# SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization

arXiv: https://arxiv.org/abs/2601.22491 · HTML: https://mlsanity.com/paper/2601.22491/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 28 of 28)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://mlsanity.com/paper/2401.10935/) (2024)
- [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://mlsanity.com/paper/2410.23218/) (2024)
- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use](https://mlsanity.com/paper/2504.07981/) (2025)
- [GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents](https://mlsanity.com/paper/2504.10458/) (2025)
- [GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices](https://mlsanity.com/paper/2406.08451/) (2024)
- [ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems](https://mlsanity.com/paper/2505.11831/) (2025)
- [Large Language Model-Brained GUI Agents: A Survey](https://mlsanity.com/paper/2411.18279/) (2024)
- [OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web](https://mlsanity.com/paper/2402.17553/) (2024)
- [Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping](https://mlsanity.com/paper/2011.02669/) (2020)
- [GUI Agents: A Survey](https://mlsanity.com/paper/2412.13501/) (2024)
- [GUI-G2: Gaussian Reward Modeling for GUI Grounding](https://mlsanity.com/paper/2507.15846/) (2025)
- [A Survey on Large Language Models for Mathematical Reasoning](https://mlsanity.com/paper/2506.08446/) (2025)
- [Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications](https://mlsanity.com/paper/2408.10215/) (2024)
- [A Configurable Library for Generating and Manipulating Maze Datasets](https://mlsanity.com/paper/2309.10498/) (2023)
- [Teaching Language Models to Self-Improve through Interactive Demonstrations](https://mlsanity.com/paper/2310.13522/) (2023)
- [Towards Rationality in Language and Multimodal Agents: A Survey](https://mlsanity.com/paper/2406.00252/) (2024)
- [Understanding Reward Ambiguity Through Optimal Transport Theory in Inverse Reinforcement Learning](https://mlsanity.com/paper/2310.12055/) (2023)
- [Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning](https://mlsanity.com/paper/2307.11897/) (2023)

## Abstract (arXiv)

Reinforcement learning with verifiable rewards has emerged as a powerful paradigm for training intelligent agents. However, existing methods typically employ binary rewards that fail to capture quality differences among trajectories achieving identical outcomes, thereby overlooking potential diversity within the solution space. Inspired by the ``sweet spot'' concept in tennis-the racket's core region that produces optimal hitting effects, we introduce Sweet Spot Learning (SSL), a novel framework that provides differentiated guidance for agent optimization. SSL follows a simple yet effective principle: progressively amplified, tiered rewards guide policies toward the sweet-spot region of the solution space. This principle naturally adapts across diverse tasks: visual perception tasks leverage distance-tiered modeling to reward proximity, while complex reasoning tasks reward incremental progress toward promising solutions. We theoretically demonstrate that SSL preserves optimal solution ordering and enhances the gradient signal-to-noise ratio, thereby fostering more directed optimization. Extensive experiments across GUI perception, short/long-term planning, and complex reasoning tasks show consistent improvements over strong baselines on 12 benchmarks, achieving up to 2.5X sample efficiency gains and effective cross-task transferability. Our work establishes SSL as a general principle for training capable and robust agents.