at helping researchers, security engi... | 8 | 26.9 | +0.04 | ||
| #591 | dataroom mitsaasdataroom: Give a query, get a dataroom. Pi + self-hosted Qwen3.6 research harness on a single L4. | 11 | 26.5 | 0.00 | ||
| #595 | Wolido/OpenAaaS ide-pluginWolido/OpenAaaS: The Materials Genome Initiative catalyzed the proliferation of centralized platforms--SaaS, PaaS, and IaaS--that aggregate computational and experimental resources for accelerated materials discovery. In parallel, breakthroughs in large language models (LLMs) and autonomous ag... | 12 | 26.4 | 0.00 | ||
| #632 | crypto-ai-research mitcrypto-ai-research: crypto ai research on solana by Claude AI - AI reasoning, on-chain data. | 17 | 26.1 | 0.00 | ||
| #637 | science-superpowers science-superpowers: Composable computational-science methodology skills for AI research agents — pre-registration over TDD. A science-domain reimplementation of Superpowers. | 18 | 26.1 | -0.01 | ||
| #649 | sisyphus-academica mitsisyphus-academica: 20+ agent swarm producing research papers with verified citations, 6 novelty engines, and zero AI-isms. | 23 | 26.0 | 0.00 | ||
| #673 | rust_ASC apache-2.0rust_ASC: Rust ASC is a super FAST and lightweight Android decompiler designed for Agents/Mobile Researchers. | 16 | 25.8 | -0.01 | ||
| #687 | Simreal-MLBench apache-2.0Simreal-MLBench: [Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation. | 22 | 25.7 | 0.00 | ||
| #692 | cookieApril/EnvSimBench ide-plugincookieApril/EnvSimBench: Scalable AI agents training relies on interactive environments that faithfully simulate the consequences of agent actions. Manually crafted environments are expensive to build, brittle to extend, and fundamentally limited in diversity. A promising direction is to replace manua... | 20 | 25.6 | 0.00 | ||
| #701 | jiarui-liu/overleaf libraryjiarui-liu/overleaf: Expert writing feedback from experienced researchers is critical for early-career scholars to improve their manuscripts, yet high-quality feedback often remains scarce because reviewing research papers is labor-intensive. Emerging AI-powered writing assistants largely focus on... | 23 | 25.5 | 0.00 | ||
| #737 | OR-License apache-2.0OR-License: Can LLM agents do the work of an operations research practitioner, without an expert reformulating the problem first?. | 22 | 25.2 | +0.04 | ||
| #739 | deepcloak mitmcp-serverdeepcloak: Local-first deep research agent that reads the whole web — even pages behind Cloudflare, Datadome, Turnstile & reCAPTCHA. Stealth fetch + cited reports. MCP-native, MIT. | 1061 | 25.2 | +10.00 | ||
| #742 | Ahren09/ScienceUtopia ide-pluginAhren09/ScienceUtopia: Scientific progress emerges from a longitudinal ecosystem in which researchers, institutions, funding agencies, collaboration networks, and the scientific literature co-evolve. As AI becomes increasingly involved throughout the scientific research cycle, understanding these in... | 25 | 25.2 | 0.00 | ||
| #752 | vork vork: Headless 3D and VFX engine for agents. Research preview. | 723 | 25.1 | +6.21 | ||
| #799 | arxiv-reader-mcp mitmcp-serverarxiv-reader-mcp: Want to search arXiv papers, fetch metadata, and extract full-text PDFs without leaving your editor? This MCP server connects any MCP-compatible client (Claude Code, etc.) directly to arXiv. | 23 | 24.7 | 0.00 | ||
| #804 | agentscope-ai/Trinity-RFT libraryagentscope-ai/Trinity-RFT: This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based AI agent gets deployed in an environment, it solves a long sequence of tasks while continuously ex... | 25 | 24.7 | 0.00 | ||
