mlsanityData to 7 Oct 2026

Elastic Horizon: Discovering the Effective Interaction Frontier in Agentic Reinforcement Learning

arXiv 2609.07247 ↗First posted 7 Sep 2026cs.AIcited by 0

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

Scaling the interaction horizon-the maximum number of environment interactions per episode-improves LLM agents on long-horizon tasks, and curriculum-based methods that progressively expand the horizon outperform fixed-horizon alternatives. However, existing schedules are open-loop: they monotonically increase the horizon until a manually specified maximum, with no mechanism to detect when further expansion stops helping. We propose the effective interaction frontier hypothesis: a dynamic boundary beyond which additional interactions yield diminishing returns while cost grows linearly. We then introduce Elastic Horizon, a closed-loop controller that tracks this boundary via the 90th percentile of successful trajectory lengths. On AppWorld and BFCL, fixed-horizon sweeps reveal clear saturation plateaus; Elastic Horizon stabilizes the horizon inside the saturation band from both under- and over-capacity initializations, attains the best success rates across 7B and 14B backbones, and saves up to 25% of per-step trajectory tokens. Our work shifts the paradigm from how to scale interaction horizons to when to stop scaling.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 11 of its 21 references that are in the map. First posted on arXiv 7 Sep 2026.

Builds on

11 of 21 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning24 Apr

Other references · 10

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2020Scaling Laws for Neural Language Modelscited by 6,411
  4. 2024AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agentscited by 359
  5. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
  6. 2017Automatic Goal Generation for Reinforcement Learning Agentscited by 252
  7. 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 243
  8. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 185
  9. 2025Budget-Aware Tool Use Enables Effective Agent Scalingcited by 42
  10. 2025Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agentscited by 18

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
  2. 2025Horizon Reduction Makes RL Scalable
  3. 2026CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents
  4. 2026ASTER: Agentic Scaling with Tool-integrated Extended Reasoning
  5. 2025Environment Scaling for Interactive Agentic Experience Collection: A Survey
  6. 2026TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios
  7. 2026StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
  8. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning