pith. sign in

Jianghao Lin

Identifiers

  • name variant Jianghao Lin 0.60 · backfill

Papers (18)

  1. Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench cs.CL · 2026 · author #3
  2. Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents cs.CL · 2026 · author #7
  3. Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering cs.CL · 2026 · author #12
  4. SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory cs.CL · 2026 · author #8
  5. MMSkills: Towards Multimodal Skills for General Visual Agents cs.AI · 2026 · author #4
  6. OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention cs.LG · 2026 · author #4
  7. Holder Policy Optimisation cs.LG · 2026 · author #9
  8. Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents cs.CL · 2026 · author #9
  9. SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System cs.MA · 2026 · author #6
  10. InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees cs.LG · 2026 · author #2
  11. From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling math.OC · 2026 · author #1
  12. Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations cs.IR · 2026 · author #3
  13. Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering cs.SE · 2026 · author #20
  14. Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization cs.AI · 2026 · author #9
  15. Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web cs.AI · 2026 · author #19
  16. ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling cs.AI · 2025 · author #1
  17. A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models cs.CL · 2025 · author #9
  18. CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning cs.CL · 2025 · author #3

Mentions

  • 2605.12058 #9 · arxiv_oai · confidence 0.70 Jianghao Lin
  • 2507.15698 #3 · arxiv_oai · confidence 0.70 Jianghao Lin
  • 2605.17079 #3 · arxiv_oai · confidence 0.70 Jianghao Lin
  • 2605.16986 #7 · arxiv_oai · confidence 0.70 Jianghao Lin
  • 2605.09341 #6 · arxiv_oai · confidence 0.70 Jianghao Lin
  • 2605.15721 #12 · arxiv_oai · confidence 0.70 Jianghao Lin
  • 2605.15710 #8 · arxiv_oai · confidence 0.70 Jianghao Lin

Frequent Coauthors