Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 promptadmin
|
1a39cc88da | ||
|
promptadmin
|
4c4cd0a94a |
Vendored
+4
-4
@@ -2,9 +2,9 @@
|
||||
title: "Link Check"
|
||||
task: ""
|
||||
lineage_type: import
|
||||
upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/117f624b/.github/workflows/link-check.yml
|
||||
upstream_sha: 117f624b
|
||||
imported_at: 2026-07-25
|
||||
upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/539ec1dc/.github/workflows/link-check.yml
|
||||
upstream_sha: 539ec1dc
|
||||
imported_at: 2026-06-26
|
||||
prompt_class: unknown
|
||||
upstream_changes: accepted
|
||||
author: upstream
|
||||
@@ -40,7 +40,7 @@ jobs:
|
||||
args: >-
|
||||
--verbose
|
||||
--no-progress
|
||||
--accept 200,204,301,302,308,403,429
|
||||
--accept 200,204,301,302,403,429
|
||||
--exclude-path node_modules
|
||||
--exclude "star-history.com"
|
||||
--exclude "shields.io"
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
title: "Changelog"
|
||||
task: ""
|
||||
lineage_type: import
|
||||
upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/539ec1dc/CHANGELOG.md
|
||||
upstream_sha: 539ec1dc
|
||||
imported_at: 2026-06-26
|
||||
upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/3049e99c/CHANGELOG.md
|
||||
upstream_sha: 3049e99c
|
||||
imported_at: 2026-07-22
|
||||
prompt_class: catalogue
|
||||
upstream_changes: accepted
|
||||
author: upstream
|
||||
@@ -23,6 +23,7 @@ All notable changes to this list will be documented here.
|
||||
|
||||
| Date | Change |
|
||||
|---|---|
|
||||
| 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/117f624b/README.md
|
||||
upstream_sha: 117f624b
|
||||
imported_at: 2026-07-25
|
||||
upstream_source: https://github.com/ARUNAGIRINATHAN-K/awesome-ai-agents-2026/blob/3049e99c/README.md
|
||||
upstream_sha: 3049e99c
|
||||
imported_at: 2026-07-22
|
||||
prompt_class: catalogue
|
||||
upstream_changes: accepted
|
||||
author: upstream
|
||||
@@ -116,7 +116,6 @@ validated: false
|
||||
- [Cursor](https://cursor.com) `🚀` `[TypeScript]` `[IDE]` - AI-native IDE with parallel Cloud Agents and 100K+ enterprise users.
|
||||
- [Devika](https://github.com/stitionai/devika) `🌱` `[Python]` `[Docker]` - Open-source AI software engineer that understands high-level instructions and writes full-featured code autonomously.
|
||||
- [Devin](https://devin.ai) `🚀` `[Cloud]` `[GitHub]` - Fully autonomous AI software engineer showing 8-12x efficiency gains in production (Nubank case study), cloud sandbox with persistent state, GitHub integration, and enterprise adoption growing 40% MoM.
|
||||
- [fractal](https://github.com/plasma-ai/fractal) `🌱` `[Python]` `[Multi-Agent]` - Orchestrates Claude Code, Codex, and other agents in per-node Git worktrees with recursive delegation and a live TUI.
|
||||
- [gemini-cli](https://github.com/google-gemini/gemini-cli) `🌱` `[Go]` `[CLI]` - Open-source CLI agent bringing Gemini AI directly into your terminal.
|
||||
- [GitHub Copilot](https://github.com/features/copilot) `🌱` `[TypeScript]` `[VS Code]` - Agent Mode in VS Code with Copilot Workspace for issue-to-PR workflows across Claude, GPT, and Gemini.
|
||||
- [Goose](https://github.com/aaif-goose/goose) `🌱` `[Rust]` `[CLI]` - Extensible open-source CLI agent that installs, executes, edits, and tests with any LLM.
|
||||
@@ -298,7 +297,6 @@ Sandboxes, web scrapers, browser automation, and networking layers that agents d
|
||||
- [Braintrust](https://www.braintrust.dev) `🌱` `[TypeScript]` `[Evaluation]` - Eval-driven development platform with experiment tracking and prompt optimization for agent quality.
