Pith. sign in

REVIEW 32 cited by

AutoAgents: A Framework for Automatic Agent Generation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2309.17288 v3 pith:TYT535XT submitted 2023-09-29 cs.AI

classification cs.AI
keywords agentstasksautoagentsdifferentmulti-agentframeworkmultipleexisting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) have enabled remarkable advances in automated task-solving with multi-agent systems. However, most existing LLM-based multi-agent approaches rely on predefined agents to handle simple tasks, limiting the adaptability of multi-agent collaboration to different scenarios. Therefore, we introduce AutoAgents, an innovative framework that adaptively generates and coordinates multiple specialized agents to build an AI team according to different tasks. Specifically, AutoAgents couples the relationship between tasks and roles by dynamically generating multiple required agents based on task content and planning solutions for the current task based on the generated expert agents. Multiple specialized agents collaborate with each other to efficiently accomplish tasks. Concurrently, an observer role is incorporated into the framework to reflect on the designated plans and agents' responses and improve upon them. Our experiments on various benchmarks demonstrate that AutoAgents generates more coherent and accurate solutions than the existing multi-agent methods. This underscores the significance of assigning different roles to different tasks and of team cooperation, offering new perspectives for tackling complex tasks. The repository of this project is available at https://github.com/Link-AGI/AutoAgents.

Discussion (0). Sign in to comment.

Forward citations

Cited by 32 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. OctoT2I: A Self-Evolving Agentic Text-to-Image Router

    cs.AI 2026-06 unverdicted novelty 7.0 of 10

    OctoT2I uses a no-supervision PSEL loop to discover model capability frontiers and route T2I tasks, reaching 0.96 GenEval score with 90.3% speedup over Flow-GRPO.

  2. Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights

    cs.CL 2026-05 unverdicted novelty 7.0 of 10

    TFlow enables multi-agent LLMs to collaborate via transient low-rank LoRA perturbations derived from sender activations, yielding up to 8.5 accuracy gains and 83% token reduction versus text-based baselines on Qwen3-4...

  3. From Static Analysis to Audience Dissemination: A Training-Free Multimodal Controversy Detection Multi-Agent Framework

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    AuDisAgent reformulates multimodal controversy detection as a dynamic audience dissemination process using screening, panel discussion, and arbitration agents, plus comment bootstrapping, and reports outperforming pri...

  4. Incisor: Ex Ante Cloud Instance Selection for HPC Jobs

    cs.DC 2026-04 unverdicted novelty 7.0 of 10

    Incisor uses program analysis and frontier LLMs to select working AWS EC2 instances ex ante for 100% of first-time HPC runs of C/C++/Fortran and Python codes, cutting runtime 54% and costs 44% versus an expert-constra...

  5. Automated Design of Agentic Systems

    cs.AI 2024-08 conditional novelty 7.0 of 10

    Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across...

  6. Harnessing the Wisdom of LLM Crowds through Complementarity-Driven Iterative Collaboration

    cs.AI 2026-07 reject novelty 6.0 of 10

    WILC coordinates heterogeneous LLMs in a relay, selecting each successor model with a contextual bandit to fix the previous answer's diagnosed bottleneck, and reports large accuracy gains plus a 7× cost advantage over...

  7. Agent Security Needs Redefinition through a Holistic Framework

    cs.CR 2026-07 conditional novelty 6.0 of 10

    Agent security should be redefined around four contextual authorization properties instead of the content of the action performed.

  8. Self-Modifying Lean Proof Agents with Verifier-Grounded Benchmark Coevolution

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A verifier-grounded self-evolving Lean proof agent with a champion-driven, self-hardening benchmark reached 45.1% held-out miniF2F solve rate versus 32.0% for a fixed-benchmark baseline.

  9. Knowledge-Centric Agents for Workflow Generation in ComfyUI

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A knowledge-centric pipeline distills strategies and pseudo-codes from real workflows, fine-tunes a language model on those levels, and reconstructs executable ComfyUI graphs from task descriptions.

  10. Verilog-Evolve: Feedback-Driven and Skill-Evolving Verilog Generation

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    Verilog-Evolve uses executable feedback from simulation, synthesis, timing, and GEMM metrics to refine LLM-generated Verilog and evolves skills across tasks, improving functional success and downstream hardware qualit...

  11. Effective Strategies for Asynchronous Software Engineering Agents

    cs.CL 2026-03 conditional novelty 6.0 of 10

    CAID, a manager-driven multi-agent system using git worktrees, commits, and merges, improves long-horizon SWE success by roughly 14–27 absolute points over single-agent baselines.

  12. ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation

    cs.AI 2026-02 conditional novelty 6.0 of 10

    An LLM agent that can call a reconfiguration tool to update its sub-goals, toolbox, strategy, and context outperforms static-config agents across FRAMES, xbench, GAIA, and SWE-bench Lite.

