# Set-shifting Behavioral Test for Harnessed Agents

arXiv: https://arxiv.org/abs/2607.13396 · HTML: https://mlsanity.com/paper/2607.13396/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 27 of its 51 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 27 of 27)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [The Primacy Bias in Deep Reinforcement Learning](https://mlsanity.com/paper/2205.07802/) (2022)
- [MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use](https://mlsanity.com/paper/2310.03128/) (2023)
- [Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2505.01441/) (2025)
- [Can large language models explore in-context?](https://mlsanity.com/paper/2403.15371/) (2024)
- [CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents](https://mlsanity.com/paper/2511.02734/) (2025)
- [LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-based Code Completion](https://mlsanity.com/paper/2406.09834/) (2024)
- [Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models](https://mlsanity.com/paper/2406.03009/) (2024)
- [ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering](https://mlsanity.com/paper/2510.20036/) (2025)
- [Tool Preferences in Agentic LLMs are Unreliable](https://mlsanity.com/paper/2505.18135/) (2025)
- [BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models](https://mlsanity.com/paper/2510.00307/) (2025)
- [Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction](https://mlsanity.com/paper/2603.04783/) (2026)
- [Reflection-Bench: Evaluating Epistemic Agency in Large Language Models](https://mlsanity.com/paper/2410.16270/) (2024)
- [Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks](https://mlsanity.com/paper/2602.19008/) (2026)
- [Visual Large Language Models Exhibit Human-Level Cognitive Flexibility in the Wisconsin Card Sorting Test](https://mlsanity.com/paper/2505.22112/) (2025)
- [Large Language Models are Near-Optimal Decision-Makers with a Non-Human Learning Behavior](https://mlsanity.com/paper/2506.16163/) (2025)
- [From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness](https://mlsanity.com/paper/2602.12285/) (2026)

## Abstract (arXiv)

What happens to an LLM agent's tool choice when the reliable tool silently changes within an ongoing session? We borrow the notion of set-shifting from cognitive psychology to study how well agents adapt to hidden reliability shifts. Our cognitive test for LLM agents mounts libraries of redundant tools and skills, in which many tools solve the same task but differ in hidden reliability. Using a branching schedule, we shift the reliable tool group in the environment and compare it with a stable control, allowing us to isolate the effect of each shift on the agent's behavior. We conduct our study on a panel of LLMs equipped with harnesses and show that the same set of shifts results in distinct behaviors across models: some latch onto a fixed routine within a few turns, whereas others continue to vary. Less capable models often omit the reliable tool group, while frontier models keep calling it alongside the other groups. We introduce a suite of measures to quantify agent behavior after reliability shifts. While policy prompting substantially alters behavior in some tested models, our findings highlight agents' brittleness when changes occur in indirectly observable context.