The reviewed record of science sign in
Pith

arxiv: 2312.10003 · v1 · pith:HLHTXXLS · submitted 2023-12-15 · cs.CL

ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:HLHTXXLSrecord.jsonopen to challenge →

classification cs.CL
keywords agentexternalknowledgemodellanguagelargemulti-stepquestions
0
0 comments X
read the original abstract

Answering complex natural language questions often necessitates multi-step reasoning and integrating external information. Several systems have combined knowledge retrieval with a large language model (LLM) to answer such questions. These systems, however, suffer from various failure cases, and we cannot directly train them end-to-end to fix such failures, as interaction with external knowledge is non-differentiable. To address these deficiencies, we define a ReAct-style LLM agent with the ability to reason and act upon external knowledge. We further refine the agent through a ReST-like method that iteratively trains on previous trajectories, employing growing-batch reinforcement learning with AI feedback for continuous self-improvement and self-distillation. Starting from a prompted large model and after just two iterations of the algorithm, we can produce a fine-tuned small model that achieves comparable performance on challenging compositional question-answering benchmarks with two orders of magnitude fewer parameters.

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 11 Pith papers

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

  1. Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

    cs.CL 2025-11 unverdicted novelty 7.0

    Evo-Memory is a new benchmark for self-evolving memory in LLM agents across task streams, with baseline ExpRAG and proposed ReMem method that integrates reasoning, actions, and memory updates for continual improvement.

  2. Stop Hand-Holding Your Coding Agent: Engineering the Loops that Replace Step-by-Step Prompting

    cs.SE 2026-06 unverdicted novelty 6.0

    Introduces loop engineering as a distinct practice layer for coding agents, supplies a taxonomy and verification ladder, and analyzes a hand-coded corpus of fifty real loops.

  3. Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training

    cs.AI 2026-06 unverdicted novelty 6.0

    REINFORCE self-training on competitive programming tasks exhibits robust rise-then-collapse in pass@1; CARE, ES, and GRPO mitigate it in model-size-dependent ways across Qwen-2.5-3B/7B and a Gemma pilot.

  4. Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts

    cs.AI 2026-06 unverdicted novelty 6.0

    Graph2Idea builds dynamic knowledge graphs from retrieved literature to supply compact, relational contexts that guide LLMs in generating novel, feasible, and high-quality scientific ideas, outperforming flat-text bas...

  5. Quantifying Trust: Financial Risk Management for Trustworthy AI Agents

    cs.AI 2026-04 unverdicted novelty 6.0

    The paper introduces the Agentic Risk Standard (ARS) as a payment settlement framework that delivers predefined compensation for AI agent execution failures, misalignment, or unintended outcomes.

  6. Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

    cs.CL 2025-11 unverdicted novelty 6.0

    Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and ...

  7. SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating

    cs.LG 2026-06 unverdicted novelty 5.0

    SlimSearcher reduces tool-call rounds by 17-58% on GAIA, BrowseComp and XBenchDeepSearch while maintaining accuracy via Pareto filtration in SFT and Adaptive Reward Gating in RL.

  8. EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation

    cs.CL 2026-05 unverdicted novelty 5.0

    EvoGens uses rank-based mutation, semantic-aware crossover, and lightweight evaluation to evolve populations of LLM-generated scientific ideas, boosting novelty and diversity metrics.

  9. DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition

    cs.AI 2026-05 unverdicted novelty 4.0

    DuIVRS-2 deploys an LLM-driven IVR pipeline that processes 0.4 million calls per day at 83.9 percent task success rate using FSM-guided augmentation, selective CoT generation, and cooperative policy iteration.

  10. Agentic Reasoning for Large Language Models

    cs.AI 2026-01 unverdicted novelty 4.0

    The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applicat...

  11. From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review

    cs.AI 2025-04 accept novelty 4.0

    A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.