REVIEW 13 cited by
AgentSquare: Automatic LLM Agent Search in Modular Design Space
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
Recent advancements in Large Language Models (LLMs) have led to a rapid growth of agentic systems capable of handling a wide range of complex tasks. However, current research largely relies on manual, task-specific design, limiting their adaptability to novel tasks. In this paper, we introduce a new research problem: Modularized LLM Agent Search (MoLAS). We propose a modular design space that abstracts existing LLM agent designs into four fundamental modules with uniform IO interface: Planning, Reasoning, Tool Use, and Memory. Building on this design space, we present a novel LLM agent search framework called AgentSquare, which introduces two core mechanisms, i.e., module evolution and recombination, to efficiently search for optimized LLM agents. To further accelerate the process, we design a performance predictor that uses in-context surrogate models to skip unpromising agent designs. Extensive experiments across six benchmarks, covering the diverse scenarios of web, embodied, tool use and game applications, show that AgentSquare substantially outperforms hand-crafted agents, achieving an average performance gain of 17.2% against best-known human designs. Moreover, AgentSquare can generate interpretable design insights, enabling a deeper understanding of agentic architecture and its impact on task performance. We believe that the modular design space and AgentSquare search framework offer a platform for fully exploiting the potential of prior successful designs and consolidating the collective efforts of research community. Code repo is available at https://github.com/tsinghua-fib-lab/AgentSquare.
Forward citations
Cited by 13 Pith papers
-
MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents
MobiBench reaches near-human offline evaluation fidelity for mobile GUI agents by accepting any valid action at each step, and enables modular attribution of performance to agent components.
-
AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery
AutoSOTA uses eight specialized agents to replicate and optimize models from recent AI papers, producing 105 new SOTA results in about five hours per paper on average.
-
Global Optimization and Inference-Time Region Grafting for Agentic Workflows
A training-free method that locally replaces failing regions of an offline-optimized agent workflow at inference time, improving average benchmark performance over prior workflow-optimization baselines.
-
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.
-
LOGOS: A Living Logic for AI Agent Teams That Evolve With Humans
LOGOS makes multi-agent self-evolution governable by compiling inputs into versioned Agent Packs and promoting only candidates that pass held-out evidence, root policy, and human authorization.
-
Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models
The monotonicity of token probabilities during initial decoding predicts chain-of-thought gains, enabling dynamic selection between CoT and direct answers.
-
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.
-
AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
AgentRecBench is a public text-based benchmark for LLM recommendation agents, but its headline claim of agent superiority is undercut by its own tables.
-
Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents
Division-of-Thoughts reduces LLM API cost and latency by about 84% and 66% on seven reasoning benchmarks via subtask decomposition and small/large model routing, with accuracy near cloud-only baselines.
-
Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation
Automatically adapted agent harnesses let capable SLMs recover most frontier-LLM accuracy on repetitive business tasks at a few percent of the inference cost.
-
EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-making
EvoCurr couples an LLM curriculum designer with an LLM code-generating solver, but its only reported success is 1 of 5 runs and no direct baseline is shown.
-
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.
-
AI Agent Behavioral Science
AI agents should be studied as behavioral entities shaped by context and interaction, not only as trained models.
Discussion (0). Continue with ORCID to comment.