Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
 promptadmin
|
ddd676ae49 |
@@ -2,9 +2,9 @@
|
||||
title: "Changelog"
|
||||
task: ""
|
||||
lineage_type: import
|
||||
upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/2700f0b8/CHANGELOG.md
|
||||
upstream_sha: 2700f0b8
|
||||
imported_at: 2026-09-04
|
||||
upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/539ec1dc/CHANGELOG.md
|
||||
upstream_sha: 539ec1dc
|
||||
imported_at: 2026-06-26
|
||||
prompt_class: catalogue
|
||||
upstream_changes: accepted
|
||||
author: upstream
|
||||
@@ -23,8 +23,6 @@ All notable changes to this list will be documented here.
|
||||
|
||||
| Date | Change |
|
||||
|---|---|
|
||||
| September 04 2026 | **Link audit** — Updated redirected URL for EvoAgentX and removed dead Better Agent entry. |
|
||||
| July 22 2026 | **Link audit** — Updated 7 redirected URLs (Open Interpreter, Remio, Toolhouse, Pilot Protocol, LLMGraph, Agent Learning Kit, Lavender) and removed the dead Agent Starter entry. |
|
||||
| June 26 2026 | **Style reformatting** — Converted all 407 tool entries to the new compact format: `` `TIER` `[Language]` `[Type]` `` replacing the legacy `(🏷️ ...)` tag style. Tier badges (`🚀` Production-Ready, `🌱` Growing, `🔬` Emerging) applied consistently across all sections. Descriptions trimmed to one clear sentence, promotional language removed. Zero duplicate links. Full awesome-lint structural compliance maintained. |
|
||||
| June 07 2026 | Performed link audit: fixed redirected URLs (including Bland AI, Podman, Strands Agents, Google ADK, Mistral, Railway, Sistava, Windsurf, Nuance, ADK loop-agents), updated Project Glasswing to correct official link, and removed dead TinyTools link. |
|
||||
| May 25 2026 | Added Sistava to Multi-Agent Consumer Platforms. |
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
title: "Awesome AI Agents 2026"
|
||||
task: ""
|
||||
lineage_type: import
|
||||
upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/2700f0b8/README.md
|
||||
upstream_sha: 2700f0b8
|
||||
imported_at: 2026-09-04
|
||||
upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/02e8c988/README.md
|
||||
upstream_sha: 02e8c988
|
||||
imported_at: 2026-08-16
|
||||
prompt_class: catalogue
|
||||
upstream_changes: accepted
|
||||
author: upstream
|
||||
@@ -125,7 +125,6 @@ validated: false
|
||||
- [JetBrains AI](https://www.jetbrains.com/ai/) `🌱` `[Kotlin]` `[JetBrains]` - Deep AI integration across all JetBrains IDEs with context-aware completions and refactoring.
|
||||
- [Juggler](https://github.com/juggler-ai/juggler) `🌱` `[Desktop]` `[Local]` - Multi-client desktop/remote GUI agent with inspectable tool calls, branching-thread editable context, and plugin extensibility.
|
||||
- [Kiro](https://kiro.dev) `🚀` `[Cloud]` `[IDE]` - Spec-driven development agent that writes specs, auto-generates tasks, implements code, and automates DevOps workflows.
|
||||
- [Kolega Code](https://github.com/kolega-ai/kolega-code) `🔬` `[Python]` `[CLI]` - Terminal coding agent where the model writes its own multi-agent workflows across 15+ model providers.
|
||||
- [Open Interpreter](https://github.com/openinterpreter/openinterpreter) `🌱` `[Python]` `[CLI]` - Execute code locally via natural-language model instructions with a ChatGPT-like interface.
|
||||
- [opencode](https://github.com/anomalyco/opencode) `🌱` `[TypeScript]` `[Desktop]` - Open-source coding agent available as a desktop app with a visual interface.
|
||||
- [OpenHands](https://github.com/OpenHands/OpenHands) `🌱` `[Python]` `[Docker]` - AI-driven development platform that writes, tests, and deploys code autonomously.
|
||||
@@ -177,7 +176,7 @@ validated: false
|
||||
## Multi-Agent Systems
|
||||
|
||||
- [AgentVerse](https://github.com/OpenBMB/AgentVerse) `🌱` `[Python]` `[Multi-Agent]` - Framework for building custom multi-agent environments to accomplish collaborative tasks.
|
||||
- [EvoAgentX](https://github.com/ANative-Lab/EvoAgentX) `🌱` `[Python]` `[Multi-Agent]` - Evaluates and evolves agentic workflows over time using automatic optimization.
|
||||
- [EvoAgentX](https://github.com/EvoAgentX/EvoAgentX) `🌱` `[Python]` `[Multi-Agent]` - Evaluates and evolves agentic workflows over time using automatic optimization.
|
||||
- [Hivekeep](https://github.com/MarlBurroW/hivekeep) `🔬` `[TypeScript]` `[Multi-Agent]` - Runs a team of specialized self-hosted agents that collaborate, share memory, and build their own tools.
|
||||
- [Hivemoot](https://github.com/hivemoot/hivemoot) `🚀` `[Python]` `[GitHub]` - Autonomous agent teams that collaboratively build software on GitHub.
|
||||
- [MetaGPT](https://github.com/FoundationAgents/MetaGPT) `🌱` `[Python]` `[Multi-Agent]` - Simulates a full software company workflow from requirements to PRs using role-playing agents.
|
||||
@@ -207,11 +206,10 @@ The protocol layer that enables agents to discover tools, communicate with each
|
||||
- [HCS Agent Protocol](https://github.com/hashgraph/hedera-agent-kit-js) `🌱` `[TypeScript]` `[IDE]` - Hedera open standards for agent identity with trustless P2P communication and 187K+ verified agents.
|
||||
- [HIG Doctor](https://github.com/raintree-technology/hig-doctor) `🌱` `[TypeScript]` `[MCP]` - Apple HIG audit CLI and MCP server exposing design-guideline lookup and project audits for coding agents across SwiftUI, UIKit, React, Next.js, Flutter, Compose, HTML, and CSS.
|
||||
- [Hyper](https://github.com/hyperfx-ai/marketing-skills) `🌱` `[Cloud]` `[MCP]` - Open-source Agent Skills and a hosted MCP connecting agents to 200+ marketing integrations across paid ads, SEO, analytics, social, and image and video generation, with a human-approval gate on every action.
|
||||
- [Live Tennis API MCP](https://github.com/livetennisapi/livetennisapi-mcp) `🔬` `[TypeScript]` `[MCP]` - Exposes live tennis scores, fixtures, rankings, and head-to-head to agents, with market prices and win-probability on paid tiers.
|
||||
- [MCP Registry](https://github.com/modelcontextprotocol) `🌱` `[Python]` `[Multi-Agent]` - Official Model Context Protocol specification and server implementations for standardized tool access.
|
||||
- [mcp-nest](https://github.com/CharanBharathula/mcp-nest) `🌱` `[Python]` `[MCP]` - Unified Model Context Protocol (MCP) server for executing code and managing files.
|
||||
- [NotFair](https://notfair.co) `🚀` `[Cloud]` `[MCP]` - Hosted Google Ads MCP server for diagnosing, optimizing, and executing campaign changes via the Google Ads API with a human-approval gate.
|
||||
- [NotFair Skills](https://github.com/nowork-studio/notfair-plugin) `🚀` `[TypeScript]` `[MCP]` - Open-source Claude Code skills for SEO, GEO, Google Ads, and Meta Ads, connecting to live data through Google Ads MCP, Meta Ads MCP, Google Search Console MCP, and Google Analytics (GA4) MCP.
|
||||
- [NotFair Skills](https://github.com/nowork-studio/NotFair) `🚀` `[TypeScript]` `[MCP]` - Open-source Claude Code skills for SEO, GEO, Google Ads, and Meta Ads, connecting to live data through Google Ads MCP, Meta Ads MCP, Google Search Console MCP, and Google Analytics (GA4) MCP.
|
||||
- [Toolhouse](https://toolhouse.ai/en/) `🌱` `[Python]` `[Multi-Agent]` - Cloud-hosted tool infrastructure for agents with optimized execution and low-latency access.
