Set-shifting Behavioral Test for Harnessed Agents

[2607.13396] Set-shifting Behavioral Test for Harnessed Agents Skip to main content Search Submit Donate Log in Computer Science > Artificial Intelligence arXiv:2607.13396 (cs) [Submitted on 15 Jul 2026 ( v1 ), last revised 28 Aug 2026 (this version, v2)] Title: Set-shifting Behavioral Test for Harnessed Agents Authors: Ye Ziwei View PDF HTML (experimental) Abstract: 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. Comments: Accepted at COLM 2026 Workshop on Agent Behavior Subjects: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Software Engineering (cs.SE) Cite as: arXiv:2607.13396 [cs.AI] (or arXiv:2607.13396v2 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2607.13396 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ziwei Ye [ view email ] [v1] Wed, 15 Jul 2026 02:49:05 UTC (117 KB) [v2] Fri, 28 Aug 2026 05:22:38 UTC (1,091 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.AI < prev | next > new | recent | 2026-07 Change to browse by: cs cs.CL cs.SE References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Set-shifting Behavioral Test for Harnessed Agents#682760
• Set-shifting Behavioral Test for Harnessed Agents#370395
• Harness Learning Enables Generalizable Test-Time Adaptation#1130385
• Harness Learning Enables Generalizable Test-Time Adaptation#1108748
• Code as Agent Harness#209747