paper-with-me

Papers

THOUGHTSCULPT: Reasoning with Intermediate Revision and Search

2024-04-09 · Yizhou Chi, Kevin Yang, Dan Klein

We present THOUGHTSCULPT, a general reasoning and search method for tasks with outputs that can be decomposed into components. THOUGHTSCULPT explores a search tree of potential solutions using Monte Carlo Tree Search (MCTS), building solutions one action at a time and evaluating according to any domain-specific heuristic, which in practice is often simply an LLM evaluator. Critically, our action space includes revision actions: THOUGHTSCULPT may choose to revise part of its previous output rather than continuing to build the rest of its output. Empirically, THOUGHTSCULPT outperforms state-of-the-art reasoning methods across three challenging tasks: Story Outline Improvement (up to +30% interestingness), Mini-Crosswords Solving (up to +16% word success rate), and Constrained Generation (up to +10% concept coverage).

📄 PDF Abstract BibTeX arXiv:2404.05966

Code (1)

cyzus/thoughtsculpt 공식 구현

Similar Papers 제목 키워드 기반

Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search

2026-01-07 · Yu Guo, Shenghao Ye, Shuangwu Chen, Zijian Wen 외 arxiv

Table Question Answering (TableQA) benefits significantly from table pruning, which extracts compact sub-tables by eliminating redundant cells to streamline downstream reasoning. However, existing pruning methods typical…

Question Answering

Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference

2022-03-09 · Yufei Feng, Xiaoyu Yang, Xiaodan Zhu, Michael Greenspan

We introduce a neuro-symbolic natural logic framework based on reinforcement learning with introspective revision. The model samples and rewards specific reasoning paths through policy gradient, in which the introspectiv…

Natural Language Inferencereinforcement-learningReinforcement Learning (RL)Systematic Generalization

Unlocking Reasoning Capability on Machine Translation in Large Language Models

2026-02-16 · Sara Rajaee, Sebastian Vincent, Alexandre Berard, Marzieh Fadaee 외 arxiv

Reasoning-oriented large language models (RLMs) achieve strong gains on tasks such as mathematics and coding by generating explicit intermediate reasoning. However, their impact on machine translation (MT) remains undere…

Machine Translation

VeriTrace: Evolving Mental Models for Deep Research Agents

2026-05-25 · Haolang Zhao, Yunbo Long, Lukas Beckenbauer, Alexandra Brintrup arxiv

Deep research agents face vast, interdependent, and pervasively uncertain information. Existing systems explore what evolving intermediate representations should look like, but leave their evolution to the LLM's implicit…

Annotation and Classification of Evidence and Reasoning Revisions in Argumentative Writing

2021-07-14 · WS 2020 7 · Tazin Afrin, Elaine Wang, Diane Litman, Lindsay C. Matsumura 외

Automated writing evaluation systems can improve students' writing insofar as students attend to the feedback provided and revise their essay drafts in ways aligned with such feedback. Existing research on revision of ar…

Automated Writing EvaluationSentence