Research map / Reinforcement learning / RL from feedback
Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents
Jiawei Wang, Jiacai Liu, Yuqian Fu, Yingru Li, Xintao Wang, Yuan Lin, Yu Yue, Lin Zhang, Yang Wang, WANG KE
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add EMPG advantage modulation | GRPO Qwen2.5-1.5B-Instruct · ALFWorld | success rate (%): 65.6 -> 73.7 (+8.1) | Improved |
| add EMPG advantage modulation | DAPO Qwen2.5-1.5B-Instruct · ALFWorld | success rate (%): 80.8 -> 88.1 (+7.3) | Improved |
| add EMPG advantage modulation | GRPO Qwen2.5-7B-Instruct · ALFWorld | success rate (%): 74.8 -> 78.5 (+3.7) | Improved |
| add EMPG advantage modulation | DAPO Qwen2.5-7B-Instruct · ALFWorld | success rate (%): 90.0 -> 91.6 (+1.6) | Improved |
| add EMPG advantage modulation | GRPO Qwen2.5-1.5B-Instruct · WebShop | success rate (%): 58.2 -> 60.8 (+2.6) | Improved |
| add EMPG advantage modulation | DAPO Qwen2.5-1.5B-Instruct · WebShop | success rate (%): 73.2 -> 73.8 (+0.6) | No clear effect |
| add EMPG advantage modulation | DAPO Qwen2.5-7B-Instruct · WebShop | success rate (%): 79.6 -> 82.7 (+3.1) | Improved |
| add EMPG advantage modulation | DAPO Qwen2.5-32B-Instruct · Deep Search overall average | score: 62.0 -> 65.3 (+3.3) | Improved |
| add EMPG advantage modulation | DAPO Qwen2.5-32B-Instruct · Deep Search out-of-domain average | score: 59.8 -> 63.7 (+3.9) | Improved |
| add self-calibrating gradient scaling only (ablation) | DAPO Qwen2.5-32B-Instruct · Deep Search out-of-domain average | score: 59.8 -> 63.7 | Improved |
| add future clarity bonus only (ablation) | DAPO Qwen2.5-32B-Instruct · Deep Search in-domain average | score: 63.5 -> 66.1 | Improved |
| add self-calibrating gradient scaling only (ablation) | DAPO Qwen2.5-32B-Instruct · Deep Search in-domain average | score: 63.5 -> 63.7 | No clear effect |
Closest papers by meaning
- AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning (NeurIPS 2026 · similarity 0.92)
- LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models (NeurIPS 2025 · similarity 0.90)
- Reasoning with Exploration: An Entropy Perspective (AAAI 2026 · similarity 0.90)
- Agentic Reinforced Policy Optimization (ICLR 2026 · similarity 0.89)
- Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning (ICML 2025 · similarity 0.89)
- Expanding LLM Agent Boundaries with Strategy-Guided Exploration (NeurIPS 2026 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
