Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems

• URL: http://arxiv.org/abs/2609.02264v1
• Date: Wed, 02 Sep 2026 08:10:22 GMT
• Title: Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems
• Abstract summary: We develop a query-independent 16-entry codebook that ranks the top decoded candidates in a single batched forward pass.<n>With no iterative search and no message passing at test time, Codebook Agent is the most accurate method on all six benchmarks.
• Score: 67.04448659688579
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adapting the communication topology of an LLM multi-agent system to each query improves both accuracy and efficiency, yet current designers treat this as conditional graph generation: a variational, autoregressive, or diffusion decoder searches the $N \times N$ adjacency space, and a graph-network proxy trained on utility and a structural cost such as edge count ranks the sampled candidates. We argue that this formulation is misaligned with the problem. Empirically, topologies that survive a reward filter collapse to about six distinct graphs even when the codebook capacity grows from 8 to 64; edge count is negatively correlated with measured token consumption (Pearson $r \approx -0.4$), so sparsifying the graph makes inference more expensive; and a message-passing scorer over agent-profile nodes is adjacency-invariant whenever agents share a profile---the default configuration of published benchmarks---so it cannot rank candidates at all in that regime. These three facts motivate Codebook Agent: a vector-quantized autoencoder compresses successful topologies into a query-independent 16-entry codebook; a reward-weighted MLP maps the query embedding to a distribution over codes; and an MLP proxy that reads the flattened adjacency, regressed on measured utility and per-task normalized token cost, reranks the top decoded candidates in a single batched forward pass. With no iterative search and no message passing at test time, Codebook Agent is the most accurate method on all six benchmarks we compare (84.6 average against 83.0 for the strongest prior designer), emits a topology in 2.4 ms, and uses 21.9--33.2% fewer LLM tokens.

Related papers

• Inference-Time Graph Engineering for Multi-Agent LLM Workflows [51.56038180639833]
  We introduce ReActNet, a training-free framework that compiles a query and a set of role-specialized agents into a sequence of directed communication graphs.<n>We show that ReActNet consistently improves over fixed-topology and learned-topology baselines while maintaining competitive inference cost.
  arXiv  Detail & Related papers  (2026-09-04T23:32:11Z)
• MARS: Multi-Specialist LLM Relay System for Competitive Programming [3.8421682531018564]
  MARS (Multi-Agent Relay of Specialized LLMs) is a prompt-only framework in which each agent is a topic specialist.<n>A starter writes an initial C++17 solution, and each subsequent turn runs the candidate against public examples in a sandbox.<n>A single infrastructure-fixer pass normalizes boilerplate at the end.
  arXiv  Detail & Related papers  (2026-08-24T23:51:02Z)
• SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant [79.24089819400126]
  Subsampled TurboQuant (SSTQ) is a framework that combines overcomplete equal-width tight frames, coordinate subsampling, and privacy-aware quantization.<n>SSTQ achieves mean squared error scaling while using only $lceil log N il + b$ bits per client, where $N = (d)$ is the frame size.<n>We also derive a surrogate privacy-aware codebook objective that reduces the codebook-dependent MSE scaling from $O(4b)$ to $O(2b)$.
  arXiv  Detail & Related papers  (2026-08-05T17:51:25Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• ExecuGraph: A Multi-Agent, Execution-Grounded Framework for Reliable Backend Code Synthesis with Large Language Models [2.3004655342211078]
  Large Language Models generate plausible backend code, but a single-pass paradigm provides no guarantee of correctness or runtime reliability.<n>We present ExecuGraph, a multi-agent framework that places execution-based validation at the center of backend code.<n>A per-agent ablation, retry-budget sweep, error-class taxonomy, and test-source audit are reported.
  arXiv  Detail & Related papers  (2026-06-18T05:58:17Z)
• SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale [54.70985426016736]
  We present SkillDAG, which models inter-skill relationships as a typed directed graph.<n>Each search returns vector matches, typed-edge neighbors, and conflict signals, and a propose-then-commit protocol lets the agent register execution-backed edges.<n>On ALFWorld and SkillsBench with MiniMax-M2.7, SkillDAG reaches 67.1% success and 27.3% reward.
  arXiv  Detail & Related papers  (2026-06-02T02:45:21Z)
• Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis [3.0663322946413287]
  We introduce MEMOIR, a memory-guided tree-search framework with a two-level memory hierarchy.<n>Across seven Combinatorial optimization problems, MEMOIR achieves 96.7% solution validity.<n>MeMOIR's run-to-run validity standard deviation is more than an order of magnitude below that of every baseline we evaluated.
  arXiv  Detail & Related papers  (2026-05-17T16:47:31Z)
• Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration [57.23877089929136]
  Graph-of-Agents (GoA) is a new graph-based framework for modeling multi-agent LLM communication.<n>GoA achieves superior performance using only 3 selected agents, outperforming recent multi-agent LLM baselines.
  arXiv  Detail & Related papers  (2026-04-18T21:13:03Z)
• OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation [1.3722079106827219]
  OptAgent is a novel framework that combines multi-agent simulations with genetic algorithms to verify and optimize queries for e-commerce queries.<n>We evaluate OptAgent on a dataset of 1000 real-world e-commerce queries in five different categories.
  arXiv  Detail & Related papers  (2025-10-04T10:41:09Z)
• Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies [65.92826041406802]
  We propose a Proxy-based deep Graph Metric Learning approach from the perspective of graph classification. Multiple global proxies are leveraged to collectively approximate the original data points for each class. We design a novel reverse label propagation algorithm, by which the neighbor relationships are adjusted according to ground-truth labels.
  arXiv  Detail & Related papers  (2020-10-26T14:52:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.