Method Drift›Long-context / context-window extension
CoA
Long-context / context-window extension
superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 2 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating CoA. Values are copied from the source paper's tables — verify against the cited paper.
- Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration
GoA beats CoA · Average F1 [Llama 3.1 8B, 2K context]
48.67 vs 38.54
- Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration
GoA beats CoA · Average F1 [Llama 3.1 8B, 8K context]
49.18 vs 46.08
- Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration
GoA beats CoA · Average F1 [Qwen3 8B, 2K context]
42.06 vs 39.47
- Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration
GoA beats CoA · Average F1 [Qwen3 8B, 8K context]
48.98 vs 44.81
- Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration
XpandA beats CoA · HotpotQA [Qwen2.5-7B-Inst-1M]
64.5 vs 62.1
- Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration
XpandA beats CoA · Narr.QA [Qwen2.5-7B-Inst-1M]
26.4 vs 25.3
- Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration
XpandA beats CoA · CR [Qwen2.5-7B-Inst-1M]
17.4 vs 13.4
- Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration
XpandA beats CoA · MIR [Qwen2.5-7B-Inst-1M]
13.9 vs 9.7
- Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration
XpandA beats CoA · Code.Debug [Qwen2.5-7B-Inst-1M]
40.5 vs 33.3
- Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration
XpandA beats CoA · Code.Run [Qwen2.5-7B-Inst-1M]
25.8 vs 18.4
- Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration
XpandA beats CoA · GraphWalks [Qwen2.5-7B-Inst-1M]
32.5 vs 30.3
- Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration
XpandA beats CoA · MRCR [Qwen2.5-7B-Inst-1M]
15.3 vs 11.9
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.