REVIEW 13 cited by
Language Agents as Optimizable Graphs
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
Signed reviews
read the original abstract
Various human-designed prompt engineering techniques have been proposed to improve problem solvers based on Large Language Models (LLMs), yielding many disparate code bases. We unify these approaches by describing LLM-based agents as computational graphs. The nodes implement functions to process multimodal data or query LLMs, and the edges describe the information flow between operations. Graphs can be recursively combined into larger composite graphs representing hierarchies of inter-agent collaboration (where edges connect operations of different agents). Our novel automatic graph optimizers (1) refine node-level LLM prompts (node optimization) and (2) improve agent orchestration by changing graph connectivity (edge optimization). Experiments demonstrate that our framework can be used to efficiently develop, integrate, and automatically improve various LLM agents. The code can be found at https://github.com/metauto-ai/gptswarm.
Forward citations
Cited by 13 Pith papers
-
A Workflow-Aware Serving Layer for Agentic Applications
A workflow-aware serving layer compiles per-node model-verifier-backend plans with an ILP and adapts only uncommitted work via pre-solved pressure rungs and residual re-solves.
-
Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges
Per-bias selection of a cross-family LLM auditor lifts biased-judgment accuracy from 0.805/0.824 baselines to 0.884.
-
The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
Reasoning messages between heterogeneous VLMs can be routed through the image-token span: a distilled universal codec plus affine alignment transmits latent traces across model families, cutting wall-clock time in sma...
-
ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems
A perturbation-based framework measures how value opinions propagate through multi-agent LLM systems, revealing that susceptibility varies by value, model, and topology.
-
Latent Collaboration in Multi-Agent Systems
Replacing text inter-agent dialogue with direct transfer of hidden-state (KV-cache) representations cuts output tokens by ~70-84%, speeds inference ~4x, and keeps multi-agent accuracy roughly on par or slightly better.
-
Graph World Model
The Graph World Model uses action nodes and graph message passing to unify multimodal and graph-structured tasks, but its 'outperforms or matches' claim is contradicted by results on Goodreads.
-
Bridging Literature and the Universe Via A Multi-Agent Large Language Model System
A multi-agent large language model system extracts cosmological simulation parameters from published papers and generates valid MP-GADGET configuration files, achieving 98.7% micro-F1 on a new 41-simulation benchmark.
-
What makes prompts a graph: necessary and sufficient conditions for prompt graph engineering
The paper defines prompt graph engineering via four necessary and sufficient conditions (explicit structure, structure/content separation, executable semantics, first-class artifact) and an inclusion/exclusion test th...
-
Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scale
FGO is a divide-and-conquer framework that runs LLM-based agent optimization on dataset subsets and recursively merges the optimized prompts or tool sets into a final agent system.
-
Orchestrator: Active Inference for Multi-Agent Systems in Long-Horizon Tasks
Orchestrator, an active-inference-inspired feedback system for LLM multi-agent teams, substantially raises maze-solving success rates on medium-difficulty mazes but not consistently on hard mazes.
-
Flow: Modularized Agentic Workflow Automation
Flow represents a task as a dependency graph of subtasks and lets LLM agents redraw that graph during execution, reporting better success rates than three baselines on three coding tasks.
-
Memory-Augmented Agent Training for Business Document Understanding
Matrix iteratively refines an LLM agent's memory from training trajectories and outperforms prompting and vanilla agent baselines on private UBL invoice transport-reference extraction, though gains on the released ano...
-
REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization
REVOLVE adds a response-evolution similarity term to TextGrad's textual gradients and reports gains on several LLM optimization benchmarks, though its 'second-order' derivation is flawed.
Discussion (0). Continue with ORCID to comment.