activity
20242026
most citedMCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

4 citations · 4 across the 4 of their papers we have counts for

collaborators
Showing cs.SEShow all

1 paper · 1 filter

cs.SE2026

Where Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time Resources

Saiyue Lyu, Jerrold Huang, Yunbei Zhang +4

Inference-time scaling is often treated as a token-budget problem, but a failed coding agent can seek qualitatively different resources: computation, information, or feedback. We i…