Unverified50% confidenceBenchmarkExact time
The paper conducted RL experiments on Qwen3-8B, and after 40 training steps, EnvSched achieved an average score of 48.81 on the three benchmarks BFCL-v3, tau-Bench, and ACEBench-Agent.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/28/2026
First Seen
Valid until: 1/26/2027
Sources
Related Entities
Related Claims
Unverified3,189 successful rollouts were collected from Qwen3.8-27B for supervised fine-tuning (imitation learning), and performance stagnated at 47.5%, below the results of two rounds of RL training.71% similarUnverifiedThe author's fine-tuning used the QLoRA method, with LoRA rank/alpha of 32/64, a learning rate of 1e-4, batch size 1 with gradient accumulation of 16, AdamW 8-bit optimizer, and training for 1 epoch.69% similarUnverifiedCompared with Qwen3-30B-A3B, Hy-Memory-30B-A3B improves by an average of 11 points, and still scores 56.89 on the EverMemOS framework, which it never saw in training.66% similarUnverifiedQwen2.5-3B-Instruct achieved an overall score of 0.90 on EvidenceFlip, with an action accuracy of 0.90, conflict detection of 1.00, and pressure resistance of 1.00.65% similarUnverifiedOn agentic coding benchmarks such as SWE Bench Pro, Qwen 3.8 reportedly surpasses Opus 4.6 Max on some tasks.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1105988API
curl https://kongchang.com/api/v1/knowledge/claims/1105988MCP
get_claim(id=1105988)