5 papers
Evaluating Name-Only Directory Routing for One-Shot Code Search
Manoj Bajaj
Finding the right files is an early challenge for coding agents. We test whether a language model can follow directory and file names to find annotated code files missed by fixed l…
Measure Learning at Steady State: A BIRD-SQL Formula 1 Case Study
Manoj Bajaj
Continual Learning Bench scores learning as short-horizon gain versus a reset baseline and finds naive full-context ICL strongest among the memories it tested. We treat ICL as one…
Synthesizing Procedural Memory: Challenges and Architectures in Automated Workflow Generation
Nishant Gaurav, Adit Akarsh, Ankit Ranjan +1
While CodeMem establishes executable code as the optimal representation for agentic procedural memory, the mechanism for autonomously synthesizing this memory from a blank slate re…
CodeMem: Architecting Reproducible Agents via Dynamic MCP and Procedural Memory
Nishant Gaurav, Adit Akarsh, Tejas Ravishankar +1
Current tool-using AI agents suffer from limited action space, context inefficiency, and probabilistic instability that makes them unsuitable for handling repetitive tasks which ar…
Dynamic ReAct: Scalable Tool Selection for Large-Scale MCP Environments
Nishant Gaurav, Adit Akarsh, Ankit Ranjan +1
We present Dynamic ReAct, a novel approach for enabling ReAct agents to efficiently operate with extensive Model Control Protocol (MCP) tool sets that exceed the contextual memory…