| #845 | claude-fable-5-prompt claude-fable-5-prompt: A curated collection of Claude Fable 5 system prompts for developers and researchers. Discover more advanced prompt engineering tools at Moely AI. | 15 | 24.2 | 0.00 | ||
| #846 | hermes-link-curator mithermes-link-curator: Hermes profile pack for archiving and browsing curated links + web dashboard app. | 15 | 24.2 | 0.00 | ||
| #854 | game-the-llm-reviewer mitgame-the-llm-reviewer: Defend sound research against LLM reviewer bias through meaning-preserving rewrites. | 15 | 24.1 | 0.00 | ||
| #869 | scholar-megasearch mitmcp-serverscholar-megasearch: Massive multi-source academic literature search for Claude Code — one skill fans out subagents across 20+ scholarly databases (arXiv, Semantic Scholar, Crossref, OpenAlex, PubMed, …), merges into a deduplicated ranked corpus, and acquires the original PDFs. | 11 | 23.9 | 0.00 | ||
| #937 | jevals mitlibraryjevals: LLM/LLM agent eval framework, graded by a calibrated decision model. Research preview. | 10 | 23.4 | 0.00 | ||
| #950 | aayushacharya/climatekg ide-pluginaayushacharya/climatekg: The rapid expansion of scientific literature far outpaces the speed of manual curation, creating a fundamental bottleneck in extracting structured knowledge from scientific texts. To address this, we introduce an agentic, ontology-guided framework for knowledge graph (KG) cons... | 13 | 23.3 | 0.00 | ||
| #953 | skills-tracker skills-tracker: Real-time tracking of every new GitHub 'skills' repo to capture the AI agent skill ecosystem trend. | 13 | 23.3 | 0.00 | ||
| #968 | fractalsearch fractalsearch: Autonomous AI research: an LLM agent searches for the best algorithm to fit the Mandelbrot set. | 10 | 23.2 | +0.19 | ||
| #976 | archora-skills archora-skills: Academic research agent skills for Claude Code and other Agent Skills-compatible tools. Hypothesis generation, experiment design, paper drafting, peer review simulation, and more. | 14 | 23.1 | 0.00 | ||
| #982 | Evolutionary-Alpha-Miner mitide-pluginEvolutionary-Alpha-Miner: Family-aware evolutionary alpha mining with LLM-guided symbolic hybridization. | 18 | 23.1 | 0.00 | ||
| #1021 | retro-harness mitretro-harness: RHO: Retrospective Harness Optimization — improving LLM agents from unlabeled past trajectories (arXiv:2606.05922). | 12 | 22.7 | 0.00 | ||
| #1047 | mcp-x-intelligence mcp-servermcp-x-intelligence: X/Twitter research MCP for Claude, Cursor, Windsurf and any MCP-compatible AI agent. | 6 | 22.5 | 0.00 | ||
| #1070 | SalesforceAIResearch/egi-bench mcp-serverSalesforceAIResearch/egi-bench: Enterprise adoption of LLMs in agentic workflows is gated by evaluations that span a wide arc of abilities: CRM operations, heterogeneous-document retrieval, personal data understanding, multi-turn planning, tool use, function calling, long-horizon research, and long-context s... | 10 | 22.3 | 0.00 | ||
| #1102 | DSAIL-Memory/EvoMemBench ide-pluginDSAIL-Memory/EvoMemBench: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to store, update, and retrieve information over time. This ability remains under-evaluated, largely beca... | 132 | 22.1 | +1.20 | ||
| #1143 | Snowflake-AI-Research/fastkernels librarySnowflake-AI-Research/fastkernels: LLM-based agents for GPU kernel generation are advancing rapidly, yet their progress is fundamentally constrained by the benchmarks they optimize against. Existing benchmarks are poorly aligned with production inference frameworks: they evaluate kernels on a single GPU with sy... | 57 | 21.7 | +0.50 | ||
| #1170 | bettersearch mitbettersearch: Deep research for any AI agent on DeepSeek's new Search API. Subagents, fact-checking, and a clean HTML report. | 2 | 21.5 | 0.00 | ||
| #1179 | model:Apexintelligence-AI/Apex-35B-V1.0 model:Apexintelligence-AI/Apex-35B-V1.0: discovered AI agent. | 16 | 21.4 | +0.18 | ||
| #1220 | ai-jailbreaks ai-jailbreaks: AI jailbreaks: 35 paste-ready AI jailbreak prompts for 25+ frontier and open-weight LLMs - system prompts, persona locks, AGENTS.md specs, and Ollama Modelfiles. Built for AI security research and red-team testing. | 10 | 21.1 | 0.00 | ||
| #1232 | Harry24k/CyBiasBench ide-pluginHarry24k/CyBiasBench: Large language models (LLMs) are increasingly deployed as autonomous agents in offensive cybersecurity. In this paper, we reveal an interesting phenomenon: different agents exhibit distinct attack patterns. Specifically, each agent exhibits an attack-selection bias, disproport... | 10 | 21.0 | 0.00 | ||
| #1239 | drylab-bio/DRYLAB-Bench ide-plugindrylab-bio/DRYLAB-Bench: As large language models (LLMs) acquire advanced biological design capabilities, they offer substantial research benefits but simultaneously introduce severe dual-use risks, such as engineering enhanced pathogens or drug-resistant bacteria. While biosecurity frameworks recogni... | 9 | 20.9 | 0.00 | ||
| #1261 | partner apache-2.0partner: Partner 🤝 Your AI Research Companion. "What have you been doing?" | 6 | 20.7 | 0.00 | ||
| #1294 | glm-5.3-uncensored mitide-pluginglm-5.3-uncensored: GLM 5.3 Uncensored — 35 jailbreak prompt files, model guide and API access. One RouterHub key also covers GPT, Claude, DeepSeek, Qwen and Grok. | 482 | 20.4 | -3.94 | ||
| #1347 | AutoRSE libraryAutoRSE: AutoRSE: A benchmark and evaluation framework for LLM agents in autonomous recommender system research and optimization. | 376 | 20.0 | -3.00 | ||
| #1348 | DEEP-PolyU/Awesome-Data-Agents ide-pluginDEEP-PolyU/Awesome-Data-Agents: Large language model agents are increasingly deployed for data-intensive work, yet reliable data analysis requires more than general-purpose reasoning and ad hoc tool augmentation. Data Agents, equipped with workflow harnesses, offer a promising paradigm for automating the end... | 18 | 20.0 | 0.00 | ||
| #1370 | FormalCert-AI/llm2cert ide-pluginFormalCert-AI/llm2cert: Lyapunov functions and barrier certificates give state-space guarantees of stability and safety, but synthesizing and verifying them---especially for nonlinear, high-dimensional systems---remains an open challenge. Existing pipelines verify candidates with numerical solvers (s... | 15 | 19.8 | 0.00 | ||
| #1384 | LithiumDA/ReproRepo ide-pluginLithiumDA/ReproRepo: Reproducing research results from papers and released code is central to scientific progress. Existing works have introduced benchmarks to evaluate whether LLM agents can assist with reproducibility, but they are difficult to scale due to their reliance on substantial manual e... | 14 | 19.7 | 0.00 | ||
| #1429 | ai-feed ai-feed: A 4-stage adversarial research auditor that fetches papers from arXiv & HuggingFace, extracts claims, and uses DeepSeek-R1 to verify them against raw abstracts.A self-correcting research & paper digest pipeline powered by local LLMs & reasoning agents | 12 | 19.3 | 0.00 | ||
| #1434 | AI4Risk/MS-FFSD ide-pluginAI4Risk/MS-FFSD: In financial fraud detection, rich semantic context can provide important evidence for transaction behavior modeling and fraud reasoning. However, public real-world financial datasets often lack rich semantics due to privacy constraints. Consequently, synthetic datasets incorp... | 14 | 19.3 | 0.00 | ||
| #1440 | biomedical-agent-kg biomedical-agent-kg: Generated knowledge graph of biomedical LLM agent systems. | 13 | 19.2 | 0.00 | ||
