Short contexts maintain LLM performance on long-horizon tasks
Frontier language models sacrifice little to no task accuracy when maintaining short contexts across long-horizon tasks.
Stories per day · 30 days
2 RSS
Relatedagent-evals1ai-benchmarks1compaction1depth-metrics1embodied-ai1hierarchical-planning1inverse-dynamics1llm-context1semantic-state-space-models1terminal-tasks1world-models1
7 stories, newest first · one card per story
Stories tagged #long-horizon-tasks
Paper finds most long-horizon benchmarks lack depth
Audit reveals 94% of synthetic tasks pass in three turns yet depth predicts difficulty better; authors propose DEPTH method and release 105 harder tasks.
ID-WM decouples reachability from control in hierarchical world models
ID-WM uses high-level sampling of feasible transitions and low-level inverse dynamics solving to enable scalable long-horizon planning with 38.5% better performance.
From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
PARTS fine-tunes pretrained robot policies with RL on targeted bottleneck subtasks, boosting long-horizon manipulation success on YAM and Franka robots with minimal human intervention.
Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks
Survey of four harness mechanisms—context budgeting, compaction, todo-state, and memory—that keep long-horizon LLM agents on task across 200+ tool calls.
9
T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks
T1, a 122B MoE terminal agent trained with reinforcement learning, reaches 64.0% on Terminal-Bench 2.1, surpassing GPT-5.4 and GLM-5.1 on long-horizon tasks.
Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks
Researchers propose Feedback-Enriched Environments (FEEs) that reduce reward sparsity and improve RL training of Qwen3-based agents on SciWorld and BFCL.