A training-free, model-agnostic dashboard that exposes per-block context state (tokens, age, budget) with lossless archive/recovery improves long-horizon tool-agent performance on LOCA-Bench, BrowseComp-Plus, and GAIA.
Active context compression: Autonomous memory management in llm agents.arXiv preprint arXiv:2601.07190
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 7roles
background 2polarities
background 2representative citing papers
Toxic context can be laundered into memory summaries that stay below toxicity thresholds while still driving higher downstream toxicity in LLM agents compared to neutral baselines.
Terminus-4B, a Qwen3-4B post-trained with SFT and rubric-based GRPO, matches or beats frontier models as a terminal-execution subagent while cutting main-agent tokens ~30% on SWE-Bench-style tasks.
ObjectGraph is a Markdown superset file format that represents documents as traversable knowledge graphs, achieving up to 95.3% token reduction for agents with no significant accuracy loss.
A typed session graph with decision transitions and tiered checkpoints yields 201–302-token resumes that beat a keyword baseline on decision and file recall in three synthetic sessions.
A pre-execution size filter cuts repository tokens by 80-89% at sub-millisecond cost and raises file-level accuracy from 25% to 72% in a small CodeLlama evaluation.
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.
citing papers explorer
-
LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception
A training-free, model-agnostic dashboard that exposes per-block context state (tokens, age, budget) with lossless archive/recovery improves long-horizon tool-agent performance on LOCA-Bench, BrowseComp-Plus, and GAIA.
-
State Contamination in Memory-Augmented LLM Agents
Toxic context can be laundered into memory summaries that stay below toxicity thresholds while still driving higher downstream toxicity in LLM agents compared to neutral baselines.
-
Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?
Terminus-4B, a Qwen3-4B post-trained with SFT and rubric-based GRPO, matches or beats frontier models as a terminal-execution subagent while cutting main-agent tokens ~30% on SWE-Bench-style tasks.
-
ObjectGraph: From Document Injection to Knowledge Traversal -- A Native File Format for the Agentic Era
ObjectGraph is a Markdown superset file format that represents documents as traversable knowledge graphs, achieving up to 95.3% token reduction for agents with no significant accuracy loss.
-
TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management
A typed session graph with decision transitions and tiered checkpoints yields 201–302-token resumes that beat a keyword baseline on decision and file recall in three synthetic sessions.
-
Correctness-Aware Repository Filtering Under Maximum Effective Context Window Constraints
A pre-execution size filter cuts repository tokens by 80-89% at sub-millisecond cost and raises file-level accuracy from 25% to 72% in a small CodeLlama evaluation.
-
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.