From the 2 of 5 linked papers with an AI index.
5 papers
STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle
Sagar Deb, Ashwanth Krishnan
The paper presents STOCKTAKE, a 26‑week supply‑chain replenishment benchmark that isolates perception errors from action errors in large language model agents by using a computable…
How Far Can Root Cause Analysis Go on Real-World Telemetry Data?
Athira Gopal, Ashwanth Krishnan
The paper studies why existing classical and LLM‑based methods struggle to pinpoint root causes of microservice failures on large, multimodal telemetry data, and proposes a structu…
ReTreVal: Reasoning Tree with Validation and Cross-Problem Memory for Large Language Models
Abhishek HS, Pavan C Shekar, Arpit Jain +1
Every existing inference-time reasoning framework discards all failure context at problem boundaries, leaving a model solving problem 500 no wiser than it was on problem 1. We pres…
Adaptive Minds: Empowering Agents with LoRA-as-Tools
Pavan C Shekar, Aswanth Krishnan
We investigate a framework in which LoRA adapters are treated as callable tools that a base language model can dynamically select and invoke. We hypothesize that, when adapters are…
ReflexGrad: Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process Routing
Ankush Kadu, Aswanth Krishnan
We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commit to a wrong approach early and exhaus…