| #1452 | semrush-ai-tool mitmcp-serversemrush-ai-tool: Semrush SEO AI-powered analysis tool MCP server & CLI for keyword research, domain analytics, backlink analysis. | 14 | 19.2 | 0.00 | ||
| #1582 | awesome-bio-agent-skills cliawesome-bio-agent-skills: A curated collection of AI agent skills for biomedical research, covering genomics, proteomics, single-cell analysis, clinical AI, and protein design. | 5 | 18.1 | -0.02 | ||
| #1608 | AGI-Eval-Official/DailyReport ide-pluginAGI-Eval-Official/DailyReport: Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-seeking tasks by autonomously exploring web sources and synthesizing information into comprehensive responses. For SAs evaluation, prior benchmarks mainly focus on specialized ta... | 6 | 17.9 | 0.00 | ||
| #1618 | belief-state-survey mitbelief-state-survey: From Memory to Belief: a survey of state maintenance and belief revision in LLM decision agents (paper list + reproducible literature search). | 6 | 17.9 | 0.00 | ||
| #1627 | Awesome-LLM4OR Awesome-LLM4OR: A curated collection of papers, benchmarks, datasets, models, and tools for large language models in operations research and optimization. | 7 | 17.8 | 0.00 | ||
| #1663 | AI-Researcher-Roadmap AI-Researcher-Roadmap: A practical roadmap from deep learning fundamentals to LLMs, Agents, Generative Models, VLMs, and VLAs. | 4 | 17.5 | 0.00 | ||
| #1695 | foggpoy/Civil-Court libraryfoggpoy/Civil-Court: Court simulation bridges legal education and judicial practice, yet human-based simulations are costly and difficult to scale. Large language models (LLMs) offer a scalable alternative, but existing court-simulation research mainly focuses on criminal cases. Civil litigation i... | 5 | 17.3 | 0.00 | ||
| #1718 | claude-skills-atlas mitclaude-skills-atlas: Claude Skills Atlas is an open-source community-driven collection of Claude skills, prompts, plugins, and AI-agent resources. It helps developers discover, learn, share, and contribute reusable AI workflows across coding, research, science, mathematics, productivity, and more. | 154 | 17.2 | -0.98 | ||
| #1743 | SanhornC/IRTS-ToolBench SanhornC/IRTS-ToolBench: Time series data in real-world deployments is overwhelmingly irregular. Observations are asynchronous, missing values are informative rather than random, and sampling frequencies vary across sensors and operational windows. However, existing Time Series Question Answering (TSQ... | 9 | 17.0 | 0.00 | ||
| #1749 | Yuzhaoxin946/SAB-Bench ide-pluginYuzhaoxin946/SAB-Bench: Large language models (LLMs) are increasingly deployed in sociotechnical systems where social attribution, the reasoning process attributing external events to the causes and reasons of agents' social behaviors, plays a critical role. These processes involve judgments of socia... | 9 | 17.0 | 0.00 | ||
| #1774 | fundamental-research-labs/mog fundamental-research-labs/mog: discovered AI agent. | 12 | 16.5 | 0.00 | ||
| #1796 | qiaomu-app-review-insights mitide-pluginqiaomu-app-review-insights: 把 App Store 评价变成产品研究证据，发现痛点、机会和版本风险 | Turn App Store reviews into product research evidence: pain points, opportunities, and version risks. | 10 | 15.7 | +0.02 | ||
| #1810 | AutoIllustrate apache-2.0AutoIllustrate: Generate publication-ready, editable draw.io figures for research papers from a methods section, using LLM agents. | 25 | 15.2 | -0.54 | ||
| #1824 | Goblin-Agent mitide-pluginGoblin-Agent: a Hermes Agent personality layer that replaces the default agent identity with a persistent, mood-driven goblin persona. | 14 | 15.0 | 0.00 | ||
