Searcharxiv⌕ Search

arXiv subjects

Rabi Mahapatra

Publications and source records attributed to Rabi Mahapatra.

3 recordsLinked to original sources

Repeating Work Can Lower Energy per Successful Goal in LLM Agents

When a temporary call failure interrupts a tool-using LLM agent, the framework must choose how much completed work to repeat. Repeating less completed work intuitively saves computation, but recovery mechanisms also change subsequent execution and the chance of success. We compare recovery mechanisms by energy per successful goal (EpG), which divides the energy of all task runs (including failed runs) by the number that finish correctly. In controlled vLLM experiments on one node, we measure board energy above idle for eight recovery options on reliably solved multi-turn tasks, with selected comparisons across three model families. For the model tested across all eight options, with the prefix cache retained, starting over has 22 percent lower EpG than continuing after early failures. Under the same cache condition, continuing has 24 percent lower EpG than starting over after late failures. Among all eight recovery options, repeating only the interrupted turn has the lowest observed EpG after early and late tool failures on this model. Holding recovery fixed, retaining the prefix cache reduces prompt tokens needing fresh computation by 86 percent but reduces recovery energy by only 8 percent at contexts up to 7,333 tokens. These measurements and a condition relating recovery energy and success show when repeating work lowers EpG, helping framework developers choose how their agents recover on their intended models and tasks.

cs.PF↗

Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems

Current AI energy benchmarks measure consumption per model invocation. For agentic systems, where a single user goal may trigger multistep orchestration, tool calls, retries, and failure recovery, the invocation count is an implementation artifact rather than a task property, and per inference normalization misrepresents the energy cost of completing a goal. We present A-LEMS (Agentic LLM Energy Measurement System), a cross layer framework that redefines the unit of AI energy accounting as Energy per Successful Goal (EpG): total workflow energy across all attempts, including failures and retries, divided by successfully completed goals. A-LEMS combines a temporal boundary model, a five layer attribution pipeline mapping hardware signals (RAPL on x86; SPBM and DCGM on ARM) to workflow energy, and a reproducibility protocol binding every measurement to hardware, environment, and runtime configuration. Building on EpG, we define the Orchestration Overhead Index (OOI), the ratio of agentic to linear EpG on matched goals under identical success criteria. Across nine task families on Intel x86 and NVIDIA Grace GB10 ARM, CPU only OOI ranges 0.35x to 11.07x. Including GPU dynamic energy, which accounts for 83.8% of agentic EpG in local inference, widens this to 0.4x to 26.48x, so CPU only measurement understates overhead about twofold for reasoning tasks. For remote inference, network wait energy shifts OOI from 2.5x to 2.35x. The overhead arises from orchestration structure (planning, retries, recovery) that induces additional inference calls, not from costlier individual calls. The metric is not biased upward: single tool calculator dispatch inverts to OOI = 0.61x (95% CI [0.35, 0.97]) on x86. Goal level accounting via EpG and OOI provides a measurement foundation for benchmarking agentic AI.

cs.AI↗

A Time-shared Photonic Reservoir Computer for Big Data Analytics

Information processing has reached the era of big data. Big data challenges are difficult to address with traditional Von Neumann or Turing approach. Hence implementation of new computational techniques is highly essential. Nanophotonics with its remarkable speed and multiplexing capability is a promising candidate for such implementations. This paper proposes a novel photonic computing system made-up of Mach-Zehnder interferometer and an optical fiber spool to emulate a powerful machine learning technique called reservoir computing. The proposed system is also integrated with a time-division-multiplexing circuit to facilitate parallel computation of multiple tasks which is first of its kind. The proposed design performs large-scale tasks like spoken digit recognition, channel equalization, and time-series prediction. Experimental results with standard photonic simulator demonstrate significant performance in terms of speed and accuracy compared to state of the art digital and software implementations.

cs.ET↗