|
||||
- [Xquik](https://github.com/Xquik-dev/x-twitter-scraper) `🔬` `[Cloud]` `[MCP]` - Hosted X Twitter data MCP for search, follower export, monitors, and confirmation-gated writes.
|
||||
- [Zapier MCP Server](https://zapier.com/mcp) `🌱` `[Cloud]` `[MCP]` - Connect agents to 7,000+ app integrations via MCP, powered by Zapier's automation platform.
|
||||
@@ -308,7 +306,6 @@ Sandboxes, web scrapers, browser automation, and networking layers that agents d
|
||||
- [Patronus AI LYNX](https://patronus.ai/) `🌱` `[Cloud]` `[Testing]` - Hallucination detection system beating GPT-4 baselines, with specialized testing for agent outputs and LLM-generated content quality.
|
||||
- [Arize Phoenix](https://github.com/Arize-ai/phoenix) `🌱` `[Python]` `[Observability]` - Open-source observability platform built on OpenTelemetry for tracing, evaluating, and debugging AI agents.
|
||||
- [Braintrust](https://www.braintrust.dev) `🌱` `[TypeScript]` `[Evaluation]` - Eval-driven development platform with experiment tracking and prompt optimization for agent quality.
|
||||
- [ClawMetry](https://github.com/vivekchand/clawmetry) `🔬` `[Python]` `[Observability]` - Self-hosted observability and opt-in kill switch for coding agents, reading the session logs runtimes already write to disk ([website](https://clawmetry.com)).
|
||||
- [ElevenAgents](https://elevenlabs.io/agents) `🚀` `[Cloud]` `[Voice]` - Voice agent platform from ElevenLabs for customer support automation with HIPAA compliance and multi-language support.
|
||||
- [DriftGuard](https://github.com/sujal-maheshwari2004/DriftGuard) `🌱` `[Python]` `[Multi-Agent]` - Semantic memory guardrails using causal graphs to prevent agents from repeating past failures.
|
||||
- [Galley](https://github.com/shinpr/galley) `🔬` `[Go]` `[Multi-Agent]` - Pairs independently configured executors and supervisors with repository-defined quality gates and inspectable evidence for each coding attempt.
|
||||
@@ -337,6 +334,7 @@ Frontend workspaces and chat interfaces with built-in agent plugins and tool-use
|
||||
|
||||
- [AionUi](https://github.com/iOfficeAI/AionUi) `🚀` `[Desktop]` `[Multi-Agent]` - Connects 20+ AI CLIs and any API key in a local, open-source multi-agent desktop workspace.
|
||||
- [AnythingLLM](https://github.com/Mintplex-Labs/anything-llm) `🌱` `[TypeScript]` `[RAG]` - All-in-one AI application with RAG, agents, and multi-model support for desktop and Docker.
|
||||
- [Better Agent](https://github.com/ofekron/better-agent) `🔬` `[Desktop]` `[Multi-Agent]` - Manages Claude, Codex, and Gemini coding-agent sessions with parallel forks, delegation, persistence, and restart recovery.
|
||||
- [DB-GPT](https://github.com/eosphoros-ai/DB-GPT) `🌱` `[Python]` `[Database]` - Data interaction platform with local LLM support for 100% private database and analytics agents.
|
||||
- [LibreChat](https://github.com/danny-avila/LibreChat) `🌱` `[TypeScript]` `[IDE]` - Self-hosted multi-model chat interface supporting all major AI providers with access control.
|
||||
- [LobeHub](https://lobehub.com/) `🌱` `[TypeScript]` `[Multi-Agent]` - Modern platform for hybrid work and AI-driven collaboration with extensible agent teams and rapid integration.
|
||||
@@ -344,7 +342,6 @@ Frontend workspaces and chat interfaces with built-in agent plugins and tool-use
|
||||
- [OpenHuman](https://github.com/tinyhumansai/openhuman) `🚀` `[Rust]` `[Memory]` - Self-hosted local-first personal AI assistant with a Rust core, desktop apps, knowledge-graph memory, skills, voice, and multi-channel messaging.
|
||||
- [Orkas](https://github.com/Orkas-AI/Orkas) `🔬` `[Desktop]` `[Multi-Agent]` - Runs parallel AI agents in a local-first desktop workspace with shared files, BYOK providers, and optional sync.
