Benchmarking Task Takeover Across Agent Handoffs

arXiv:2610.36523v1 Announce Type: new Abstract: As agents collaborate on longer tasks, responsibility may pass between models before the work is complete. The receiving model must build on prior decisions, observations, and actions while addressing the remaining requirements. Evaluating this transition requires connecting the information preserved at handoff to how the receiver continues the work, a relationship that task-success and memory-retention scores alone do not capture. We introduce the Handoff State Continuity Benchmark (HSC-Bench), comprising 1,039 tasks that evaluate two complementary aspects of task takeover: recovering relevant repository evidence and continuing from established conversational, tool, and file-work state. Comparisons across six receiving models show that structured handoff state improves repository evidence recovery for every model and continuation performance for most models. The strongest receivers differ between the two tracks, showing that evidence-recovery rankings alone do not characterize performance when continuing from inherited state. By combining these comparisons with checks of subsequent responses and actions, HSC-Bench evaluates both access to prior evidence and adherence to established commitments and completed work. This provides a basis for selecting receiving models and assessing handoff representations according to the work that must be carried forward.

Related

• ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context
• Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents
• CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval
• When Better Turns Do Not Make Better Agents: Diagnosing the Gap Between Next-Turn Metrics and Workflow Success
• Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks

Source: arXiv cs.CL | 2026-10-28