Pith. sign in

REVIEW 29 cited by

More Agents Is All You Need

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 2402.05120 v2 pith:7S6Y425P submitted 2024-02-03 cs.CL cs.AIcs.LG

More Agents Is All You Need

classification cs.CL cs.AIcs.LG
keywords agentsllmsmethodagentagentforestavailablebenchmarkscode
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We find that, simply via a sampling-and-voting method, the performance of large language models (LLMs) scales with the number of agents instantiated. Also, this method, termed as Agent Forest, is orthogonal to existing complicated methods to further enhance LLMs, while the degree of enhancement is correlated to the task difficulty. We conduct comprehensive experiments on a wide range of LLM benchmarks to verify the presence of our finding, and to study the properties that can facilitate its occurrence. Our code is publicly available at: https://github.com/MoreAgentsIsAllYouNeed/AgentForest

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 29 Pith papers

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

  1. When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models

    cs.AI 2026-06 unverdicted novelty 7.0

    Any single-output LLM ensemble is accuracy-capped at 1-beta where beta is the all-models-wrong rate, a quantity not captured by pairwise correlations and frequently underestimated by copula models.

  2. Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs

    cs.MA 2026-05 unverdicted novelty 7.0

    LATTE coordinates LLM agent teams with an evolving shared task graph, cutting token use, time, and failures while matching or beating accuracy of MetaGPT, leader-worker, and static methods.

  3. Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR

    cs.CV 2025-04 conditional novelty 7.0

    Consensus Entropy measures inter-VLM output agreement to verify OCR reliability and enable self-improving ensembles, yielding 42.1% F1 gains over single-model judging.

  4. State-dependent error correlations shape voting thresholds in committees of AI agents

    cs.CY 2026-07 accept novelty 6.0

    Correlated errors among AI voters create an irreducible committee-error floor, and using state-dependent correlation estimates improves held-out k-of-n threshold selection.

  5. Are Diversity Metrics Measuring Diversity? A Capability-Controlled Audit of Majority-Vote Gain in LLM Ensembles

    cs.CL 2026-07 conditional novelty 6.0

    Diversity metrics used to select LLM ensembles are largely capability proxies; after control, only a modest pairwise co-failure association with majority-vote gain remains.

  6. Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds

    cs.AI 2026-06 unverdicted novelty 6.0

    A kNN lower-confidence-bound approach for act-or-defer decisions in multi-agent LLM debates respects user-declared wrong-action budgets while achieving high automation rates on benchmarks.

  7. Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning

    cs.CL 2026-06 unverdicted novelty 6.0

    EDV decouples execution, distillation by a third-party agent, and consensus verification to filter erroneous trajectories in LLM agent experience learning, outperforming baselines on tau2-bench, Mind2Web, and MMTB.

  8. Streaming Communication in Multi-Agent Reasoning

    cs.CL 2026-06 conditional novelty 6.0

    Streaming an agent's reasoning steps to the next agent as they are produced cuts latency and, when early steps are more reliable than late ones, also improves final accuracy.

  9. Streaming Communication in Multi-Agent Reasoning

    cs.CL 2026-06 unverdicted novelty 6.0

    StreamMA introduces streaming communication in multi-agent reasoning to reduce latency via pipelining and improve effectiveness by leveraging reliable early steps, with closed-form analysis and a step-level scaling law.

  10. Ontology-constrained multi-LLM scoring of hypothesis support in the predictive processing literature

    q-bio.NC 2026-05 unverdicted novelty 6.0

    A multi-LLM council scores predictive processing papers on an expert ontology, maps results in 3D hypothesis space, and introduces a dispersion metric showing greater spread in global versus local oddball paradigms.

  11. Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework

    cs.MA 2026-05 unverdicted novelty 6.0

    TopOptAgents deploys six LLM agents in self-refining loops to automate the full topology optimization workflow and succeeds on problem classes where single LLMs fail.

  12. The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning

    cs.CL 2026-05 unverdicted novelty 6.0

    Closed-system multi-step LLM reasoning is subject to an information-theoretic bound where mutual information with evidence decreases, preserving accuracy while eroding faithfulness, with EGSR recovering it on SciFact ...

  13. When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling

    cs.AI 2026-04 unverdicted novelty 6.0

    A disagreement-guided routing framework dynamically selects among resolution, voting, and rewriting strategies for test-time scaling, delivering 3-7% accuracy gains with lower sampling cost on mathematical benchmarks.

  14. Effective Strategies for Asynchronous Software Engineering Agents

    cs.CL 2026-03 conditional novelty 6.0

    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.

  15. When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines

    cs.MA 2026-03 conditional novelty 6.0

    In a 42-task controlled comparison, selecting the best candidate with judge panels beats MoA-style synthesis in every task, and a crossover threshold explains when team diversity helps.

  16. Tacit Coordination of Large Language Models

    cs.GT 2026-01 conditional novelty 6.0

    Across 20+ open-source LLMs, tacit coordination in focal-point games is often at or above human levels, with systematic failures on cultural and numerical salience that culture prompts partially fix.

  17. ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods

    cs.CE 2026-01 unverdicted novelty 6.0

    ALL-FEM fine-tunes LLMs on a corpus of verified FEniCS scripts and uses multi-agent workflows to automate finite element code generation, achieving 71.79% success on 39 benchmarks across elasticity, flow, and coupled ...

  18. Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search

    cs.CL 2025-02 unverdicted novelty 6.0

    DITS replaces Q-value guidance in MCTS with influence scores for synthetic data synthesis in multi-agent LLM training, claiming better efficiency and performance on eight datasets.

  19. A Technical Taxonomy of LLM Agent Communication Protocols

    cs.MA 2026-06 unverdicted novelty 5.0

    Creates a five-dimension taxonomy (counterparty, payload, interaction state, discovery mechanism, schema flexibility) from nine protocols and identifies architectural patterns plus convergence trends.

  20. Do More Agents Help? Controlled and Protocol-Aligned Evaluation of LLM Agent Workflows

    cs.AI 2026-06 conditional novelty 5.0

    Under controlled identical protocols, only one of six multi-agent LLM systems marginally exceeds a single-agent baseline on benchmark-balanced accuracy while the rest trail and cost more; a runtime workflow reaches 66...

  21. When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling

    cs.AI 2026-04 conditional novelty 5.0

    A disagreement-based router that decides per math problem whether to accept, majority-vote, or rewrite improves accuracy by 3–7% with fewer samples than fixed test-time scaling methods.

  22. Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems

    cs.MA 2026-03 unverdicted novelty 5.0

    LLMA-Mem improves long-horizon performance in LLM multi-agent systems over baselines while reducing cost and shows non-monotonic scaling where memory-enabled smaller teams can beat larger ones.

  23. Transition from Statistical to Hardware-Limited Scaling in Photonic Quantum State Reconstruction

    quant-ph 2026-03 unverdicted novelty 5.0

    Classical shadow tomography on integrated photonics shows a sharp transition from statistical O(M^{-1/2}) error scaling to a hardware-limited floor set by unitary spectral distortions.

  24. Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process

    cs.CL 2025-12 unverdicted novelty 5.0

    LLM-PeerReview ensembles LLMs by scoring responses with LLM-as-Judge and selecting the best via averaging or truth inference, beating Smoothie-Global by 6.9-7.3 points on four datasets.

  25. A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement

    cs.CL 2025-07 unverdicted novelty 5.0

    SMCS coordinates 15 open-source LLMs via retrieval-based prior selection and exploration-exploitation posterior enhancement, outperforming GPT-4.1 by 5.36% and GPT-o3-mini by 5.28% on eight benchmarks.

  26. Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation

    cs.CR 2025-10 conditional novelty 4.0

    A backward-propagation scoring scheme over a signed temporal DAG can identify malicious agents in LLM multi-agent systems and cut their communications, improving defended accuracy by 3–7 percentage points in the autho...

  27. Token-Operations-Oriented Inference Optimization Techniques for Large Models

    cs.SE 2026-06 conditional novelty 3.0

    A survey of large-model inference optimization, organized as a four-layer 'token-operations' taxonomy: multi-model fusion, model optimization, compute-model fusion, and compute-network-model fusion.

  28. Token-Operations-Oriented Inference Optimization Techniques for Large Models

    cs.SE 2026-06 unverdicted novelty 3.0

    The paper introduces a four-layer technical architecture for token-operations-oriented inference optimization in large models and reviews key technologies and industry status at each layer.

  29. Harnessing Multiple Large Language Models: A Survey on LLM Ensemble

    cs.CL 2025-02 unverdicted novelty 2.0

    A systematic survey of LLM ensemble methods organized into a taxonomy of ensemble-before-inference, ensemble-during-inference, and ensemble-after-inference stages, with review of benchmarks, applications, and future d...