long-horizon-tasks

Tag

Cards List
#long-horizon-tasks

@0xLogicrw: Zhipu AI founder and chief scientist Tang Jie predicts that the biggest breakthrough in large models this year will be long-horizon tasks, where AI can continuously operate in real environments and solve complex problems. Once long-horizon tasks are achieved, today's 'one-person companies' will rapidly become 'no-employee companies...

X AI KOLs Timeline · 2d ago

Zhipu AI founder Tang Jie predicts that the biggest breakthrough in large models this year will be long-horizon tasks, where AI can continuously solve complex problems in real environments, and mentions three technical pillars and Anthropic's progress in autonomous training.

0 favorites 0 likes
#long-horizon-tasks

Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty

arXiv cs.CL · 2d ago Cached

This paper introduces Agent-BRACE, a method that decouples LLM agents into belief state and policy models to handle long-horizon tasks in partially observable environments. By verbalizing state uncertainty, it achieves significant performance improvements over baselines while maintaining constant context window size.

0 favorites 0 likes
#long-horizon-tasks

@jietang: Recent thoughts: The Shift to Long-Horizon Tasks The most likely breakthrough this year will be in long-horizon tasks. …

X AI KOLs Timeline · 2d ago

The article discusses the anticipated breakthrough in long-horizon AI tasks and autonomous agents, suggesting a shift from 'one-person' to 'none-person' companies. It highlights technical pillars like memory, continual learning, and self-judging as key to realizing fully self-evolving AI systems that could redefine AGI and operating systems.

0 favorites 0 likes
#long-horizon-tasks

ReFlect: An Effective Harness System for Complex Long-Horizon LLM Reasoning

arXiv cs.AI · 2026-05-08 Cached

This paper introduces ReFlect, a training-free harness system that wraps LLMs with deterministic error detection and recovery logic to improve performance on complex, long-horizon reasoning tasks.

0 favorites 0 likes
#long-horizon-tasks

Milestone-Guided Policy Learning for Long-Horizon Language Agents

arXiv cs.CL · 2026-05-08 Cached

This paper introduces BEACON, a milestone-guided policy learning framework designed to improve credit assignment and sample efficiency for long-horizon language agents. It demonstrates significant performance improvements over GRPO and GiGPO on benchmarks like ALFWorld, WebShop, and ScienceWorld.

0 favorites 0 likes
#long-horizon-tasks

FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents

arXiv cs.CL · 2026-04-20 Cached

FS-Researcher introduces a file-system-based dual-agent framework that enables LLM agents to conduct deep research beyond context window limits by using persistent external memory as a shared workspace. The framework achieves state-of-the-art results on research benchmarks and demonstrates effective test-time scaling through computation allocation to evidence collection.

0 favorites 0 likes
← Back to home

Submit Feedback