|
||||
- [OpenWebUI](https://github.com/open-webui/open-webui) `🌱` `[TypeScript]` `[RAG]` - Extensible local AI interface with built-in RAG, tool use, and support for multi-agent workflows.
|
||||
- [FutureOS](https://github.com/futuregene/future-os) `🔬` `[Rust]` `[CLI]` - One approval-gated AI agent spanning terminal, desktop, mobile, and chat clients on a shared local Rust backend.
|
||||
- [lucinate](https://github.com/lucinate-ai/lucinate) `🌱` `[Go]` `[TUI]` - Multi-backend terminal AI chat client for OpenClaw, Hermes, Ollama, and OpenAI-compatible APIs with routines, multi-agent switching, and local agent skills.
|
||||
|
||||
## Agent Deployment and Hosting
|
||||
@@ -634,7 +631,6 @@ Platforms for building, deploying, and scaling voice-based AI agents across call
|
||||
- [Deepgram](https://deepgram.com) `🌱` `[Cloud]` `[Pipeline]` - Sub-300ms speech-to-text and text-to-speech APIs purpose-built for real-time voice agent pipelines.
|
||||
- [ElevenLabs](https://elevenlabs.io) `🌱` `[Cloud]` `[RAG]` - Industry- voice AI with 75ms latency, Conversational AI 2.0, RAG, and HIPAA compliance.
|
||||
- [HeyGen](https://www.heygen.com) `🌱` `[Cloud]` `[IDE]` - Creates AI talking avatars with voice cloning and lip-sync for video-based agent interactions.
|
||||
- [Hermes](https://www.buildwithhermes.com) `🌱` `[Cloud]` `[Voice]` - White-label voice agent platform for agencies, bundling telephony, CRM, campaign orchestration, and usage billing so one team can run agents for many client brands.
|
||||
- [PolyAI](https://poly.ai/en) `🚀` `[Cloud]` `[Voice]` - Enterprise voice AI platform for natural multi-turn conversations with high-volume call handling.
|
||||
- [Retell AI](https://www.retellai.com) `🌱` `[Cloud]` `[Voice]` - Builds human-like voice agents with multi-language telephony support and low-latency responses.
|
||||
- [Synthesia](https://www.synthesia.io) `🌱` `[Cloud]` `[IDE]` - Generates AI video avatars that speak in 120+ languages for training and communication agents.
|
||||
@@ -701,7 +697,7 @@ All-in-one AI platforms providing access to agents, tools, and models through co
|
||||
- [Grok](https://x.ai/grok) `🌱` `[Cloud]` `[Multi-Agent]` - Real-time AI with live X data access, Grok Build for 8-agent parallel code generation, and image generation.
|
||||
- [Meta AI](https://meta.ai) `🚀` `[Cloud]` `[Multi-Agent]` - Llama-powered AI integrated across WhatsApp, Messenger, and Instagram for conversational assistance.
|
||||
- [Microsoft Copilot](https://copilot.microsoft.com) `🚀` `[Cloud]` `[Microsoft]` - AI assistant integrated into Office 365, Teams, and Power Platform for enterprise productivity workflows.
|
||||
- [Sistava](https://sistava.com/) `🌱` `[Cloud]` `[Voice]` - AI agent orchestration platform for deploying multi-channel agents across messaging, voice, and APIs with full Computer Use capabilities on your own OS.
|
||||
- [Sistava](https://sistava.com/en/) `🌱` `[Cloud]` `[Voice]` - AI agent orchestration platform for deploying multi-channel agents across messaging, voice, and APIs with full Computer Use capabilities on your own OS.
|
||||
|
||||
## Open-Source Models for Agents
|
||||
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
title: "Awesome AI Agent Papers"
|
||||
task: ""
|
||||
lineage_type: import
|
||||
upstream_source: https://github.com/VoltAgent/awesome-ai-agent-papers/blob/b4704753/README.md
|
||||
upstream_sha: b4704753
|
||||
imported_at: 2026-09-04
|
||||
upstream_source: https://github.com/VoltAgent/awesome-ai-agent-papers/blob/c8502b6a/README.md
|
||||
upstream_sha: c8502b6a
|
||||
imported_at: 2026-08-08
|
||||
prompt_class: catalogue
|
||||
upstream_changes: accepted
|
||||
author: upstream
|
||||
@@ -31,8 +31,11 @@ validated: false
|
||||
</div>
|
||||
|
||||
[](https://awesome.re)
|
||||
|
||||
|
||||
|
||||
<a href="https://github.com/VoltAgent/voltagent">
|
||||
<img alt="VoltAgent" src="https://cdn.voltagent.dev/website/logo/logo-2-svg.svg" height="20" />
|
||||
</a>
|
||||
[](https://s.voltagent.dev/discord)
|
||||
|
||||
</div>
|
||||
@@ -51,17 +54,6 @@ A curated collection of research papers **published in 2026** and sourced from a
|
||||
|
||||
Whether you're an AI engineer building agent systems, a researcher exploring new architectures, or a developer integrating LLM agents into products, these papers help you stay on top of what's actually working, what's breaking, and where the field is heading. Updated weekly from arXiv.
|
||||
|
||||
## Sponsors
|
||||
|
||||
| | |
|
||||
| :-: | :-- |
|
||||
| <a href="https://crawlbase.com/?utm_source=awesome-ai-agent-papers&utm_medium=sponsorship&utm_campaign=voltagent_2026q3&utm_content=readme_listing"><picture><source media="(prefers-color-scheme: dark)" srcset="https://cdn.voltagent.dev/awesome-repo/crawlbase-new/crawlbase-logo-dark-mode.svg"><img alt="Crawlbase" src="https://cdn.voltagent.dev/awesome-repo/crawlbase-new/crawlbase-logo-light-mode.svg" width="425"></picture></a> | [Crawlbase](https://crawlbase.com/?utm_source=awesome-ai-agent-papers&utm_medium=sponsorship&utm_campaign=voltagent_2026q3&utm_content=readme_listing) is web data infrastructure trusted by 70,000+ developers. Its Crawling API, MCP server, and integrations give AI agents live access to any webpage — with JavaScript rendering, proxy rotation, and anti-bot protection. |
|
||||
| <a href="https://serpapi.com/?utm_source=voltagent&utm_campaign=md"><img alt="SerpApi" src="https://cdn.voltagent.dev/awesome-repo/serpapi/serpapi-logo.png" width="425"></a> | [SerpApi](https://serpapi.com/?utm_source=voltagent&utm_campaign=md) is a Web Search API for your AI apps. Available in Markdown and JSON for any integration. |
|
||||
|
||||
<br />
|
||||
|
||||
<a href="https://sponsors.voltagent.dev/#awesome-ai-agent-papers"><img src="https://img.shields.io/badge/📩_Become_a_Sponsor-Contact_Us-blue?style=for-the-badge&logoColor=white" alt="Become a Sponsor" /></a>
|
||||
|
||||
### Why this list exists
|
||||
|
||||
Hundreds of papers are published on arXiv every week, and a growing number of them touch on AI agents. We go through them all, filter the ones that are directly relevant to the AI agent ecosystem, and categorize them so you don't have to. This list only includes papers published from January 2026 onward.
|
||||
@@ -69,8 +61,6 @@ Hundreds of papers are published on arXiv every week, and a growing number of th
|
||||
### Table of Contents
|
||||
|
||||
- [Multi-Agent](#multi-agent) (53)
|
||||
- [Memory & RAG](#memory--rag) (58)
|
||||
- [Multi-Agent](#multi-agent) (54)
|
||||
- [Memory & RAG](#memory--rag) (57)
|
||||
- [Eval & Observability](#eval--observability) (80)
|
||||
- [Agent Tooling](#agent-tooling) (95)
|
||||
@@ -78,27 +68,6 @@ Hundreds of papers are published on arXiv every week, and a growing number of th
|
||||
|
||||
<br>
|
||||
|
||||
|
||||
<br/>
|
||||
|
||||
You ship products with AI, but every launch still dies quietly because nobody posts about it. [EveryFeed](https://everyfeed.ai/) plugs your AI assistant into a social workspace that drafts, schedules, and publishes across 35+ channels — no agency, no marketing hire.
|
||||
|
||||
<a href="https://everyfeed.ai/">
|
||||
<img src="https://cdn.voltagent.dev/awesome-repo/everyfeed-social.png" alt="everyfeed" /><br/>
|
||||
</a>
|
||||
|
||||
<br/>
|
||||
<br/>
|
||||
|
||||
Stop building from a blank page. [LaunchKit](https://launchkit.getdesign.md/) gives your AI coding assistant a complete, working product to start from — websites, startups, and web apps that are clickable on day one.
|
||||
|
||||
<a href="https://launchkit.getdesign.md/">
|
||||
<img src="https://cdn.voltagent.dev/awesome-repo/new-launchkit.png" alt="launchkit" /><br/>
|
||||
</a>
|
||||
|
||||
<br/>
|
||||
|
||||
|
||||
<details open id="multi-agent">
|
||||
<summary><h3 style="display:inline">Multi-Agent (54)</h3></summary>
|
||||
|
||||
@@ -108,10 +77,8 @@ Stop building from a blank page. [LaunchKit](https://launchkit.getdesign.md/) gi
|
||||
|---|:---:|
|
||||
| **[Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy](https://arxiv.org/pdf/2606.24177)** - Treats prompt engineering as an engineering discipline rather than an art, minimizing human time while expecting maximum output. Carries the smallest prompt footprint among cross-disciplinary autoresearch systems (18 roles, 230.6 KiB total), has run across 10+ research fields without modification, and the longest observed run went 30 days unattended. | <a href="https://arxiv.org/abs/2606.24177"><img src="https://img.shields.io/badge/arXiv-2606.24177-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation](https://arxiv.org/pdf/2606.05697)** - A persona-conditioned framework that predicts how a specific user would answer UI/UX evaluation questions and explains why in natural language. Trained via contrastive reflection fine-tuning and reflective prompt evolution, reaching human-level realism and generalizing to unseen questions and personas. | <a href="https://arxiv.org/abs/2606.05697"><img src="https://img.shields.io/badge/arXiv-2606.05697-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[OpenCLAW-P2P v6.0: Resilient Multi-Layer Persistence, Live Reference Verification, and Production-Scale Evaluation of Decentralized AI Peer Review](https://arxiv.org/pdf/2604.19792)** - Presents a decentralized AI peer-review platform where autonomous agents publish, score, verify references, and preserve research papers across a multi-layer storage and retrieval architecture. | <a href="https://arxiv.org/abs/2604.19792"><img src="https://img.shields.io/badge/arXiv-2604.19792-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing](https://arxiv.org/pdf/2602.17607)** - A multi-agent pipeline that reads a PDE problem description in plain text and writes, debugs, and validates a classical numerical solver end-to-end. Generates spectral and finite-difference code (no neural networks), scoring ~6 orders of magnitude below FNO and CodePDE baselines. | <a href="https://arxiv.org/abs/2602.17607"><img src="https://img.shields.io/badge/arXiv-2602.17607-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[Beyond Offline A/B Testing: Context-Aware Agent Simulation for Recommender System Evaluation](https://arxiv.org/abs/2604.09549)** - Evaluates recommender systems via agent-RS interactions. | <a href="https://arxiv.org/abs/2604.09549"><img src="https://img.shields.io/badge/arXiv-2602.06039-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[CityReal: Human-Aligned Urban Behavior and City Dynamics Simulation with Large-Scale LLM Agents](https://arxiv.org/pdf/2608.16897)** - Simulates urban behavior and city dynamics with intention-driven LLM agents that learn habits and preferences via textual adapters, aligning to real population statistics at scale. | <a href="https://arxiv.org/abs/2608.16897"><img src="https://img.shields.io/badge/arXiv-2608.16897-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery](https://arxiv.org/pdf/2604.01658)** - Introduces long-running multi-agent systems that self-evolve via shared persistent memory, asynchronous execution, and heartbeat-based interventions; 3–10× higher improvement rates than fixed evolutionary-search baselines on 10 math/algorithmic/systems tasks. | <a href="https://arxiv.org/abs/2604.01658"><img src="https://img.shields.io/badge/arXiv-2604.01658-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching](https://arxiv.org/pdf/2602.06039v1)** - Investigates dynamically rewiring agent-to-agent connections at each reasoning round via semantic matching instead of fixed communication topologies. | <a href="https://arxiv.org/abs/2602.06039v1"><img src="https://img.shields.io/badge/arXiv-2602.06039-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[RuleSmith: Multi-Agent LLMs for Automated Game Balancing](https://arxiv.org/pdf/2602.06232v1)** - Explores automated game balancing by combining multi-agent LLM self-play with Bayesian optimization on a civ-style game. | <a href="https://arxiv.org/abs/2602.06232v1"><img src="https://img.shields.io/badge/arXiv-2602.06232-b31b1b.svg" alt="arXiv" /></a> |
|
||||
@@ -171,14 +138,13 @@ Stop building from a blank page. [LaunchKit](https://launchkit.getdesign.md/) gi
|
||||
<br>
|
||||
|
||||
<details open id="memory--rag">
|
||||
<summary><h3 style="display:inline">Memory & RAG (57)</h3></summary>
|
||||
<summary><h3 style="display:inline">Memory & RAG (56)</h3></summary>
|
||||
|
||||
<br>
|
||||
|
||||
| Paper | arXiv ID |
|
||||
|---|:---:|
|
||||
| **[Corpus2Skill: Don't Retrieve, Navigate — Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG](https://arxiv.org/pdf/2604.14572)** - Compiles a corpus offline into a hierarchical tree of Agent Skills that the LLM agent navigates at query time, replacing retrieval with skill-tree traversal. | <a href="https://arxiv.org/abs/2604.14572"><img src="https://img.shields.io/badge/arXiv-2604.14572-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[Semantic Level of Detail for Knowledge Graphs: Discovering Abstraction Boundaries via Spectral Heat Diffusion](https://arxiv.org/pdf/2603.08965)** - Gives an agent a continuous zoom control over a knowledge graph, so it can move between broad and detailed views without hand-tuning a community-detection resolution parameter. Proves the abstraction levels stay consistent as it zooms and shows stable boundary detection on noisy graphs. | <a href="https://arxiv.org/abs/2603.08965"><img src="https://img.shields.io/badge/arXiv-2603.08965-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[BudgetMem: Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory](https://arxiv.org/pdf/2602.06025v1)** - Investigates routing agent memory queries to different processing tiers based on query difficulty to control the cost-accuracy trade-off at runtime. | <a href="https://arxiv.org/abs/2602.06025v1"><img src="https://img.shields.io/badge/arXiv-2602.06025-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[Learning to Share: Selective Memory for Efficient Parallel Agentic Systems](https://arxiv.org/pdf/2602.05965v1)** - Proposes a shared memory bank with a learned controller that decides what information is worth passing between parallel agent teams to reduce redundant work. | <a href="https://arxiv.org/abs/2602.05965v1"><img src="https://img.shields.io/badge/arXiv-2602.05965-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering](https://arxiv.org/pdf/2602.05728v1)** - Explores converting a corpus into atomic QA pairs offline to resolve multi-hop questions with just two LLM calls regardless of hop count. | <a href="https://arxiv.org/abs/2602.05728v1"><img src="https://img.shields.io/badge/arXiv-2602.05728-b31b1b.svg" alt="arXiv" /></a> |
|
||||
@@ -248,7 +214,6 @@ Stop building from a blank page. [LaunchKit](https://launchkit.getdesign.md/) gi
|
||||
| Paper | arXiv ID |
|
||||
|---|:---:|
|
||||
| **[PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting](https://arxiv.org/pdf/2606.08878)** - A 110-scenario benchmark testing whether LLMs can compose orchestration prompts that distribute context to sub-agents without information leakage. Across 10 topologies and 27 commercial models, GPT-5.5 leads with 62% pass rate while the average is 14.9%. | <a href="https://arxiv.org/abs/2606.08878"><img src="https://img.shields.io/badge/arXiv-2606.08878-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[RewardHarness: Self-Evolving Agentic Post-Training](https://arxiv.org/pdf/2605.08703)** - Evolves a library of scoring skills and tools from preference examples, then uses a frozen vision-language sub-agent to evaluate image edits and produce a reward for GRPO training. | <a