LightThinker++：从推理压缩到内存管理的演进

摘要

大语言模型在复杂推理任务中表现出色，但其效率受限于冗长思维轨迹带来的激增认知负荷。本文提出LightThinker方法，使大语言模型能够将中间思维动态压缩为紧凑的语义表征。然而静态压缩方法在复杂推理中常面临挑战，中间细节的不可逆损失可能导致逻辑瓶颈。为此，我们升级框架至LightThinker++，引入显式自适应记忆管理机制。该范式通过集成显式记忆原语转向行为级管理，并辅以专门设计的轨迹合成流程来训练目标导向的记忆调度策略。大量实验证明该框架具有三维度优势：（1）LightThinker在精度损失最小化前提下，峰值令牌使用量降低70%，推理时间缩短26%；（2）在标准推理任务中，LightThinker++在同等上下文预算下实现峰值令牌使用量下降69.9%，同时准确率提升2.42%；（3）在长周期智能体任务中表现尤为突出，模型在超过80轮交互后仍保持稳定内存占用（降低60%-70%），在不同复杂场景下平均性能提升14.8%。本研究为持续开展深度大语言模型推理提供了可扩展的低开销解决方案。

English

Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces. In this paper, we propose LightThinker, a method that enables LLMs to dynamically compress intermediate thoughts into compact semantic representations. However, static compression often struggles with complex reasoning where the irreversible loss of intermediate details can lead to logical bottlenecks. To address this, we evolve the framework into LightThinker++, introducing Explicit Adaptive Memory Management. This paradigm shifts to behavioral-level management by incorporating explicit memory primitives, supported by a specialized trajectory synthesis pipeline to train purposeful memory scheduling. Extensive experiments demonstrate the framework's versatility across three dimensions. (1) LightThinker reduces peak token usage by 70% and inference time by 26% with minimal accuracy loss. (2) In standard reasoning, LightThinker++ slashes peak token usage by 69.9% while yielding a +2.42% accuracy gain under the same context budget for maximum performance. (3) Most notably, in long-horizon agentic tasks, it maintains a stable footprint beyond 80 rounds (a 60%-70% reduction), achieving an average performance gain of 14.8% across different complex scenarios. Overall, our work provides a scalable direction for sustaining deep LLM reasoning over extended horizons with minimal overhead.

LightThinker++：从推理压缩到内存管理的演进

LightThinker++: From Reasoning Compression to Memory Management

摘要

Support