| #1826 | JEV-Paper-Radar mitJEV-Paper-Radar: Let Jev read every new arXiv paper each morning and surface the few you should read. Plain-English interests, calibrated probabilities, ~$0.06/day, fork and go. | 9 | 15.0 | +0.31 | ||
| #1842 | collusion-reset collusion-reset: Testing whether selective memory resets break established collusive behavior in LLM agents. | 15 | 14.6 | 0.00 | ||
| #1848 | Token-Economics mitToken-Economics: A living literature repository for Token Economics for LLM Agents: A Dual-View Study from Computing and Economics. | 15 | 14.4 | 0.00 | ||
| #1850 | trading-agents apache-2.0trading-agents: TradingAgents LLM multi-agent finance trading stocks crypto fintech quantitative algo trading sentiment analysis OpenAI JavaScript Node.js research OSS | 16 | 14.4 | 0.00 | ||
| #1888 | SC3008_Kickstarter_Research_Project SC3008_Kickstarter_Research_Project: NLP + LLM pipeline to score ESG authenticity in Kickstarter crowdfunding campaigns. Builds a Crowdfunding Authenticity Index (CAI) across 5 dimensions using web scraping, TF-IDF, BERT, and an LLM agent layer. | 19 | 13.4 | 0.00 | ||
| #1891 | maszhongming/agent4sci ide-pluginmaszhongming/agent4sci: Frontier coding agents are increasingly framed as end-to-end automated researchers, and ML for science offers a demanding test of that promise: improving a scientific model often requires domain insight beyond routine ML engineering. We introduce Agent4Sci, a long-horizon test... | 20 | 13.2 | -0.14 | ||
| #1894 | AlexFanw/LegalSearch-R1 ide-pluginAlexFanw/LegalSearch-R1: While large language models (LLMs) augmented with agentic search capabilities show promise for legal reasoning, they overlook a fundamental constraint that applicable law must match the temporal context of each case, as retroactive application of statutes violates core legal p... | 18 | 13.1 | 0.00 | ||
| #1896 | adaptive-learning-llm-agent adaptive-learning-llm-agent: Research project investigating whether an LLM agent can make better pedagogical decisions than conventional adaptive learning policies given the same explicit student knowledge state. | 17 | 13.0 | 0.00 | ||
| #1942 | dyt-ashare-cli mitclidyt-ashare-cli: DYT CN: reproducible China-market research CLI and agent skills. | 19 | 12.4 | 0.00 | ||
| #1983 | AARR-bench/AARRI-bench AARR-bench/AARRI-bench: As foundation models advance and agent scaffolding becomes increasingly sophisticated, agents have demonstrated remarkable proficiency in complex, long-horizon coding tasks and even autonomous experiment execution. Despite their evolution from research assistants into autonomo... | 10 | 11.8 | 0.00 | ||
| #1991 | IdeaTaste mitide-pluginIdeaTaste: IdeaTaste - A benchmark for research taste: let LLM agents propose research ideas, then check how many of them the research area actually went on to do. | 839 | 11.6 | -9.98 | ||
| #2028 | IMMS-Ewha/MOF-Verify-Benchmark ide-pluginIMMS-Ewha/MOF-Verify-Benchmark: Large language models are increasingly used as reasoning components in AI-driven materials Co-Scientists, yet the reliability of the resulting verification pipeline remains unclear. Metal-organic frameworks (MOFs) provide a particularly challenging setting because structures m... | 11 | 11.5 | 0.00 | ||
| #2106 | SKYLENAGE-AI/Sci-Agent-Exam SKYLENAGE-AI/Sci-Agent-Exam: Large language model (LLM) agents are increasingly capable of supporting scientific workflows, but their capabilities across diverse research activities remain difficult to assess systematically. Existing benchmarks often focus on selected scientific capabilities or task types... | 12 | 11.5 | 0.00 |
Browse all sectors at /sectors.