arXiv AI October 9, 2026 By Xihe Qiu (Shanghai University of Engineering Science, National University of Singapore), Yongxin Deng (Shanghai University of Engineering Science, University of Technology Sydney), Xiaoyu Tan (National University of Singapore), Zhen Fang (University of Technology Sydney), Ling Chen (University of Technology Sydney)

Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Bootstrapped Prolog-based Chain-of-Thought

Read the original on arXiv AI →

Thought‑Like‑Pro is a learning framework that enhances large language models’ reasoning by combining imitation learning with a Prolog logic engine. The approach imitates chain‑of‑thought processes verified by symbolic reasoning, allowing models to formulate rules from instructions and convert Prolog‑derived reasoning trajectories into natural language. Experiments show significant reasoning improvements and robust generalization with only a marginal performance drop on distributional extrapolation tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

arXiv AI

Aug 11

Think Deep, Speak Once: Relit, A Recursive Latent Implicit Transformer Framework

arXiv:2608. 08113v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has become the dominant paradigm for eliciting reasoning in Large Language Models (LLMs), yet it creates substantial computational overhead by forcing models to externalize intermediate reasoning steps as discrete tokens.

By Abhishek Panwar, Maheep Singh, Saksham Bansal

llms benchmarks

arXiv AI

Jun 4

Making Expert Reasoning Learnable with Self-Distillation

arXiv:2602. 02405v2 Announce Type: replace-cross Abstract: Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or the existence of a stronger model able to solve the problem.

By Ethan Mendes, Jungsoo Park, Alan Ritter

llms efficiency

arXiv Computer Vision

Aug 28

Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs

The paper introduces Echo-GRPO, a method that rewrites privileged reasoning traces into a model’s own idiolect to align off‑policy supervision with the student policy’s vocabulary. By preserving semantics through Dual‑Reference Decoding, Echo‑GRPO mitigates gradient clipping on critical reasoning tokens and improves reasoning distillation. The approach is instantiated as VideoEcho‑R1 for video reasoning, yielding consistent gains across multiple multimodal LLM backbones and benchmarks, and it can be applied as a plug‑in to both RL and supervised fine‑tuning frameworks.

By Ji Soo Lee, Jinyoung Park, Seohyun Lee, Jongha Kim, Joonmyung Choi, Jinsung Yoon, Hyunwoo J. Kim

llms reinforcement-learning fine-tuning efficiency multimodal benchmarks

arXiv AI

Jul 1

Deductive Logic in Language Models: Horizontal vs Vertical Reasoning

arXiv:2510. 09340v2 Announce Type: replace Abstract: Recent language models exhibit significant logical reasoning abilities, yet the mechanisms supporting deductive inference remain poorly understood.

By Davide Maltoni, Matteo Ferrara

llms safety

arXiv AI

Jun 15

Fractured Chain-of-Thought Reasoning

arXiv:2505. 12992v4 Announce Type: replace-cross Abstract: Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining.

By Baohao Liao, Hanze Dong, Yuhui Xu, Doyen Sahoo, Christof Monz, Junnan Li, Caiming Xiong

llms benchmarks

arXiv Computation and Language

Aug 27

GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning

GRIP (Granular Reward-guided Interpolation of Parameters) is a lightweight framework that blends a reasoning-oriented large language model with an instruction-tuned model by assigning learnable interpolation ratios to individual modules. The ratios are optimized while keeping both source models frozen, using a reward signal that prefers correct and concise responses. Experiments demonstrate that GRIP improves the accuracy-efficiency trade-off compared to fixed or search-based merging baselines and uncover module-wise fusion patterns linked to efficient reasoning.

By Lam So, Canhui Wu, Han Lin

llms

One email a morning, machine-written

Related stories

Think Deep, Speak Once: Relit, A Recursive Latent Implicit Transformer Framework

Making Expert Reasoning Learnable with Self-Distillation

Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs

Deductive Logic in Language Models: Horizontal vs Vertical Reasoning

Fractured Chain-of-Thought Reasoning

GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning