The Signal

Everything that matters in AI, with our take.

Updated through the day. Every headline links straight to the source. The two lines underneath are ours.

research1156 agents716 infra561 labs317 culture268 capital253 regulation233 claude175 openai149 safety103 security89 evaluation77 reasoning61 alignment52 benchmarks50 interpretability48

arXiv cs.CLPaper8d ago

ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback

This is the missing piece for tool-use reliability. A 4B model trained on 11K generated examples reaches 86% accuracy on the Berkeley Function Calling Leaderboard, and crucially, it generalizes to functions outside the training set. If you're training agents on Claude or another model, this data synthesis pattern beats static filtering. The shift from generate-then-filter to generate-verify-refine is the real contribution, not the 11K examples.

research agents tool-use data-synthesis

arXiv cs.CLPaper10d ago

Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe

This is a sharp paper on a bottleneck: open-source models consistently fail on multi-step tool-calling, and there's been no good way to measure or improve that failure. EDGE's trick is elegant: build a dependency graph of how each API's output feeds another, keep only the verified links, and synthesize trajectories along those paths. A 9B model fine-tuned on EDGE data nearly matches a 27B baseline. If you're building agents that chain tools in real systems, this technique for generating training data is immediately useful. For non-agent builders, this is less relevant.

research agents tool-calling data-synthesis