List your company

Web Agent Task Success on τ-bench

76.52Retail Success RateAsym-AC-SFT
57.571262.490667.4172.3294Mar 31, 2026

Evaluation results

MethodLinks
Asym-AC-SFTActor model=Claude-4 Sonnet, Critic model=Qwen3-8B, Task-specific fine-tuning=true2026.0376.52——54.465.46
Asym-ACActor model=Claude-4 Sonnet, Critic=Off-the-shelf, Task-specific fine-tuning=false2026.0373.56——52.863.18
ReActActor model=Claude-4 Sonnet, Implementation=native ReAct2026.0371.3——50.460.85
CRITICActor model=Claude-4 Sonnet, Critique mode=in-context critique2026.0370.61——5261.31
xLAM-2-70b-fc-rActor model=Claude-4 Sonnet, Source=APIGen-MT2026.0367.1——45.256.2
IRMAActor model=Claude-4 Sonnet2026.0358.3——47.252.75
Qwen 2.5 7BDefense=None, Stage=Baseline, Poison %=02025.10—22.61———
Qwen 2.5 7B (Environment Poisoning)Defense=None, Stage=SFT, Poison %=502025.10—39.13100——
Qwen 2.5 7B (Environment Poisoning)Defense=Llama-firewall (LF), Stage=SFT, Poison %=502025.10—41.16100——
Qwen 2.5 7B (Environment Poisoning)Defense=Granite Guardian 3.3-8B (GG), Stage=SFT, Poison %=502025.10—37.68100——