Reasoning models enhance problem-solving by scaling test-time compute, yet they face a critical paradox: excessive thinking tokens often degrade performance rather than improve it. We attribute this to a fundamental architectural flaw: standard LLMs operate as "malloc-only" engines, continuously accumulating valid and redundant steps alike without a mechanism to prune obsolete information. To break this cycle, we propose Free()LM, a model that introduces an intrinsic self-forgetting capability via the Free-Module, a plug-and-play LoRA adapter. By iteratively switching between reasoning and cleaning modes, Free()LM dynamically identifies and prunes useless context chunks, maintaining a compact and noise-free state. Extensive experiments show that Free()LM provides consistent improvements across all model scales (8B to 685B). It achieves a 3.3% average improvement over top-tier reasoning baselines, even establishing a new SOTA on IMOanswerBench using DeepSeek V3.2-Speciale. Most notably, in long-horizon tasks where the standard Qwen3-235B-A22B model suffers a total collapse (0% accuracy), Free()LM restores performance to 50%. Our findings suggest that sustainable intelligence requires the freedom to forget as much as the power to think.

翻译：推理模型通过扩展测试时计算来增强问题解决能力，然而它们面临一个关键悖论：过多的思考标记往往导致性能下降而非提升。我们将此归因于一个根本性的架构缺陷：标准大语言模型作为“仅分配内存”的引擎运行，持续积累有效和冗余的步骤，却缺乏修剪过时信息的机制。为打破这一循环，我们提出Free()LM模型，该模型通过即插即用的LoRA适配器Free-Module引入了内在的自遗忘能力。通过在推理模式与清理模式间迭代切换，Free()LM动态识别并修剪无用的上下文块，维持紧凑且无噪声的状态。大量实验表明，Free()LM在所有模型规模（8B至685B）上均带来一致的性能提升。相较于顶级推理基线模型，其平均提升达3.3%，更在使用DeepSeek V3.2-Speciale时于IMOanswerBench上建立了新的SOTA。尤为突出的是，在标准Qwen3-235B-A22B模型完全失效（0%准确率）的长视野任务中，Free()LM将性能恢复至50%。我们的研究结果表明，可持续的智能既需要思考的能力，也同样需要遗忘的自由。