Skip to content

Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems

Sep 2026 · 0 citations · 41 references
Computer Science

TL;DR

This work studies blackboard intelligence: an inference-time perspective in which a model works on a fixed, revisable canvas and searches over candidate solution states rather than committing to a causal, left-to-right trajectory, and concludes that mean confidence, a simple model-internal quantity available from the standard masked diffusion objective, provides a useful proxy for global coherence and can guide inference-time search and revision.

Abstract

Next-token prediction has driven remarkable progress in large language models, yet a growing body of evidence suggests that they can struggle on problems governed by complex global constraints. In this work, we focus on this regime and ask whether some of these limitations arise from the inference interface induced by next-token prediction itself. We study this question through blackboard intelligence: an inference-time perspective in which a model works on a fixed, revisable canvas and searches over candidate solution states rather than committing to a causal, left-to-right trajectory. We instantiate this idea with diffusion language models, whose any-order prediction interface naturally exposes predictions over partially filled solution states. Our key observation is that mean confidence, a simple model-internal quantity available from the standard masked diffusion objective, provides a useful proxy for global coherence and can guide inference-time search and revision. Empirically, across ZebraLogic, Nurse Rostering, and Job-Shop Scheduling, Blackboard consistently improves inference while holding the fine-tuned LLaDA-8B-Instruct checkpoint fixed and substantially outperforms same-scale autoregressive baselines, reaching 90.4% accuracy on ZebraLogic-Hard, 76.4% exact feasibility on Nurse Rostering, and 80.2% optimality on JSSP. Stronger autoregressive search and refinement also fail to close the gap on ZebraLogic-Hard, while Blackboard surpasses tested frontier LLMs there and on JSSP despite their substantially greater scale and strong test-time reasoning. We open-source our codebase at https://github.com/jwoosang1/blackboard-intelligence.

View source

Similar papers

Open access 2026

Efficient LLM Reasoning via Logit-Based Introspection

This paper proposes LLM Introspection, a practical inference-time reasoning control method that leverages keyword-token logits to enable early stopping during the reasoning process, and integrates the method into a vLLM-based proxy, providing a practical, plug-and-play deployment path.

Kai-Hao Zhang, Bin Shi, Kai Sun et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Thinking with Looped Flows

Looped flows are proposed, an approach that allows solving harder problems by spending more computation through a finer temporal grid and enables multiple valid predictions from different initial noise samples.

Jinwoo Kim · 13 citations · ⚡1
#natural language process... Preprint Oct 2026

Test-Time Adaptation of Reasoning Strategies with Bayesian Nonparametric Memory

This work introduces a Hierarchical Dirichlet Process Gaussian Mixture Model over behavior embeddings, which shares components across domains while allowing domain-specific mixing weights, and uses the posterior predictive to retrieve relevant behaviors for a query, and shows that the Bayesian Cheatsheet is an adaptive...

Keshav Ramji, Tahira Naseem, R. Astudillo · 0 citations
#artificial intelligence Review Sep 2026

RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases

Research Attention Prediction (RAP), a rolling benchmark covering 278 AI/ML fields and 1,390 episodes, is introduced, a rolling benchmark covering 278 AI/ML fields and 1,390 episodes for large language models to track shifts in research attention.

Ying-Qian Wu, Jingcong Liang, Si-Yuan Wang et al. · 0 citations
#machine learning Preprint Sep 2026

RecurTrace: Adaptive Latent Reasoning with Loop-Time Memory

RecurTrace introduces Loop Memory Attention, which lets each looped layer attend to its own states from previous iterations along the loop-time axis, so the model can revisit earlier computations instead of relying on the latest state alone.

Yu-Xiang Wang, Kun-Yu Feng, Ying-Da Shen et al. · 7 citations
#machine learning Preprint Oct 2026

Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals

A local recovery guarantee for teachers sufficiently close to the initial student in a shared parameterization under regularity conditions is proved, offering a conditional explanation for the success of self-RL teachers in the authors' experiments.

Lei Zhao, Qi-Chao Zhao, Bo-Wen Zuo et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Aug 27, 2026

Looking beyond natural sequences

A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.