Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Traces
cs.AI, cs.LG, cs.NE
Submitted: 2026-02-16
Updated: 2026-11-08
Code: https://github.com/wtong98/boule-or-baguette
Terminology
Sources
- GPT-4 Technical Report
- On Provable Length and Compositional Generalization
- Learn from Failure: Fine-Tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving
- Transformers as Soft Reasoners over Language
- 8-bit Optimizers via Block-wise Quantization
- The Ouroboros of Benchmarking: Reasoning Evaluation in an Era of Saturation
- GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models
- What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT
- Stream of Search (SoS): Learning to Search in Language
- Relational reasoning and inductive bias in transformers and large language models
- Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models
- The Llama 3 Herd of Models
- OpenThoughts: Data Recipes for Reasoning Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods
- Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Transformers Provably Solve Parity Efficiently with Chain of Thought
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents