Papers arxiv:2605.07153 Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs Published on May 8 Submitted by Wanli Yang on May 13 Authors: , , , , , , , Abstract Reinforcement learning improves large language model recall of parametric knowledge by redistributing probabilit… …
… The following papers were recommended by the Semantic Scholar API EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprises 2026 AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents 2026 AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-A… …
… View arXiv page View PDF GitHub 19 Add to collection Community An evolutionary framework is proposed for LLM agent memory that unifies fragmented research into three stages—Storage save trajectories , Reflection refine them , and Experience abstract them —driven by the need for long-range consisten… …
… Automated Auditing of LLM Agent Benchmarks 2026 AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair 2026 ValueBlindBench: Agreement-Gated Stress Testing of LLM-Judged Investment Rationales Before Returns Are Observable 2026 JudgeSense: A Bench… …
… The following papers were recommended by the Semantic Scholar API Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora 2026 Self-Consolidating Language Models: Continual Knowledge Incorporation from Context 2026 Self-Improvement of Large Language Models: A Te… …
… View arXiv page View PDF Add to collection Community 🔑 TL;DR PAAC reframes the device-cloud split as a trust boundary rather than a compute split, with two contributions working in tandem: a decoupled agentic architecture and an LLM-driven privacy sanitizer. 🤝 Decoupled Architecture Cloud-reason-an… …
… Multi-Stream LLMs is important because it attacks the interface bottleneck directly. …
… View arXiv page View PDF Project page Add to collection Community ClawGym: full-lifecycle framework for Claw-style personal agents 1️⃣ Data : ClawGym-SynData — 13.5K filtered tasks, persona-driven intents × skill-grounded ops, with mock workspaces & hybrid verification 2️⃣ Training : ClawGym-Agents… …
… This shift moves AI-driven materials science from isolated processes toward integrated and human interactive discovery. …
… The following papers were recommended by the Semantic Scholar API SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent 2026 Argus: Evidence Assembly for Scalable Deep Research Agents 2026 Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks 2026 AgentPSO: Evolving Agent Rea… …