Skip to content
Log in
Sponsored Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt

Author

Pranay M. Mahendrakar

View on Semantic Scholar

25 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#reinforcement learning Open access Oct 2026

A Starting Score Is Not a Ceiling: When Accuracy Before Reinforcement Learning Predicts Accuracy After It, Why Each Proposed Replacement Sees a Different Failure, and the Axis Test That Decides Which Proxy to Trust

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Life of Research Reasoning models are usually built in two stages, supervised fine-tuning and then reinforcement learning against a verifier, and the first stage is usually judged by the benchmark accuracy of its checkpoint. An August 2026 study reports that the st...

Pranay M. Mahendrakar · 0 citations
#reinforcement learning Open access Oct 2026

Optimism Needs a Way Back: What Value an Agent Should Give a State It Did Not Know Existed, Why Every Located Guarantee Borrows Its Answer From a Reset, a Data Horizon or a Reference, and What That Leaves for Unknown Unknowns

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Life of Research A learning agent that reaches a state outside everything it has represented must give that state a value before it can act again, and the reinforcement learning literature offers three answers. Optimism values the unknown high so that the agent goe...

Pranay M. Mahendrakar · 0 citations
#small language model Open access Oct 2026

Hard to Read Is Not Hard to Audit: Why Degrading a Text Image Raises Jailbreak Success in One 2026 Study and Lowers It in Another, Four Accounts That Fit the Same Curve, and the Ablations That Would Separate Them

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Rendering text as an image is now proposed as a way to compress long contexts for multimodal language models, and a 2026 study reports that the same move opens a safety hole: when a harmful request is rendered at a resolution low enough to be hard but not impossibl...

Pranay M. Mahendrakar · 0 citations
#small language model Open access Oct 2026

A Rewrite That Keeps the Label Has Already Read It: Why an LLM Paraphrase Can Raise a Sentiment Classifier's Accuracy Without the Classifier Getting Better, Four Accounts of the Gain, and the Re-Annotation and Neutral-Rate Controls That Would Separate Them

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. A 2026 study reports that sentiment classifiers score higher on reviews rewritten by small language models than on the human originals, by up to 5.8 accuracy points, and reads the gain as stylistic alignment: the rewrite strips idiosyncrasy and hands the classifier...

Pranay M. Mahendrakar · 0 citations
#small language model Open access Oct 2026

Which Signal Did the Synthesis Import? Information, Re-presentation and Selection in Synthetic Pretraining, Why 'the Verifier Is Doing the Work' Holds Only Where Correctness Is the Target, and the Controls That Would Assign the Credit

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. The expectation that language models will keep improving after the supply of human text runs out rests on a claim about synthetic data: that a model, or a family of models, can produce training text worth more than the text it was trained on. A competing reading ho...

Pranay M. Mahendrakar · 0 citations
#small language model Open access Oct 2026

A Contamination Flag Is Not an Inflation Estimate: What Benchmark Contamination Detectors Certify, What Decontamination Is Meant to Buy, and Why the Clean-Subset Comparison That Joins Them Is Biased From Both Sides

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Almost every large language model report now includes a contamination analysis: benchmark items that overlap the training corpus are flagged, the model is rescored on the unflagged remainder, and a small gap is read as evidence that the headline numbers stand. Two...

Pranay M. Mahendrakar · 0 citations
#large language models Open access Oct 2026

Age Is Not Evidence of Staleness: A Recency Decay Is a One-Rate Survival Model, the Rate Belongs to the Fact Rather Than the Clock, and the Silent Change Only a Rate Could Catch Is the Case No Agent-Memory Benchmark Scores

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Language agents that keep memories across sessions usually discount a record by how long ago it was written or last read. That discount was introduced to decide what an agent attends to, but it is increasingly read as a statement about whether a record is still tru...

Pranay M. Mahendrakar · 0 citations
#large language models Open access Oct 2026

Age Is Not Evidence of Staleness: A Recency Decay Is a One-Rate Survival Model, the Rate Belongs to the Fact Rather Than the Clock, and the Silent Change Only a Rate Could Catch Is the Case No Agent-Memory Benchmark Scores

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Language agents that keep memories across sessions usually discount a record by how long ago it was written or last read. That discount was introduced to decide what an agent attends to, but it is increasingly read as a statement about whether a record is still tru...

Pranay M. Mahendrakar · 0 citations
#small language model Open access Oct 2026

Problem Choice Without a Referee: An Automated Novelty Check Certifies an Empty Search, a Rediscovery Benchmark Credits the Hypothesis Humans Found Next, and Every Located Referee of Worth Independent of Proposer and Field Needs the Objective Given

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Pipelines that claim to automate scientific discovery gate their search on a judgement that a proposed idea or problem is novel and worth pursuing. The best-controlled evidence on that judgement points two ways at once: in a blind study involving more than one hund...

Pranay M. Mahendrakar · 0 citations
#small language model Open access Oct 2026

Problem Choice Without a Referee: An Automated Novelty Check Certifies an Empty Search, a Rediscovery Benchmark Credits the Hypothesis Humans Found Next, and Every Located Referee of Worth Independent of Proposer and Field Needs the Objective Given

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Pipelines that claim to automate scientific discovery gate their search on a judgement that a proposed idea or problem is novel and worth pursuing. The best-controlled evidence on that judgement points two ways at once: in a blind study involving more than one hund...

Pranay M. Mahendrakar · 0 citations
#large language models Open access Sep 2026

Does a Model Forget Differently When the Data Is Its Own? RL's Retention Advantage and Model Collapse Are Claims About the Same Loop, and No Study Has Measured Both

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Two literatures make claims about what happens when a language model trains on data that resembles its own distribution. One asks whether reinforcement learning forgets a model's prior capabilities less than supervised fine-tuning does, and answers yes: on-policy R...

Pranay M. Mahendrakar · 0 citations
#large language models Open access Sep 2026

Does a Model Forget Differently When the Data Is Its Own? RL's Retention Advantage and Model Collapse Are Claims About the Same Loop, and No Study Has Measured Both

(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Two literatures make claims about what happens when a language model trains on data that resembles its own distribution. One asks whether reinforcement learning forgets a model's prior capabilities less than supervised fine-tuning does, and answers yes: on-policy R...

Pranay M. Mahendrakar · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.