arXiv Computation and Language
Notes to Self: Can LLMs Benefit from Experiential Abstractions?
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Machine Learning
Sep 14
CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models
CanvasAnneal is a curriculum‑guided reinforcement learning framework designed to improve Diffusion Language Models (DLMs) on complex reasoning and tool‑use tasks. It starts training by injecting reasoning traces from a stronger teacher model into the diffusion canvas, then gradually reduces this guidance so the model learns to generate reasoning independently. Experiments on mathematical reasoning and tool‑use benchmarks show that CanvasAnneal outperforms standard diffusion RL methods such as diffu‑GRPO on tasks like MATH500, Countdown, and Tau2, and accelerates reward improvement, though the gains vary by task.
arXiv AI
Sep 10
Boosting LLM Reasoning via Human-Inspired Reward Shaping
The paper introduces T2T (Thickening-to-Thinning), a dynamic reward framework for large language models that mimics human learning by separating exploration and consolidation phases. During incorrect attempts, T2T encourages exploration to broaden the search space, while after correct solutions it applies length penalties to promote concise reasoning. Experiments on mathematical benchmarks across five mainstream LLMs show that T2T outperforms standard GRPO and recent baselines, improving overall reasoning performance.
arXiv Machine Learning
Jun 4
Can Large Language Models Generalize Procedures Across Representations?
arXiv:2602. 03542v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are trained and tested extensively on symbolic representations such as code and graphs, yet real-world user tasks are often specified in natural language.
arXiv Machine Learning
Jul 16
Test-Time Learning with an Evolving Library
arXiv:2605. 14477v2 Announce Type: replace Abstract: We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates or external supervision.
arXiv AI
Sep 1
AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing
AgenticRag‑R1 is a reinforcement‑learning framework that integrates reasoning, retrieval, and memory through a stack and fine‑grained action space. It uses hierarchical action‑aware rewards and an information‑aware trajectory rejection strategy to support long‑horizon learning. Experiments on multi‑hop, open‑domain, and agentic reasoning benchmarks show that AgenticRag‑R1 outperforms strong baselines and produces robust, interpretable, memory‑aware reasoning behaviors.
arXiv Machine Learning
Jun 17
Continual Self-Improvement with Lightweight Experiential Latent Memories
arXiv:2606. 17803v1 Announce Type: new Abstract: Large language models achieve strong reasoning performance by scaling inference-time compute, yet remain fundamentally stateless, discarding the rich, self-produced reasoning traces generated during this process.