Pith. sign in

REVIEW 4 cited by

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation

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 2403.05313 v1 pith:MTHC6PB5 submitted 2024-03-08 cs.CL cs.AI

Zihao Wang , Anji Liu , Haowei Lin , Jiaqi Li , Xiaojian Ma , Yitao Liang This is my paper
classification cs.CLcs.AI
keywords generationlong-horizonreasoningthoughtsimprovesinformationretrievaltask
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-horizon generation tasks, while hugely mitigating hallucination. In particular, the proposed method -- *retrieval-augmented thoughts* (RAT) -- revises each thought step one by one with retrieved information relevant to the task query, the current and the past thought steps, after the initial zero-shot CoT is generated. Applying RAT to GPT-3.5, GPT-4, and CodeLLaMA-7b substantially improves their performances on various long-horizon generation tasks; on average of relatively increasing rating scores by 13.63% on code generation, 16.96% on mathematical reasoning, 19.2% on creative writing, and 42.78% on embodied task planning. The demo page can be found at https://craftjarvis.github.io/RAT

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 10 citations worldwide. Full citation record

  1. REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning

    cs.CL 2026-07 conditional novelty 6.0 of 10

    REFACT teaches LLMs to adaptively cite only the source facts needed during chain-of-thought reasoning, improving faithfulness and shortening reasoning traces.

  2. Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

    cs.LG 2025-12 conditional novelty 6.0 of 10

    CrossAgent learns step-level action-interface selection via a three-stage SFT + single-turn GRPO + multi-turn GRPO pipeline, reporting 54.6% mean success on 800+ Minecraft tasks after RL on only 30 tasks.

  3. Am I on the Right Track? What Can Predicted Query Performance Tell Us about the Search Behaviour of Agentic RAG

    cs.IR 2025-07 conditional novelty 6.0 of 10

    QPP estimates of the first search query in agentic RAG are weakly positively correlated with final answer quality, and stronger retrievers shorten reasoning while improving answers.

  4. GroupRAG: Cognitively Inspired Group-Aware Retrieval and Reasoning via Knowledge-Driven Problem Structuring

    cs.IR 2026-03 conditional novelty 5.0 of 10

    Structuring questions into knowledge-driven keypoint groups before retrieval and reasoning improves small-model accuracy on MedQA.

Pith tools