arXiv AI June 11, 2026 By Elias Sandmann, Sebastian Lapuschkin, Wojciech Samek

The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network

arXiv:2508. 21380v3 Announce Type: replace-cross Abstract: Recent mechanistic work has uncovered learned algorithms within neural networks, from modular arithmetic to search and planning in game-playing agents.

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.

arXiv Computation and Language

Sep 22

Do Chess Explanations Reflect Model Decisions? Behavioral and Token-Level Tests of LLM Reasoning Faithfulness

arXiv:2609.22245v1 Announce Type: new Abstract: Large language models can produce fluent explanations for chess moves, but plausible language does not necessarily reflect the reasoning behind a decis...

By Angelina Parfenova

llms

arXiv Machine Learning

Aug 31

Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess

arXiv:2608.27757v1 Announce Type: new Abstract: Searchless chess networks reach human master strength from a single forward pass by imitating a stronger teacher: the strongest, Leela Chess Zero's (Lc...

By Szymon Mi{\l}osz, Piotr Duch, Szymon Grabowski

reinforcement-learning fine-tuning

arXiv AI

Jun 4

Learning Empirically Admissible Neural Heuristics for Combinatorial Search

arXiv:2606. 04860v1 Announce Type: cross Abstract: Finding optimal solution paths for combinatorial puzzles like the Rubik's Cube, sliding tile puzzles, and Lights Out remains a classical challenge in artificial intelligence.

By Siddharth Sahay

reinforcement-learning safety

arXiv AI

3d ago

Conditional Generation of Creative Chess Puzzles with Diffusion Models

The paper presents a method for generating creative chess puzzles using masked diffusion models that can be conditioned on tactical themes and partial board positions. It introduces an auxiliary best‑move prediction task that boosts solution uniqueness by 11.6% and theme‑conditioning accuracy by 2.5%. A reinforcement learning framework further increases the yield of unique, theme‑matching puzzles by 89.1%, and the authors release open‑weights models for the community.

By Aatu Selkee, Severi Rissanen, Xidong Feng, Tom Zahavy, Eric Malmi

llms diffusion reinforcement-learning

arXiv Machine Learning

Jul 24

The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning

arXiv:2607. 20952v1 Announce Type: new Abstract: Latent, or silent, reasoning lets language models carry out intermediate computation in continuous vector space instead of words, and is widely assumed to function as an internal scratchpad the model actively consults during inference.

By Ishan S. Kshirsagar

llms reinforcement-learning fine-tuning

arXiv AI

Sep 16

Managing Action Preconditions in Neuro-Symbolic RL: Three Placement Strategies for Embodied Agents

arXiv:2609.16056v1 Announce Type: cross Abstract: Humans carry behaviour knowledge of how to act in familiar situations into every new task rather than relearning it from scratch. There is no reason...

By Norbert Oswald, Fabian Deuser, Thomas Br\"aunl

agents reinforcement-learning robotics benchmarks safety

One email a morning, machine-written

Related stories

Do Chess Explanations Reflect Model Decisions? Behavioral and Token-Level Tests of LLM Reasoning Faithfulness

Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess

Learning Empirically Admissible Neural Heuristics for Combinatorial Search

Conditional Generation of Creative Chess Puzzles with Diffusion Models

The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning

Managing Action Preconditions in Neuro-Symbolic RL: Three Placement Strategies for Embodied Agents