Pith. sign in

REVIEW 9 cited by

SELF: Self-Evolution with Language Feedback

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2310.00533 v4 pith:V5URQLT4 submitted 2023-10-01 cs.CL cs.AIcs.LG

Jianqiao Lu , Wanjun Zhong , Wenyong Huang , Yufei Wang , Qi Zhu , Fei Mi , Baojun Wang , Weichao Wang
show 4 more authors
Xingshan Zeng Lifeng Shang Xin Jiang Qun Liu
This is my paper · ORCID
classification cs.CLcs.AIcs.LG
keywords llmsselfmodelself-evolutionlanguageprocessself-refinementcapabilities
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large Language Models (LLMs) have demonstrated remarkable versatility across various domains. To further advance LLMs, we propose 'SELF' (Self-Evolution with Language Feedback), a novel approach that enables LLMs to self-improve through self-reflection, akin to human learning processes. SELF initiates with a meta-skill learning process that equips the LLMs with capabilities for self-feedback and self-refinement. Subsequently, the model undergoes an iterative process of self-evolution. In each iteration, it utilizes an unlabeled dataset of instructions to generate initial responses. These responses are enhanced through self-feedback and self-refinement. The model is then fine-tuned using this enhanced data. The model undergoes progressive improvement through this iterative self-evolution process. Moreover, the SELF framework enables the model to apply self-refinement during inference, which further improves response quality. Our experiments in mathematics and general tasks demonstrate that SELF can enhance the capabilities of LLMs without human intervention. The SELF framework indicates a promising direction for the autonomous evolution of LLMs, transitioning them from passive information receivers to active participants in their development.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

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

  1. SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models

    cs.CL 2024-12 conditional novelty 7.0 of 10

    SPaR trains LLMs by having them refine their own failed responses through tree search, producing preference pairs with minimal irrelevant variation, and lifts LLaMA3-8B above GPT-4-Turbo on IFEval.

  2. ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs

    cs.CL 2025-06 conditional novelty 6.0 of 10

    ClusterUCB uses gradient clustering plus a modified UCB bandit to match full-budget gradient influence data selection at a 20% computing budget.

  3. Aligning Instruction Tuning with Pre-training

    cs.AI 2025-01 conditional novelty 6.0 of 10

    AITP selects pre-training texts that are underrepresented relative to instruction-tuning data, rewrites them into instruction-response pairs, and improves average SFT performance on three open LLMs.

  4. Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A multimodal LLM can improve itself using only unlabeled images by self-generating questions, self-enhancing answers, and adding a description-alignment loss to DPO.

  5. Towards Adaptive Mechanism Activation in Language Agent

    cs.CL 2024-12 conditional novelty 6.0 of 10

    ALAMA trains Llama-3-8B to choose among five agent mechanisms per task via self-exploration and KTO-based preference learning, improving accuracy over fixed-mechanism baselines on math and QA tasks.

  6. AgentOmnia: Scaling Agentic Models for Full-Scenario Applications

    cs.AI 2026-07 conditional novelty 5.0 of 10

    Post-training an open Qwen3-30B agent on 52,361 verifiable tasks in 5,018 synthesized stateful environments lifts its average across four agent benchmarks from 22.9% to 41.7%.

  7. SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams

    cs.CL 2026-01 unverdicted novelty 5.0 of 10

    SERM deploys multi-agent sample mining and two-level label agreement to enable iterative self-evolution of relevance models on industrial query streams, yielding performance gains in offline and online tests.

  8. Active Inference for Self-Organizing Multi-LLM Systems: A Bayesian Thermodynamic Approach to Adaptation

    cs.CL 2024-12 reject novelty 5.0 of 10

    An active inference controller selects prompts and search actions for an LLM agent, with experiments showing learned structure in observation matrices and an exploration-to-exploitation shift.

  9. Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agents

    cs.CL 2024-12 conditional novelty 4.0 of 10

    A multi-path, reactive-plus-reflection agent framework improves gpt-3.5-turbo accuracy on MMLU physics, math, and moral reasoning subsets compared with CoT, self-consistency, and self-refine baselines.

Pith tools