On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “blocksworld”

Enriching Visual with Verbal Explanations for Relational Concepts -- Combining LIME with Alephcs.LG

Enhances visual explanations with logical rules for complex concepts.

problem Lack of explanatory power for deep learning models, especially for relational concepts.

method Combining LIME for highlighting and Aleph for logic rules.

result Generated relational rules can be explicitly linked to input images.

deep learning explanation generation Aleph LIME blocksworld

2019-10-04abs ↗pdf ↗

Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspectivecs.AI

RL enhances LLM planning but introduces spurious solutions and diversity collapse.

problem Theoretical understanding of RL's benefits and limitations in LLM planning.

method Graph-based abstraction, policy gradient, Q-learning, supervised fine-tuning.

result RL's exploration is crucial for generalization, but PG suffers from diversity collapse.

Reinforcement Learning Language Models Planning Spurious Solutions Diversity Collapse

2025-09-26abs ↗pdf ↗

PAC-MCTS: Bias-Aware Pruning for Robust LLM-Guided Search and Planningcs.LG

PAC-MCTS addresses biased search in LLM-guided planning by dynamically pruning.

problem Systematic biases in LLMs lead to inefficient and unsafe search in deep planning tasks.

method Formulates node expansion as BAI under bounded bias, derives sample complexity bounds, and proposes PAC-MCTS for dynamic confidence bounds.

result PAC-MCTS improves robustness and efficiency by up to 78% fewer API evaluations and 3x higher sample efficiency.

bias-aware pruning LLM-guided planning sample complexity information theory dynamic confidence bounds

2026-04-15abs ↗pdf ↗