ScaleLogic: synthetic logical reasoning framework for studying RL scaling with long-horizon reasoning problems
| Name | Categories | Topics | References | Credibility | CreateDate | UpdateDate | Title | RelatedNotes | NavigationOrder | Eleventy | TemplateEngineOverride | Created |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 20260511_rl_long_horizon_reasoning_llm_expressiveness | paper_analysis | reinforce_learning, reasoning, llm, test_time_scaling, symbolic_reasoning | purdue_university, georgia_tech, scalelogic | 100 | Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key | chain_of_thought_prompting_elicits_reasoning, reasoningbank_scaling_agent_self_evolving_reasoning_memory | [object Object] | [object Object] | md |