Debangshu Banerjee

debangshubanerjee's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 5 papers 4 days ago

AgentSPEX: An Agent SPecification and EXecution Language

Paper • 2604.13346 • Published Apr 14 • 164

δ-mem: Efficient Online Memory for Large Language Models

Paper • 2605.12357 • Published 5 days ago • 109

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

Paper • 2604.02721 • Published Apr 3 • 628

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation

Paper • 2604.10098 • Published Apr 11 • 81

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping

Paper • 2604.11297 • Published Apr 13 • 143

upvoted 2 papers about 1 month ago

TRACE: Capability-Targeted Agentic Training

Paper • 2604.05336 • Published Apr 7 • 14

SEVerA: Verified Synthesis of Self-Evolving Agents

Paper • 2603.25111 • Published Mar 26 • 31

upvoted a paper 3 months ago

DafnyPro: LLM-Assisted Automated Verification for Dafny Programs

Paper • 2601.05385 • Published Jan 8 • 4

upvoted a paper 4 months ago

Enforcing Temporal Constraints for LLM Agents

Paper • 2512.23738 • Published Dec 25, 2025 • 7

upvoted a paper 5 months ago

BEAVER: An Efficient Deterministic LLM Verifier

Paper • 2512.05439 • Published Dec 5, 2025 • 36

upvoted a collection 11 months ago

dLLM

Collection

20 items • Updated Mar 9 • 5

upvoted a paper 12 months ago

DINGO: Constrained Inference for Diffusion LLMs

Paper • 2505.23061 • Published May 29, 2025 • 31

upvoted 2 papers about 1 year ago

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis

Paper • 2503.23145 • Published Mar 29, 2025 • 35

CRANE: Reasoning with constrained LLM generation

Paper • 2502.09061 • Published Feb 13, 2025 • 21