# CL-bench: A Benchmark for Context Learning

arXiv: https://arxiv.org/abs/2602.03587 · HTML: https://mlsanity.com/paper/2602.03587/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- First posted on arXiv 3 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Built on by (most cited first, 30 of 47)

- [SkillNet: Create, Evaluate, and Connect AI Skills](https://mlsanity.com/paper/2603.04448/) (2026)
- [τ-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge](https://mlsanity.com/paper/2603.04370/) (2026)
- [LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues](https://mlsanity.com/paper/2605.12493/) (2026)
- [From Context to Skills: Can Language Models Learn from Context Skillfully?](https://mlsanity.com/paper/2604.27660/) (2026)
- [EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective](https://mlsanity.com/paper/2605.18421/) (2026)
- [SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents](https://mlsanity.com/paper/2606.28434/) (2026)
- [Combee: Scaling Prompt Learning for Self-Improving Language Model Agents](https://mlsanity.com/paper/2604.04247/) (2026)
- [CL-bench Life: Can Language Models Learn from Real-Life Context?](https://mlsanity.com/paper/2604.27043/) (2026)
- [OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation](https://mlsanity.com/paper/2604.10866/) (2026)
- [Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve](https://mlsanity.com/paper/2604.14475/) (2026)
- [EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training](https://mlsanity.com/paper/2604.19485/) (2026)
- [Benchmark Everything Everywhere All at Once](https://mlsanity.com/paper/2606.06462/) (2026)
- [DeonticBench: A Benchmark for Reasoning over Rules](https://mlsanity.com/paper/2604.04443/) (2026)
- [TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction](https://mlsanity.com/paper/2602.11700/) (2026)
- [PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents](https://mlsanity.com/paper/2605.19932/) (2026)
- [Personal Visual Context Learning in Large Multimodal Models](https://mlsanity.com/paper/2605.10936/) (2026)
- [Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis](https://mlsanity.com/paper/2605.25354/) (2026)
- [ContextGuard: Structured Self-Auditing for Context Learning in Language Models](https://mlsanity.com/paper/2605.26827/) (2026)
- [When Should Models Change Their Minds? Contextual Belief Management in Large Language Models](https://mlsanity.com/paper/2605.30219/) (2026)
- [MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?](https://mlsanity.com/paper/2606.01993/) (2026)
- [Hierarchical Experimentalist Agents](https://mlsanity.com/paper/2606.29315/) (2026)
- [Progressive Agent Skill Generation via Reinforcement Learning](https://mlsanity.com/paper/2608.01678/) (2026)
- [OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling](https://mlsanity.com/paper/2608.05141/) (2026)
- [MMCL-Bench: Multimodal Context Learning from Visual Rules, Procedures, and Evidence](https://mlsanity.com/paper/2605.12703/) (2026)
- [Meta-Agent: From Task Descriptions to Verified Multi-Agent Systems](https://mlsanity.com/paper/2605.25233/) (2026)
- [SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing](https://mlsanity.com/paper/2606.29887/) (2026)
- [ToolAnchor: Anchoring Counterfactual Context to Boost Agentic Tool-use Capability](https://mlsanity.com/paper/2607.14145/) (2026)
- [CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition](https://mlsanity.com/paper/2607.25294/) (2026)
- [From Refuse to Richness: Rubric Rewards for Long-Form Hallucination Reinforcement Learning](https://mlsanity.com/paper/2608.12337/) (2026)
- [Agents in the Large: Perception-Centered Architecture for Persistent Agents](https://mlsanity.com/paper/2608.30478/) (2026)

## Abstract (arXiv)

Current language models (LMs) excel at reasoning over prompts using pre-trained knowledge. However, real-world tasks are far more complex and context-dependent: models must learn from task-specific context and leverage new knowledge beyond what is learned during pre-training to reason and resolve tasks. We term this capability context learning, a crucial ability that humans naturally possess but has been largely overlooked. To this end, we introduce CL-bench, a real-world benchmark consisting of 500 complex contexts, 1,899 tasks, and 31,607 verification rubrics, all crafted by experienced domain experts. Each task is designed such that the new content required to resolve it is contained within the corresponding context. Resolving tasks in CL-bench requires models to learn from the context, ranging from new domain-specific knowledge, rule systems, and complex procedures to laws derived from empirical data, all of which are absent from pre-training. This goes far beyond long-context tasks that primarily test retrieval or reading comprehension, and in-context learning tasks, where models learn simple task patterns via instructions and demonstrations. Our evaluations of ten frontier LMs find that models solve only 17.2% of tasks on average. Even the best-performing model, GPT-5.1, solves only 23.7%, revealing that LMs have yet to achieve effective context learning, which poses a critical bottleneck for tackling real-world, complex context-dependent tasks. CL-bench represents a step towards building LMs with this fundamental capability, making them more intelligent and advancing their deployment in real-world scenarios.