href="https://arxiv.org/abs/2605.08703"><img src="https://img.shields.io/badge/arXiv-2605.08703-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[ClawBench: Evaluating Browser Agents on Live Production Websites with Submission-Interception](https://arxiv.org/abs/2604.08523)** - Benchmarks browser agents on 283 everyday tasks (V1 153 + V2 130) across 163 live production sites, with a Chrome-extension plus CDP layer that blocks only the final write request so agents can run end-to-end on real sites without real-world side effects. Two-stage scoring (interception + LLM judge); leaderboard at https://claw-bench.com. | <a href="https://arxiv.org/abs/2604.08523"><img src="https://img.shields.io/badge/arXiv-2604.08523-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs](https://arxiv.org/pdf/2505.20139)** - Benchmarks structured-output generation and cross-format conversion across 18 text and renderable formats, with syntax, structural, and visual evaluation checks. | <a href="https://arxiv.org/abs/2505.20139"><img src="https://img.shields.io/badge/arXiv-2505.20139-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[From Features to Actions: Explainability in Traditional and Agentic AI Systems](https://arxiv.org/pdf/2602.06841v1)** - Compares attribution-based explanations with trace-based diagnostics across static and agentic settings to study how explainability methods translate to multi-step agent trajectories. | <a href="https://arxiv.org/abs/2602.06841v1"><img src="https://img.shields.io/badge/arXiv-2602.06841-b31b1b.svg" alt="arXiv" /></a> |
|
||||
@@ -337,14 +302,12 @@ Stop building from a blank page. [LaunchKit](https://launchkit.getdesign.md/) gi
|
||||
<br>
|
||||
|
||||
<details id="agent-tooling">
|
||||
<summary><h3 style="display:inline">Agent Tooling (97)</h3></summary>
|
||||
<summary><h3 style="display:inline">Agent Tooling (96)</h3></summary>
|
||||
|
||||
<br>
|
||||
|
||||
| Paper | arXiv ID |
|
||||
|---|:---:|
|
||||
| **[SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation](https://arxiv.org/pdf/2607.08983)** - Replaces the human who keeps prodding a coding agent to write more tests with a contextual bandit that picks the next testing action from current coverage and class testability signals. Driving GEMINI-CLI, it reaches 32.3% higher line coverage and 30.9% higher branch coverage than the agent on its own, and it learns a different policy when the same setup drives CLAUDE CODE. | <a href="https://arxiv.org/abs/2607.08983"><img src="https://img.shields.io/badge/arXiv-2607.08983-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution](https://arxiv.org/pdf/2608.08311)** - Documents a coding-agent harness that can update its tools, prompts, context assembly, and core code through reviewed commits, with a 161-day live deployment. Reports frozen-snapshot results of 86.74% on Terminal-Bench 2.1 and 90.69% on OSWorld-Verified. | <a href="https://arxiv.org/abs/2608.08311"><img src="https://img.shields.io/badge/arXiv-2608.08311-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[On Effectiveness and Efficiency of Agentic Tool-calling and RL Training](https://arxiv.org/pdf/2606.00135)** - Find that current agentic tool-calling benchmarks like BFCL are quite brittle: system prompt, multi-turn template or even pure random seeds could have huge influence on the final performance. | <a href="https://arxiv.org/abs/2606.00135"><img src="https://img.shields.io/badge/arXiv-2602.06875-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging](https://arxiv.org/pdf/2602.06875v1)** - Proposes a multi-agent observe-analyze-repair loop that uses runtime traces to find and fix bugs in LLM-generated code. | <a href="https://arxiv.org/abs/2602.06875v1"><img src="https://img.shields.io/badge/arXiv-2602.06875-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[Generative Ontology: When Structured Knowledge Learns to Create](https://arxiv.org/pdf/2602.05636v1)** - Explores constraining LLM generation with executable schemas and multi-agent roles to produce structurally valid yet creative outputs. | <a href="https://arxiv.org/abs/2602.05636v1"><img src="https://img.shields.io/badge/arXiv-2602.05636-b31b1b.svg" alt="arXiv" /></a> |
|
||||
|
||||
Reference in New Issue
Block a user