LightThinker++: From Reasoning Compression to Memory Management

• URL: http://arxiv.org/abs/2604.03679v1
• Date: Sat, 04 Apr 2026 10:46:09 GMT
• Title: LightThinker++: From Reasoning Compression to Memory Management
• Abstract summary: Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces.<n>We propose LightThinker, a method that enables LLMs to dynamically compress intermediate thoughts into compact semantic representations.<n>We evolve the framework into LightThinker++, introducing Explicit Adaptive Memory Management.
• Score: 61.2260619973687
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Drive by Hindsight and Foresight: Tool-Grounded Synergistic Reasoning over Hierarchical Memory for Autonomous Driving [0.8419406375517101]
  VLMs have shown promise for autonomous driving yet still suffer from weak-temporal perception, and limited generalization.<n>Recent methods improve reasoning and decision-making through CoT explanations, retrieval-augmented generation or the static injection of tool outputs.<n>We present to our knowledge, the first synergistic framework that tightly couples hierarchical memory with proactive tool invocation in a closed loop.
  arXiv  Detail & Related papers  (2026-09-08T03:59:10Z)
• ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning [46.225019133047965]
  Memory is essential for enabling large language model (LLM) agents to handle long-horizon reasoning tasks.<n>We propose ActiveMem, a framework that decouples agent memory from the core reasoning process.<n>Experiments on BrowseComp-Plus and GAIA show that ActiveMem achieves state-of-the-art accuracy with significantly reduced overhead.
  arXiv  Detail & Related papers  (2026-06-09T08:03:38Z)
• From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents [78.30630000529133]
  We propose MM-Mem, a pyramidal multimodal memory architecture grounded in Fuzzy-Trace Theory.<n> MM-Mem memory structures hierarchically into a Sensory Buffer, Episodic Stream, and Symbolic.<n>Experiments confirm the effectiveness of MM-Mem on both offline and streaming tasks.
  arXiv  Detail & Related papers  (2026-03-02T05:12:45Z)
• Training Large Reasoning Models Efficiently via Progressive Thought Encoding [63.254758972725654]
  Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency.<n>We introduce Progressive Thought, a parameter-efficient fine-tuning method that enables LRMs to reason effectively under fixed-size caches.
  arXiv  Detail & Related papers  (2026-02-18T20:03:38Z)
• Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents [26.39049374286037]
  External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making.<n>Existing paradigms typically follow a two-stage process: computationally expensive memory construction followed by naive retrieval-augmented generation.<n>We propose CoM (Chain-of-Memory), a novel framework that advocates for a paradigm shift toward lightweight construction paired with sophisticated utilization.
  arXiv  Detail & Related papers  (2026-01-14T04:42:15Z)
• SimpleMem: Efficient Lifelong Memory for LLM Agents [73.74399447715052]
  We introduce SimpleMem, an efficient memory framework based on semantic lossless compression.<n>We propose a three-stage pipeline designed to maximize information density and token utilization.<n> Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost.
  arXiv  Detail & Related papers  (2026-01-05T21:02:49Z)
• TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs [57.217593337454026]
  TokenSqueeze is a novel Long2Short method that condenses reasoning paths while preserving performance and relying exclusively on self-generated data.<n>We show that TokenSqueeze reduces token usage while maintaining accuracy on the MATH500 benchmark.
  arXiv  Detail & Related papers  (2025-11-17T10:38:56Z)
• PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models [14.824367675818355]
  Large reasoning models (LRMs) such as Claude 3.7 Sonnet and OpenAI o1 achieve strong performance on mathematical benchmarks using lengthy chain-of-thought (CoT) reasoning.<n>This inflates token usage and cost, limiting deployment in latency-sensitive or API-constrained settings.<n>We introduce PREMISE, a prompt-only framework that reduces reasoning overhead without modifying model weights.
  arXiv  Detail & Related papers  (2025-06-12T14:05:09Z)
• LightThinker: Thinking Step-by-Step Compression [74.34839026338342]
  We propose LightThinker, a method that enables large language models to dynamically compress intermediate thoughts during reasoning.<n>Inspired by human cognitive processes, LightThinker compresses thought steps into compact representations and discards the original reasoning chains.<n>Experiments show that LightThinker reduces peak memory usage and inference time, while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-02-21T16:57:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.