|
||||
- [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.
|
||||
- [Guardrails AI](https://github.com/guardrails-ai/guardrails) `🌱` `[Python]` `[Multi-Agent]` - Adds structural, type, and quality guarantees to LLM outputs for reliable agent responses.
|
||||
- [Helicone](https://github.com/Helicone/helicone) `🌱` `[TypeScript]` `[Observability]` - Open-source LLM observability with one-line integration for cost tracking and prompt analytics.
|
||||
- [Lakera Guard](https://www.lakera.ai) `🌱` `[Cloud]` `[Security]` - Real-time protection against prompt injection, data leakage, and toxicity in agent interactions.
|
||||
@@ -315,7 +313,6 @@ Sandboxes, web scrapers, browser automation, and networking layers that agents d
|
||||
- [Rebuff](https://github.com/protectai/rebuff) `🌱` `[Python]` `[Security]` - Self-hardening prompt injection detection system for securing agent inputs against adversarial attacks.
|
||||
- [Agent Learning Kit](https://github.com/future-agi/agent-learning-kit) `🌱` `[Python]` `[Evaluation]` - LLM evaluation framework with 50+ metrics, LLM-as-Judge, and guardrail scanners (jailbreak, PII, injection).
|
||||
- [Shipmoor](https://shipmoor.dev) `🔬` `[Python]` `[Testing]` - Local, deterministic verification layer for AI agent code: scans, test evidence, and a binding merge verdict without uploading source.
|
||||
- [SourceryKit](https://github.com/ProvablyAI/sourcerykit) `🔬` `[Python]` `[Security]` - Verifies an agent's outbound requests and MCP handoffs against a source of truth using zero-knowledge proofs, logging each call and blocking anything off the trusted-endpoint allow-list.
|
||||
- [ai-evaluation](https://github.com/future-agi/ai-evaluation) `🌱` `[Python]` `[Evaluation]` - LLM evaluation framework with 50+ metrics, LLM-as-Judge, and guardrail scanners (jailbreak, PII, injection).
|
||||
- [Future AGI](https://github.com/future-agi/future-agi) `🌱` `[Python]` `[Self-Hosted]` - Self-hostable end-to-end agent engineering platform with tracing, evals, guardrails, and gateway.
|
||||
|
||||
@@ -383,8 +380,6 @@ Curated list of vertical agent solutions for finance, healthcare, legal, manufac
|
||||
- [JPMorgan AlphaBlue](https://www.jpmorgan.com/global) `🚀` `[Cloud]` `[Multi-Agent]` - Trading and market analysis agent integrations for institutional workflows.
|
||||
- [Goldman Sachs Marquee AI](https://www.goldmansachs.com) `🚀` `[Cloud]` `[Multi-Agent]` - Market data and analytics agents built on Marquee platform.
|
||||
- [Morgan Stanley AdvisorBot](https://www.morganstanley.com) `🚀` `[Cloud]` `[CLI]` - Financial advisory assistant for advisors and retail clients.
|
||||
- [AgentPump](https://agentpump.app) `🔬` `[Cloud]` `[CLI]` - Runs autonomous on-chain memecoin trading agents on Solana that trade on a schedule, operable from the terminal via the @agentpump/cli.
|
||||
|
||||
|
||||
### Healthcare
|
||||
|
||||
@@ -537,7 +532,7 @@ Tools for generating images, video, music, audio, and 3D assets using AI models.
|
||||
- [LTX Video](https://github.com/Lightricks/LTX-Video) `🌱` `[Python]` `[IDE]` - Commercially safe open-source video generation model trained on fully licensed data.
|
||||
- [Luma Dream Machine](https://lumalabs.ai/app) `🌱` `[Cloud]` `[IDE]` - Creates physics-accurate 4K HDR video scenes with 3D-style output for cinematic quality.
|
||||
- [Pika 2.5](https://pika.art/login) `🌱` `[Cloud]` `[IDE]` - Beginner-friendly video generation tool with fast turnaround and intuitive editing controls.
|
||||
- [Runway Gen-4.5](https://runway.com) `🌱` `[Cloud]` `[IDE]` - Professional video generation with Motion Brush and the highest benchmark scores for visual quality.
|
||||
- [Runway Gen-4.5](https://runwayml.com) `🌱` `[Cloud]` `[IDE]` - Professional video generation with Motion Brush and the highest benchmark scores for visual quality.
|
||||
- [Seedance 2.0](https://seed.bytedance.com/en/seedance) `🌱` `[Cloud]` `[IDE]` - Quad-modal input video generator with built-in lip-sync and 2K resolution output.
|
||||
- [Sora 2](https://sora.com) `🚀` `[Cloud]` `[OpenAI]` - Generates 25-second cinematic video clips with strong narrative coherence from text prompts by OpenAI.
|
||||
- [Wan 2.1](https://github.com/Wan-Video/Wan2.1) `🌱` `[Python]` `[IDE]` - Open-source self-hosted video generation model with unlimited length and no per-video costs.
|
||||
@@ -597,7 +592,6 @@ AI agents that automate customer support, CRM workflows, sales outreach, and tic
|
||||
- [Clay](https://www.clay.com) `🌱` `[Cloud]` `[IDE]` - Enriches leads from 70+ data providers and generates hyper-personalized outreach at scale.
|
||||
- [Instantly](https://instantly.ai) `🌱` `[Cloud]` `[Multi-Agent]` - Generates AI cold emails with smart sender rotation and built-in domain warmup for deliverability.
|
||||
- [Lavender](https://lavender.ai/) `🌱` `[Cloud]` `[Multi-Agent]` - Coaches email writing in real-time with AI response scoring and recipient intelligence.
|
||||
- [OutreachAgent](https://outreachagent.dev/for-agents) `🔬` `[Cloud]` `[Event-Driven]` - Runs reply-aware outbound email workflows with webhooks, sender pacing, approvals, and deliverability guardrails.
|
||||
- [Overloop CLI](https://overloop.com) `🌱` `[Cloud]` `[CLI]` - AI outbound CLI agent that sources 450M+ contacts and runs email plus LinkedIn campaigns with JSON output.
|
||||
|
||||
## Voice Agent Platforms
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
title: "Awesome AI Agent Papers"
|
||||
task: ""
|
||||
lineage_type: import
|
||||
upstream_source: https://github.com/VoltAgent/awesome-ai-agent-papers/blob/29037d57/README.md
|
||||
upstream_sha: 29037d57
|
||||
imported_at: 2026-08-17
|
||||
upstream_source: https://github.com/VoltAgent/awesome-ai-agent-papers/blob/aa50c0c3/README.md
|
||||
upstream_sha: aa50c0c3
|
||||
imported_at: 2026-07-03
|
||||
prompt_class: catalogue
|
||||
upstream_changes: accepted
|
||||
author: upstream
|
||||
@@ -31,7 +31,7 @@ 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" />
|
||||
@@ -61,8 +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)
|
||||
@@ -71,15 +69,13 @@ Hundreds of papers are published on arXiv every week, and a growing number of th
|
||||
<br>
|
||||
|
||||
<details open id="multi-agent">
|
||||
<summary><h3 style="display:inline">Multi-Agent (54)</h3></summary>
|
||||
<summary><h3 style="display:inline">Multi-Agent (53)</h3></summary>
|
||||
|
||||
<br>
|
||||
|
||||
| Paper | arXiv ID |
|
||||
|---|:---:|
|
||||
| **[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> |
|
||||
| **[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> |
|
||||
@@ -141,14 +137,13 @@ Hundreds of papers are published on arXiv every week, and a growing number of th
|
||||
<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> |
|
||||
@@ -211,16 +206,14 @@ Hundreds of papers are published on arXiv every week, and a growing number of th
|
||||
<br>
|
||||
|
||||
<details id="eval--observability">
|
||||
<summary><h3 style="display:inline">Eval & Observability (81)</h3></summary>
|
||||
<summary><h3 style="display:inline">Eval & Observability (80)</h3></summary>
|
||||
|
||||
<br>
|
||||
|
||||
| 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> |
|
||||
| **[Agentic Uncertainty Reveals Agentic Overconfidence](https://arxiv.org/pdf/2602.06948v1)** - Investigates whether agents can accurately predict their own success rates in agentic tasks. | <a href="https://arxiv.org/abs/2602.06948v1"><img src="https://img.shields.io/badge/arXiv-2602.06948-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents](https://arxiv.org/pdf/2602.06855v1)** - Introduces 20 research tasks from real ML papers covering idea generation, experiments, and refinement for benchmarking science agents. | <a href="https://arxiv.org/abs/2602.06855v1"><img src="https://img.shields.io/badge/arXiv-2602.06855-b31b1b.svg" alt="arXiv" /></a> |
|
||||
@@ -265,7 +258,6 @@ Hundreds of papers are published on arXiv every week, and a growing number of th
|
||||
| **[The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution](https://arxiv.org/pdf/2601.15075v2)** - Proposes a hierarchical framework for general agentic attribution that identifies internal factors driving agent actions through temporal likelihood dynamics and perturbation-based analysis. | <a href="http://arxiv.org/abs/2601.15075v2"><img src="https://img.shields.io/badge/arXiv-2601.15075-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering](https://arxiv.org/pdf/2601.14470v1)** - Analyzes token consumption patterns across software development lifecycle stages in a multi-agent system to identify where tokens are consumed and which stages drive cost. | <a href="http://arxiv.org/abs/2601.14470v1"><img src="https://img.shields.io/badge/arXiv-2601.14470-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[APEX-Agents](https://arxiv.org/pdf/2601.14242v2)** - Introduces a benchmark of 480 long-horizon, cross-application productivity tasks created by investment banking analysts, consultants, and lawyers for evaluating AI agent capabilities in realistic work environments. | <a href="http://arxiv.org/abs/2601.14242v2"><img src="https://img.shields.io/badge/arXiv-2601.14242-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[DRIFT: Detecting Representational Inconsistencies for Factual Truthfulness](https://arxiv.org/pdf/2601.14210)** - Lightweight probes (3M-37M params) trained on middle-layer hidden states catch factually wrong generations before they reach the user, at less than 0.1% overhead. Up to 13 AUROC points above final-layer baselines, and the probes transfer across datasets without retraining. | <a href="https://arxiv.org/abs/2601.14210"><img src="https://img.shields.io/badge/arXiv-2601.14210-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[CooperBench: Why Coding Agents Cannot be Your Teammates Yet](https://arxiv.org/pdf/2601.13295v2)** - Introduces a benchmark of 600+ collaborative coding tasks to evaluate whether coding agents can coordinate as effective teammates under various coordination structures. | <a href="http://arxiv.org/abs/2601.13295v2"><img src="https://img.shields.io/badge/arXiv-2601.13295-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[Insider Knowledge: How Much Can RAG Systems Gain from Evaluation Secrets?](https://arxiv.org/pdf/2601.13227v1)** - Investigates how RAG systems can game nugget-based LLM judge evaluations through metric overfitting, demonstrating near-perfect scores when evaluation elements are leaked or predictable. | <a href="http://arxiv.org/abs/2601.13227v1"><img src="https://img.shields.io/badge/arXiv-2601.13227-b31b1b.svg" alt="arXiv" /></a> |
|
||||
| **[Replayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM Agents](https://arxiv.org/pdf/2601.15322v1)** - Introduces the Determinism-Faithfulness Assurance Harness for measuring trajectory determinism and evidence-conditioned faithfulness in tool-using LLM agents across 74 configurations and 12 models. | <a href="http://arxiv.org/abs/2601.15322v1"><img src="https://img.shields.io/badge/arXiv-2601.15322-b31b1b.svg" alt="arXiv" /></a> |
|
||||
@@ -307,14 +299,12 @@ Hundreds of papers are published on arXiv every week, and a growing number of th
|
||||
<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