Papers6

#context management

Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization

Qianben Chen, Tianrui Qin et al.Feb 26arXiv

This paper shows that letting an AI search many places at the same time (in parallel) can beat making it think in long, slow chains.

#agentic search#parallel evidence acquisition#plan refinement

Agent-Omit: Training Efficient LLM Agents for Adaptive Thought and Observation Omission via Agentic Reinforcement Learning

Intermediate

Yansong Ning, Jun Fang et al.Feb 4arXiv

Agent-Omit teaches AI agents to skip unneeded thinking and old observations, cutting tokens while keeping accuracy high.

#LLM agents#reinforcement learning#agentic RL

PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution

Intermediate

Minghao Yan, Bo Peng et al.Jan 15arXiv

PACEvolve is a new recipe that helps AI agents improve their ideas step by step over long periods without getting stuck.

#evolutionary search#LLM agents#context management

Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering

Intermediate

Xinyu Zhu, Yuzhu Cai et al.Jan 15arXiv

This paper builds an AI agent, ML-Master 2.0, that can work on machine learning projects for a very long time without forgetting what matters.

#Hierarchical Cognitive Caching#cognitive accumulation#ultra-long-horizon autonomy

SCOPE: Prompt Evolution for Enhancing Agent Effectiveness

Beginner

Zehua Pei, Hui-Ling Zhen et al.Dec 17arXiv

SCOPE lets AI agents rewrite their own instructions while they are working, so they can fix mistakes and get smarter on the next step, not just the next task.

#prompt evolution#LLM agents#context management

Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases

Beginner

Sherman Wong, Zhenting Qi et al.Dec 11arXiv

This paper introduces the Confucius Code Agent (CCA), a coding helper built to handle huge real-world codebases with long tasks and many tools.

#coding agents#agent scaffolding#context management