Experiential Reflective Learning for Self-Improving LLM Agents
Paper • 2603.24639 • Published • 3
Marc-Antoine Allard
Mallard74
AI & ML interests
Passionate about machine learning, NLP, ASR etc.
Recent Activity
authored a paper about 2 months ago
Experiential Reflective Learning for Self-Improving LLM Agents upvoted an article 8 months ago
Gaia2 and ARE: Empowering the community to study agents upvoted an article 8 months ago
Open-source DeepResearch – Freeing our search agentsOrganizations
authored a
paper about 2 months ago
upvoted 2
articles 8 months ago
Article
Gaia2 and ARE: Empowering the community to study agents
- +9
clefourrier, gregmialz, mlcu, mortimerp9, XciD, tfrere, evijit, RomainFroger, dheeraj7596, CarolinePascal, upiter
• • 134 Article
Open-source DeepResearch – Freeing our search agents
- +3
m-ric, albertvillanova, merve, thomwolf, clefourrier
• • 1.32k upvoted 4
papers 8 months ago
Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents
Paper • 2509.09265 • Published • 47
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
Paper • 2503.09572 • Published • 2
Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example
Paper • 2408.06318 • Published • 1
OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows
Paper • 2508.09124 • Published • 3
upvoted a collection 10 months ago
liked a
Space 10 months ago
upvoted 2
articles 10 months ago
Article
5 Things You Need to Know About Moonshot AI and Kimi K2, the New #1 model on the Hub
fdaudens
• • 25 Article
Introducing ColQwen-Omni: Retrieve in every modality
manu
• • 76 liked 2
models 10 months ago
liked a
Space 10 months ago
published a
Space 10 months ago
upvoted 3
articles 10 months ago
Article
Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders
thomwolf, matthieu-lapeyre
• • 799 Article
SmolLM3: smol, multilingual, long-context reasoner
- +21
eliebak, cmpatino, anton-l, edbeeching, m-ric, nouamanetazi, akseljoonas, guipenedo, hynky, clefourrier, SaylorTwift, kashif, qgallouedec, hlarcher, glutamatt, Xenova, reach-vb, ngxson, craffel, lewtun, loubnabnl, lvwerra, thomwolf
• • 775 Article
Qwen2-VL-OCR-2B-Instruct and VisionOCR-3B-061125 for precise recognition of [messy] handwriting.
prithivMLmods
• • 11 updated a
Space 10 months ago
upvoted a paper 11 months ago