Pith. sign in

REVIEW 5 cited by

Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains

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 2501.05707 v2 pith:KX6HCDZL submitted 2025-01-10 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords modelsdataself-improvementapproachlanguagemultiagentreasoningtraining
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) have achieved remarkable performance in recent years but are fundamentally limited by the underlying training data. To improve models beyond the training data, recent works have explored how LLMs can be used to generate synthetic data for autonomous self-improvement. However, successive steps of self-improvement can reach a point of diminishing returns. In this work, we propose a complementary approach towards self-improvement where finetuning is applied to a multiagent society of language models. A group of language models, all starting from the same base model, are independently specialized by updating each one using data generated through multiagent interactions among the models. By training each model on independent sets of data, we illustrate how this approach enables specialization across models and diversification over the set of models. As a result, our overall system is able to preserve diverse reasoning chains and autonomously improve over many more rounds of fine-tuning than single-agent self-improvement methods. We quantitatively illustrate the efficacy of the approach across a wide suite of reasoning tasks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models

    cs.LG 2025-06 conditional novelty 7.0 of 10

    Online self-play between attacker and defender roles of a single LLM improves safety robustness and attack diversity across Llama and Qwen models.

  2. Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic

    cs.AI 2026-01 unverdicted novelty 6.0 of 10

    Multi-agent actor-critic methods with a centralized critic improve decentralized LLM collaboration over Monte Carlo baselines in long-horizon and sparse-reward settings.

  3. OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration

    cs.AI 2025-09 reject novelty 5.0 of 10

    OSC uses learned Collaborator Knowledge Models and RL-trained communication policies to make LLM agents communicate adaptively, claiming gains on AlpacaEval 2.0 and MT-Bench.

  4. SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control

    cs.AI 2025-08 conditional novelty 4.0 of 10

    A multi-agent RL workflow that interleaves single-agent updates, applied to mobile GUI control, achieves SOTA zero-shot performance and a +14.8 MATH500 gain.

  5. Grounding Natural Language for Multi-agent Decision-Making with Multi-agentic LLMs

    cs.AI 2025-08 unverdicted novelty 3.0 of 10

    A design framework for multi-agent LLMs combining prompting, memory, multimodal input, and fine-tuning, with promised ablations on social-dilemma games that are absent from the supplied text.

Pith tools