  13. Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models

    cs.CL 2025-10 unverdicted novelty 6.0 of 10

    GTD generates task-adaptive, sparse communication topologies for multi-LLM agents via guided iterative graph diffusion steered by a proxy model predicting accuracy, utility, and cost.

  14. Establishing Best Practices for Building Rigorous Agentic Benchmarks

    cs.AI 2025-07 conditional novelty 6.0 of 10

    Agentic benchmarks frequently mis-grade agents, and the new ABC checklist helps identify and correct such errors in ten popular benchmarks.

  15. Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning

    cs.AI 2025-07 conditional novelty 6.0 of 10

    Math reasoning gains in LLMs rarely transfer to general domains; RL tuning generalizes while SFT causes forgetting and representation drift.

  16. Doc2Agent: Scalable Generation of Tool-Using Agents from API Documentation

    cs.CL 2025-06 reject novelty 6.0 of 10

    Doc2Agent automatically converts unstructured REST API documentation into validated, Python-based tools for AI agents, reporting a 55% relative WebArena improvement over direct API calling.

  17. A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration

    cs.CL 2023-10 conditional novelty 6.0 of 10

    DyLAN automatically selects and dynamically organizes LLM agents for collaboration, outperforming fixed-agent baselines on code generation, reasoning, and decision tasks with up to 25% accuracy gains on some MMLU subjects.

  18. Understanding How Enterprises Adopt the Model Context Protocol for LLM-Driven Software Engineering

    cs.SE 2026-06 unverdicted novelty 5.0 of 10

    Interviews with 20 practitioners show MCP supports cross-system collaboration and task decoupling in LLM workflows but is limited by ecosystem fragmentation, coordination issues, and state management problems.

  19. ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy

    cs.MA 2026-05 unverdicted novelty 5.0 of 10

    ATOM uses a nucleus-electron hierarchy and task-driven RL to generate budget-controllable multi-agent collaboration graphs for LLMs, claiming SOTA performance with up to 30% better token efficiency on six benchmarks.

  20. Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game

    cs.MA 2026-04 unverdicted novelty 5.0 of 10

    Gated escalation and partitioned states enable more efficient multi-agent collaboration in Minecraft by making communication selective rather than automatic.

  21. MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL

    cs.CL 2025-11 unverdicted novelty 5.0 of 10

    MARS-SQL trains a multi-agent RL system with ReAct-style interaction and generative validation to produce SQL queries, reaching 77.84% execution accuracy on BIRD dev and 89.75% on Spider test.

  22. Semantic-Aware Logical Reasoning via a Semiotic Framework

    cs.AI 2025-09 conditional novelty 5.0 of 10

    LogicAgent uses a semiotic-square-guided approach to enhance logical reasoning in LLMs on the new RepublicQA benchmark and others, reporting average gains of 6.25% and 7.05% respectively.

  23. Agentic Reasoning for Large Language Models

    cs.AI 2026-01 unverdicted novelty 4.0 of 10

    The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applicat...

  24. Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges

    cs.AI 2025-10 unverdicted novelty 4.0 of 10

    A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.

  25. From Script to Stage: Automating Experimental Design for Social Simulations with LLMs

    cs.HC 2025-10 unverdicted novelty 4.0 of 10

    FSTS automates multi-agent social experiment design via LLM script generation across three phases, with tests indicating reproduction of real-world outcomes.

  26. SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models

    cs.AI 2025-07 reject novelty 4.0 of 10

    The paper proposes a multi-agent loop (instructor, follower, feedback) to auto-generate human-readable system prompts, claiming good benchmark performance and readability, but the supporting experiments are not reprod...

  27. Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary

    cs.AI 2025-06 unverdicted novelty 4.0 of 10

    Agents should invoke external tools only when epistemically necessary, per the introduced Theory of Agent framework that frames tool use as a decision under uncertainty.

  28. InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction

    cs.AI 2025-05 unverdicted novelty 4.0 of 10

    InfantAgent-Next integrates tool-based and vision agents in a modular architecture and reports 7.27% accuracy on OSWorld, exceeding Claude-Computer-Use while also testing on GAIA and SWE-Bench.

  29. Large Language Model based Multi-Agents: A Survey of Progress and Challenges

    cs.CL 2024-01 unverdicted novelty 4.0 of 10

    The paper surveys LLM-based multi-agent systems, covering simulated domains, agent profiling and communication, mechanisms for capacity growth, and common benchmarks.

  30. LightAgent: Production-level Open-source Agentic AI Framework

    cs.AI 2025-09 reject novelty 3.0 of 10

    A new open-source framework combines existing agent techniques in a lightweight package, but the paper offers no benchmarks to support its production-level claims.

  31. A Survey of Reinforcement Learning for Large Reasoning Models

    cs.CL 2025-09 accept novelty 3.0 of 10

    A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.

  32. Resource Consumption Threats in Large Language Models

    cs.CR 2026-03 unverdicted novelty 2.0 of 10

    A systematic review of resource consumption threats in LLMs that organizes the problem along the full pipeline from threat induction to mitigation.

Pith tools