Test-Time Adaptation of Reasoning Strategies with Bayesian Nonparametric Memory
cs.CL
Submitted: 2026-10-05
Updated: 2026-10-05
Terminology
Sources
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- Granite Embedding R2 Models
- ATLAS: Learning to Optimally Memorize the Context at Test Time
- Titans: Learning to Memorize at Test Time
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
- Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
- Memp: Exploring Agent Procedural Memory
- Test-Time Training on Nearest Neighbors for Large Language Models
- Reinforcement Learning via Self-Distillation
- Harness Continual Learning: Continual Adaptation Beyond Model Parameters
- Generalization through Memorization: Nearest Neighbor Language Models
- Aligning Language Models from User Interactions
- Training Language Models to Self-Correct via Reinforcement Learning
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
- AutoHarness: improving LLM agents by automatically synthesizing a code harness
- Show Your Work: Scratchpads for Intermediate Computation with Language Models
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- MemGPT: Towards LLMs as Operating Systems
- Latent Principle Discovery for Language Model Self-Improvement
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering