Compare commits
4
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 promptadmin
|
2c5aee53f3 | ||
|
promptadmin
|
dde2afd783 | ||
|
promptadmin
|
8fd789e068 | ||
|
promptadmin
|
ea6455f9b7 |
@@ -2,9 +2,9 @@
|
||||
title: "Awesome AI Agent Papers"
|
||||
task: ""
|
||||
lineage_type: import
|
||||
upstream_source: https://github.com/VoltAgent/awesome-ai-agent-papers/blob/c8502b6a/README.md
|
||||
upstream_sha: c8502b6a
|
||||
imported_at: 2026-08-08
|
||||
upstream_source: https://github.com/VoltAgent/awesome-ai-agent-papers/blob/b52acd72/README.md
|
||||
upstream_sha: b52acd72
|
||||
imported_at: 2026-09-02
|
||||
prompt_class: catalogue
|
||||
upstream_changes: accepted
|
||||
author: upstream
|
||||
@@ -31,11 +31,8 @@ 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>
|
||||
@@ -54,6 +51,16 @@ 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. |
|
||||
|
||||
<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.
|
||||
@@ -61,6 +68,8 @@ 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)
|
||||
@@ -68,6 +77,27 @@ 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>
|
||||
|
||||
@@ -77,8 +107,10 @@ Hundreds of papers are published on arXiv every week, and a growing number of th
|
||||
|---|:---:|
|
||||
| **[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> |
|
||||
@@ -138,13 +170,14 @@ 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 (56)</h3></summary>
|
||||
<summary><h3 style="display:inline">Memory & RAG (57)</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> |
|
||||
@@ -214,6 +247,7 @@ Hundreds of papers are published on arXiv every week, and a growing number of th
|
||||
| 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> |
|
||||
@@ -302,12 +336,14 @@ 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 (96)</h3></summary>
|
||||
<summary><h3 style="display:inline">Agent Tooling (97)</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