What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents
Paper • 2610.34491 • Published • 23
🔄 In a Training Loop
Pratyay Banerjee
Neilblaze
AI & ML interests
IR, NLP, Pattern Recognition, xAI, Interpretability, Evals
Recent Activity
upvoted a paper about 5 hours ago
What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents upvoted a paper about 5 hours ago
Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data upvoted a paper about 5 hours ago
S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM ReasoningOrganizations
upvoted 20
papers about 5 hours ago
Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data
Paper • 2610.37386 • Published • 25
S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning
Paper • 2610.35518 • Published • 19
WebAnything: From the Wild Web to Scalable Agent Environments
Paper • 2610.37786 • Published • 19
Memory Tax: Dissecting the Net Value of Agent Memory
Paper • 2610.34073 • Published • 26
RSI Arena: Towards Recursive Self-Improvement with Human Feedback
Paper • 2610.33624 • Published • 27
TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving
Paper • 2610.37230 • Published • 27
On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models
Paper • 2610.32770 • Published • 34
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
Paper • 2610.36077 • Published • 49
Work Agents: Systems, Capabilities, and Optimization
Paper • 2610.35845 • Published • 113
rTaste: Do Research Agents Have Taste? Evaluating Early Stage Research Judgment
Paper • 2610.40488 • Published • 3
GEPA-Curator: Curated Learning for Self Improving Agents
Paper • 2610.37651 • Published • 6
MemSteer: Turning User Histories into Supervision for Agent Memory Optimization
Paper • 2610.39276 • Published • 9
HALO: Human-Grounded Granular Evaluation of Proactive Agents
Paper • 2610.39086 • Published • 10
LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents
Paper • 2611.02332 • Published • 9
CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems
Paper • 2610.34722 • Published • 25
Democratizing Robot-Use Agents: A Unified Harness with Open Models
Paper • 2611.01560 • Published • 41
IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?
Paper • 2611.03424 • Published • 25
Order-Only On-Policy Distillation
Paper • 2611.02112 • Published • 25
DecisionRank: On-Policy Distillation for Decision-Model Rerankers
Paper • 2610.42128 • Published • 14