Papersby GlyphAEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning research paper by Baidu, 2026
Baidu · Agents and evaluation · May 8, 2026 · 5 citations · 21 upvotes · unverified
What it shows
A novel supervision-free credit assignment method for reinforcement learning in language model agents that adapts entropy dynamics at the response level to improve exploration-exploitation trade-offs and task performance.
By Haotian Zhao, Songlin Zhou, Yuxin Zhang and 9 more · arXiv 2605.00425 · PDF
UnverifiedHugging Face's summary; not yet checked by hand.
More from Baidu
All 16FlashMask-3: Efficient and Expressive Mask-Aware Distributed AttentionFlashMask-3 accelerates long-context attention via a Hopper-optimized sparse-mask kernel and distributed context-parallel extensions that eliminate mask-communication overhead and improve training throughput.
Baidu11 upvotesRead →Virtual Head AttentionVirtual Head Attention improves long-context model efficiency by reducing KV cache and compute while preserving quality through lightweight linear query and output transformations.Baidu17 upvotesRead →Unlimited OCR WorksUnlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.Baidu9 citations90 upvotesRead →Memento: Reconstruct to Remember for Consistent Long Video GenerationMemento is a subject-reconstruction-guided framework that improves long-form video generation by preserving recurring subjects through memory-based reconstruction and dual-query mechanisms.Baidu6 citations18 upvotesRead →DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded ReasoningA multi-agent framework for deep research tasks that addresses planning, evidence acquisition, and report synthesis through decoupled components and dynamic optimization mechanisms.Baidu2 citations9 upvotesRead →When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM AgentsToolMaze benchmark reveals that real-world tool failures significantly degrade TIR performance, with implicit semantic failures causing the most severe drops and dynamic replanning emerging as a key bottleneck.Baidu28 citations27 upvotesRead →MapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map GenerationMapAgent is an industrial-grade agentic architecture that combines vision-language processing with constraint-aware reasoning to produce specification-compliant lane maps, achieving high automation rates in large-scale urban mapping.Baidu2 citations18 upvotesRead →Native Audio-Visual Alignment for GenerationNAVA enables joint audio-video generation with improved synchronization and controllability through native audio-visual alignment and context-conditioned denoising.Baidu8 citations31 upvotesRead →
Other agents and evaluation papers
TopicGemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic CapabilitiesGemini 2.X model family, including Gemini 2.5 Pro and Flash, offers superior coding, reasoning, and multimodal understanding capabilities across a range of computational efficiencies.
Google4,594 citations67 upvotesRead →DeepSeek-V3.2: Pushing the Frontier of Open Large Language ModelsDeepSeek-V3.2 introduces DeepSeek Sparse Attention and a scalable reinforcement learning framework, achieving superior reasoning and performance compared to GPT-5 and Gemini-3.0-Pro in complex reasoning tasks.
DeepSeek887 citations275 upvotesRead →WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?WorkArena and BrowserGym evaluate large language model-based agents' ability to perform enterprise software tasks, revealing gaps in current agent capabilities and differences between open and closed-source LLMs.
ServiceNow443 citations2 upvotesRead →Aya Model: An Instruction Finetuned Open-Access Multilingual Language ModelAya, a multilingual generative language model supporting over 50% lower-resourced languages, excels in both generative and discriminative tasks across 99 languages, and provides extensive evaluations and open-source resources.
Cohere438 citations48 upvotesRead →Rubrics as Rewards: Reinforcement Learning Beyond Verifiable DomainsRubrics as Rewards (RaR) framework uses structured rubrics as interpretable reward signals for on-policy training, improving performance in real-world reinforcement learning tasks with subjective criteria.
Scale AI431 citations6 upvotesRead →SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?SWE-Bench Pro is a challenging benchmark for coding models, featuring complex, enterprise-level problems that require substantial code modifications, with performance evaluations showing significant limitations in current models.Scale AI367 citations21 upvotesRead →
About this paper
- Venue
- arXiv.org
- Citations
- 5, 0 influential · Semantic Scholar
- Upvotes
- 21 · Hugging Face
- Lab
- Baidu · on Companies · on Quarterly
Changes
A first count of 0 influential citations.
A first count of 5 citations.
Found by the weekly Hugging Face scan; not yet checked by hand.