> Markdown version of [/events/conference-india-2026/sessions/2057-recursive-language](https://www.wearedevelopers.com/events/conference-india-2026/sessions/2057-recursive-language). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Recursive Language Models: Scaling infinitely beyond the Context Window


- **Date:** Thursday, Nov 26, 2026
- **Time:** 18:30–19:00 (30 min)
- **Room:** Stage 3 - powered by GitHub
- **Event:** Conference India 2026

## Description

Recursive Language Models (RLMs) are a novel inference framework developed by MIT CSAIL. Unlike traditional methods that feed entire prompts into a model, RLMs treat the context as an external variable within a Python REPL environment, allowing the AI to explore, partition, and summarise data programmatically. This strategy effectively scales to near-infinite context lengths by utilising recursive sub-calls to process manageable chunks, thereby preventing the "context rot" typically seen in long-form tasks. Empirical results demonstrate that RLMs significantly outperform frontier models, such as GPT-5, on complex benchmarks while maintaining comparable or even lower API costs. Beyond benchmarking, the sources highlight broader research background in GPU programming, software engineering evaluation, and the potential for RLMs to revolutionise agentic workflows in production environments. Overall, RLMs are a scalable, model-agnostic alternative to human-engineered agent scaffolds for high-precision, long-context reasoning. 

## Speaker

### [Jayita Bhattacharyya](https://www.wearedevelopers.com/@jayita-bhattacharyya)

Machine Learning Engineer | International Speaker | Organizer, Bangalore Python User Group (PSF) | Open Source Advocate


## Related talks at this congress

- [Decision models for developers who use LLMs](https://www.wearedevelopers.com/events/conference-india-2026/sessions/2030-decision-models-for) — Anurag Bhandari
- [Enterprise AI Memory at Scale](https://www.wearedevelopers.com/events/conference-india-2026/sessions/2038-enterprise-ai-memory) — Aditya Joshi
- [Bypassing the GPU Tax: Smart Layer-7 Routing with Small Language Models (SLMs)](https://www.wearedevelopers.com/events/conference-india-2026/sessions/2040-bypassing-the-gpu) — Sagar Utekar
- [Your AI Agents Are Bleeding Tokens: Building a Runtime Cost Control Plane for LLMs](https://www.wearedevelopers.com/events/conference-india-2026/sessions/2066-your-ai-agents-are) — Aakriti Aggarwal, Bhavishya Pandit

## Watch remotely

Can’t make it to Bengaluru? Watch this session live with Pro. You also get:

- All full videos, bookmarks, and playlists
- World Congress livestreams

[See pricing](https://www.wearedevelopers.com/pricing)

## Links

- [Get tickets](https://www.wearedevelopers.com/conference-india/tickets)