REVIEW 16 cited by
EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms
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
read the original abstract
The rise of powerful large language models (LLMs) has spurred a new trend in building LLM-based autonomous agents for solving complex tasks, especially multi-agent systems. Despite the remarkable progress, we notice that existing works are heavily dependent on human-designed frameworks, which greatly limits the functional scope and scalability of agent systems. How to automatically extend the specialized agent to multi-agent systems to improve task-solving capability still remains a significant challenge. In this paper, we introduce EvoAgent, a generic method to automatically extend specialized agents to multi-agent systems via the evolutionary algorithm, thereby improving the effectiveness of LLM-based agents in solving tasks. Specifically, we consider the existing agent frameworks as the initial individual and then apply a series of evolutionary operators (e.g., mutation, crossover, selection, etc.) to generate multiple agents with diverse settings. Experimental results across various tasks show that EvoAgent can significantly enhance the task-solving capability of LLM-based agents, and can be generalized to any LLM-based agent framework to extend them into multi-agent systems. Resources are available at https://evo-agent.github.io/.
Forward citations
Cited by 16 Pith papers
-
Fantastic Adaptive Taxonomies and How to Use Them
AdaMAST induces a compact, evidence-grounded failure taxonomy from an agent's own traces and shows it improves agent-system search, runtime reflection, and trajectory selection over free-text and fixed-taxonomy baselines.
-
Step-Level Preference Learning for Generative Agents in Social Simulations
Step-level human preference data collected via SimPref, then SFT+DPO, improves long-horizon social-simulation behavior of open-weight LLM agents on held-out events.
-
Self-Modifying Lean Proof Agents with Verifier-Grounded Benchmark Coevolution
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.
-
AdsQA: Towards Advertisement Video Understanding
AdsQA adds an ad-video question-answering benchmark and ReAd-R, a GRPO-trained model that beats 7B baselines but not larger closed models.
-
EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation
EvoEmo evolves emotion-transition policies for buyer LLM agents and reports higher savings, success rates, and efficiency than vanilla or fixed-emotion baselines in simulated price negotiations.
-
RETAIL: Towards Real-world Travel Planning for Large Language Models
A new travel-planning benchmark and multi-agent system that still mostly fails, with the best system passing only 2.72% of test cases.
-
MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
An LLM-based framework that generates a tool-enabled, traceback-capable multi-agent system as a finite state machine from a task description, outperforming other automatic design methods on four benchmarks.
-
Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems
On three NIST crypto standards (AES, DSS, HMAC), Spec2RTL-Agent generates RTL via a multi-agent pipeline from pseudocode to Python to synthesizable C++, reporting 3/3 correct designs with about 4.3 human interventions...
-
G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
G-Memory stores past multi-agent teamwork in a three-tier graph and retrieves it to boost performance on five benchmarks.
-
Adaptive Graph Pruning for Multi-Agent Communication
AGP trains a graph neural network to jointly decide which agents to keep and how strongly they should communicate, and reports state-of-the-art average accuracy across six LLM benchmarks with large token savings.
-
Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration
MAEL gives each agent in a multi-agent LLM system an experience pool and retrieves high-reward past steps to guide new task solving.
-
Self-Evolving Coding Agents
A systematic survey that defines self-evolving coding agents, organizes systems into a five-category object-centered taxonomy, and analyzes when and on what evidence these agents evolve.
-
ASARL: Autonomous Social-Aware Relevance Learning for QQ Search
An agent-loop data-curation pipeline with social-aware chain-of-thought, preference, and distillation training improves QQ group/channel search relevance in offline and online evaluation.
-
Representing Prompting Patterns with PDL: Compliance Agent Case Study
A PDL-based compliance agent outperformed a canned ReAct agent by up to 4x, mainly by cutting tool call failures.
-
Agent Exchange: Shaping the Future of AI Agent Economics
AEX is a proposed auction platform for AI agent marketplaces that adaptively switches between competitive bidding and direct assignment and is validated only by a synthetic proof-of-concept simulation.
-
Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings
DEEVO evolves better LLM prompts by debating outputs and selecting survivors with Elo ratings, without requiring labeled data or a hand-written fitness function.
Discussion (0). Sign in to comment.