Bridging the Agent-World Gap: Text World Models for LLM-based Agents Paper • 2606.09032 • Published 6 days ago • 7
lllp11/Qwen2_5-7B-SFT_flip_20_ad_original_avg_logprobs_gap_high_30k_data Preview • Updated 27 days ago • 55
lllp11/Qwen2_5-7B-SFT_flip_20_ad_original_avg_logprobs_gap_high_30k_data Preview • Updated 27 days ago • 55
lllp11/Qwen2___5-7B-sft-ultrachat_200k_implicit_margins_top_30k_data Preview • Updated 27 days ago • 52
lllp11/Qwen2___5-7B-sft-ultrachat_200k_implicit_margins_top_30k_data Preview • Updated 27 days ago • 52