Image de couverture de livre

Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Xiaozhe, Lyu, Tianyi, Yang, Yizhao, Shan, Liang, Yang, Siyi, Zhang, Ligao, Huang, Zhuoyi, Liu, Qingwen, Li, Yang
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

COINBench: Moving Beyond Individual Perspectives to Collective Intent Understanding
par: Li, Xiaozhe, et autres
Publié: (2026)

ConsintBench: Evaluating Language Models on Real-World Consumer Intent Understanding
par: Li, Xiaozhe, et autres
Publié: (2025)

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs
par: Li, Xiaozhe, et autres
Publié: (2026)

AutoContext: Instance-Level Context Learning for LLM Agents
par: Cai, Kuntai, et autres
Publié: (2025)

Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning
par: Huang, Xijie, et autres
Publié: (2023)

Why Retrying Fails: Context Contamination in LLM Agent Pipelines
par: Yang, Zhanfu
Publié: (2026)

ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking Agents
par: Yao, Yilun, et autres
Publié: (2026)

OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
par: Li, Xiaozhe, et autres
Publié: (2026)

What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents
par: Li, Xiaozhe, et autres
Publié: (2026)

OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems
par: Li, Xiaozhe, et autres
Publié: (2025)

Unlocking the Power of LLM Uncertainty for Active In-Context Example Selection
par: Huang, Hsiu-Yuan, et autres
Publié: (2024)

Universal and Context-Independent Triggers for Precise Control of LLM Outputs
par: Liang, Jiashuo, et autres
Publié: (2024)

Towards Monotonic Improvement in In-Context Reinforcement Learning
par: Zhang, Wenhao, et autres
Publié: (2025)

In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
par: Huang, Sili, et autres
Publié: (2024)

Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning
par: Wang, Dayu, et autres
Publié: (2025)

Federated In-Context LLM Agent Learning
par: Wu, Panlong, et autres
Publié: (2024)

Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
par: Zhang, Yong, et autres
Publié: (2025)

Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
par: Zhou, Yang, et autres
Publié: (2025)

LLM Collaboration With Multi-Agent Reinforcement Learning
par: Liu, Shuo, et autres
Publié: (2025)

LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation
par: Tan, Heng, et autres
Publié: (2025)

ByteRover: Agent-Native Memory Through LLM-Curated Hierarchical Context
par: Nguyen, Andy, et autres
Publié: (2026)

ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions
par: Yang, Bufang, et autres
Publié: (2025)

Beyond Mode Collapse: Distribution Matching for Diverse Reasoning
par: Li, Xiaozhe, et autres
Publié: (2026)

Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning
par: Duan, Wei, et autres
Publié: (2026)

Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis
par: Jin, Hongbo, et autres
Publié: (2026)

Demonstration Selection for In-Context Learning via Reinforcement Learning
par: Wang, Xubin, et autres
Publié: (2024)

SkillsInjector: Dynamic Skill Context Construction for LLM Agents
par: Li, Yanchao, et autres
Publié: (2026)

In-Context Reinforcement Learning via Communicative World Models
par: Martinez-Lopez, Fernando, et autres
Publié: (2025)

Active Context Compression: Autonomous Memory Management in LLM Agents
par: Verma, Nikhil
Publié: (2026)

Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs
par: Liu, Peidong, et autres
Publié: (2025)

SIFT: Grounding LLM Reasoning in Contexts via Stickers
par: Zeng, Zihao, et autres
Publié: (2025)

MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pipeline Parallelism
par: Liu, Shulin, et autres
Publié: (2025)

Breaking the Context Bottleneck on Long Time Series Forecasting
par: Ma, Chao, et autres
Publié: (2024)

ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild
par: Yang, Bufang, et autres
Publié: (2025)

Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning
par: Zhang, Kehao, et autres
Publié: (2026)

The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents
par: Wang, Xinrun, et autres
Publié: (2026)

Programmatic Context Augmentation for LLM-based Symbolic Regression
par: Liu, Hao, et autres
Publié: (2026)

Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning
par: Yang, Shan, et autres
Publié: (2026)

How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment
par: Huang, Heyan, et autres
Publié: (2024)

Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents
par: Xia, Fanzeng, et autres
Publié: (2024)