Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL
Paper • 2608.17253 • Published • 93
Chmielewski
Eryk-Chmielewski
AI & ML interests
Senior AI Agent Architect
Recent Activity
liked a model about 4 hours ago
Qwen/Qwen3.8-Flash-Next-FP8 upvoted a paper about 15 hours ago
Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL upvoted a paper about 15 hours ago
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive ExecutionOrganizations
upvoted 18
papers about 15 hours ago
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
Paper • 2608.16157 • Published • 97
Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements
Paper • 2608.17310 • Published • 105
Agent Lightning v1.0: Towards Harnessed Agentic RL
Paper • 2608.17528 • Published • 31
ASI-Bench: At the Dawn of Artificial Superintelligence
Paper • 2608.17271 • Published • 62
Demystifying Agent Skills: Why They Work-Until They Don't
Paper • 2608.14036 • Published • 165
Human-Centric Intelligence in the Era of Foundation Models: A Survey
Paper • 2608.18184 • Published • 9
AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale
Paper • 2608.20634 • Published • 11
FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
Paper • 2607.21596 • Published • 20
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use
Paper • 2608.20202 • Published • 33
Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
Paper • 2608.21156 • Published • 51
From Generation to Simulation: How Far Are World Models from Being True Simulators?
Paper • 2608.23070 • Published • 4
One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows
Paper • 2608.19741 • Published • 10
Towards a Densing Law for User Representation Learning at Billion-Scale Capacity
Paper • 2608.23392 • Published • 26
Prime Agent: A Self-Improving RLM Harness
Paper • 2608.23552 • Published • 39
Apodex 1.1: Scaling Agentic Intelligence for Complex Work
Paper • 2608.23283 • Published • 182
Meta^n: Recursive Self-Improvement through Emergent Depth
Paper • 2608.24735 • Published • 8
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
Paper • 2608.24876 • Published • 20
upvoted a paper about 16 hours ago
upvoted a collection 23 days ago