Reasoning Fine-Tuning Induces Persistent Latent Policy States

Authors: Abir Harrasse, Michael Lan, Hunar Batra, Fateme Hashemi Chaleshtori, Chaithanya Bandi

Abstract: Reasoning-specialized language models show large performance gains over base models, yet the internal changes responsible for improved multi-step reasoning remain poorly understood. It is unclear whether reasoning fine-tuning improves local token-level competence or globally reorganizes how models structure inference over time. We address this question by modeling Chain-of-Thought reasoning as a s… ▽ More Reasoning-specialized language models show large performance gains over base models, yet the internal changes responsible for improved multi-step reasoning remain poorly understood. It is unclear whether reasoning fine-tuning improves local token-level competence or globally reorganizes how models structure inference over time. We address this question by modeling Chain-of-Thought reasoning as a switching dynamical system (SDS), in which internal representations evolve under discrete latent policy states. Our framework combines time-aware contrastive representation learning with discrete regime discovery to recover latent policies from activation trajectories. Across four benchmarks and model scales from 1.5B to 32B parameters, reasoning-fine-tuned models exhibit richer latent-policy organization than their base counterparts, characterized by more differentiated transition structure and model-dependent changes in state utilization, persistence, and mixing. The recovered regimes exhibit functional specialization aligned with distinct reasoning stages, and extensive controls confirm that their structure is not explained by correctness, representation learning, or modeling priors, but depends on the coherent temporal organization of reasoning trajectories. Causal interventions further show that the regimes are functionally meaningful: state-swap ablations reduce one-step predictive fit, while transplanting reasoning dynamics into base models improves performance on challenging reasoning problems. Finally, SDS-guided pruning of failure-prone reasoning prefixes outperforms self-consistency in 11 of 12 model-dataset settings, with gains of up to 12.5 percentage points. Together, our results suggest that reasoning fine-tuning globally reorganizes latent dynamics, offering a new lens for mechanistic analysis and process-level control of reasoning models. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing

Authors: Michael Lan, Narmeen Fatimah Oozeer, Chaithanya Bandi, Philip Quirke, Austin Meek, Fazl Barez, Amirali Abdullah

Abstract: While mechanistic interpretability (MI) has produced important insights into neural network internals, the field has yet to establish a standardized system to audit experiments. As such, many of its findings remain underutilized in safety-critical applications such as medical AI and autonomous systems, as stakeholders cannot certify their validity. Recent work demonstrates this concretely: two pap… ▽ More While mechanistic interpretability (MI) has produced important insights into neural network internals, the field has yet to establish a standardized system to audit experiments. As such, many of its findings remain underutilized in safety-critical applications such as medical AI and autonomous systems, as stakeholders cannot certify their validity. Recent work demonstrates this concretely: two papers found conflicting conclusions for the same behavior, and a third study revealed that both were partially correct but incomparable due to methodological inconsistencies. Without standardized auditing, such ambiguities hinder adoption in high-stakes contexts requiring strong correctness guarantees. We call for the MI community to work towards developing a novel reviewing system that complements peer review via: (1) Continuous reviewing supported by a \emph{Collaborative Reviewing Platform} where meta-science results and discussions (such as critiques, negative results, post-hoc extensions, reproductions, replications, and partial results) that fit outside of papers are organized and discussed, allowing for comments and revisions to be made at any time (2) Generalizing good practices found on this platform into expert-verified guidelines and protocols to improve auditing efficiency, and (3) Source-based auditing systems that track arguments which claims depend on. This position paper encourages constructive debate over the necessity, design and implementation of such a framework, providing early concrete examples to help catalyze these dialogues. Overall, we propose that auditing MI itself is essential for its application in AI safety, industry, and governance. △ Less

Submitted 24 April, 2026; originally announced June 2026.

MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers

Authors: Chaithanya Bandi, Razvan-Gabriel Dumitru, Ben Hertzberg, Divyansh Agarwal, Geobio Boo, Tejas Polakam, Sami Hassaan, Jeff Da, HiJae Kim, Vipul Gupta, Manasi Sharma, Andrew Park, Martin Dimakis, Ernesto Gabriel Hernandez Montoya, Dan Rambado, Ivan Salazar, Rafael Cruz, MohammadHossein Rezaei, Chetan Rane, Ben Levin, Daniel Yue Zhang, Brad Kenstler, Bing Liu

Abstract: The Model Context Protocol (MCP) is emerging as a standard interface through which large language model (LLM) agents discover and invoke external tools. However, existing MCP evaluations fall short along three key axes: realistic multi-step workflows with cross-server orchestration, breadth across authentic MCP servers rather than mocks, and structured, reproducible claim-level scoring disentangle… ▽ More The Model Context Protocol (MCP) is emerging as a standard interface through which large language model (LLM) agents discover and invoke external tools. However, existing MCP evaluations fall short along three key axes: realistic multi-step workflows with cross-server orchestration, breadth across authentic MCP servers rather than mocks, and structured, reproducible claim-level scoring disentangled from agent verbosity or style. We introduce MCP-Atlas, a benchmark for measuring tool-use competency against production MCP servers. MCP-Atlas contains 1,000 natural-language tasks written and verified by human experts spanning 36 real MCP servers and 220 tools. Prompts do not specify servers, tools, or parameters, requiring agents to identify relevant tools among semantically plausible distractors and to compose multi-step, cross-server workflows. Each task is scored with a claim-level rubric, where final answers are scored against atomic factual claims grounded in tool outputs. This answer-centric scoring permits valid alternative tool-call trajectories to receive credit. We pair this with an 11-category diagnostic taxonomy that disentangles tool-call failures from cognitive failures in task understanding, synthesis, parsing, and stopping. Evaluating 20 frontier models from six providers under matched task-level conditions, we find pass rates up to 82.2% at a 0.75 claim coverage threshold and a clear three-tier performance structure. Automated diagnostics show that 63.3% of diagnosed failures are cognitive rather than tool-call related. Notably, several high-performing models fail after successful tool execution due to premature stopping or incorrect synthesis. We release the task schema, containerized harness, claim evaluator, and a 500-task public split, while reserving a 500-task private split to preserve leaderboard integrity. The code is at https://github.com/scaleapi/mcp-atlas. △ Less

Submitted 19 May, 2026; v1 submitted 31 January, 2026; originally announced February 2026.

ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents

Authors: Manasi Sharma, Chen Bo Calvin Zhang, Chaithanya Bandi, Clinton Wang, Ankit Aich, Huy Nghiem, Tahseen Rabbani, Ye Htet, Brian Jang, Sumana Basu, Aishwarya Balwani, Denis Peskoff, Marcos Ayestaran, Sean M. Hendryx, Brad Kenstler, Bing Liu

Abstract: Deep Research (DR) is an emerging agent application that leverages large language models (LLMs) to address open-ended queries. It requires the integration of several capabilities, including multi-step reasoning, cross-document synthesis, and the generation of evidence-backed, long-form answers. Evaluating DR remains challenging because responses are lengthy and diverse, admit many valid solutions,… ▽ More Deep Research (DR) is an emerging agent application that leverages large language models (LLMs) to address open-ended queries. It requires the integration of several capabilities, including multi-step reasoning, cross-document synthesis, and the generation of evidence-backed, long-form answers. Evaluating DR remains challenging because responses are lengthy and diverse, admit many valid solutions, and often depend on dynamic information sources. We introduce ResearchRubrics, a standardized benchmark for DR built with over 2,800+ hours of human labor that pairs realistic, domain-diverse prompts with 2,500+ expert-written, fine-grained rubrics to assess factual grounding, reasoning soundness, and clarity. We also propose a new complexity framework for categorizing DR tasks along three axes: conceptual breadth, logical nesting, and exploration. In addition, we develop human and model-based evaluation protocols that measure rubric adherence for DR agents. We evaluate several state-of-the-art DR systems and find that even leading agents like Gemini's DR and OpenAI's DR achieve under 68% average compliance with our rubrics, primarily due to missed implicit context and inadequate reasoning about retrieved information. Our results highlight the need for robust, scalable assessment of deep research capabilities, to which end we release ResearchRubrics(including all prompts, rubrics, and evaluation code) to facilitate progress toward well-justified research assistants. △ Less

Submitted 10 November, 2025; originally announced November 2025.

Position: Require Frontier AI Labs To Release Small "Analog" Models

Authors: Shriyash Upadhyay, Chaithanya Bandi, Narmeen Oozeer, Philip Quirke

Abstract: Recent proposals for regulating frontier AI models have sparked concerns about the cost of safety regulation, and most such regulations have been shelved due to the safety-innovation tradeoff. This paper argues for an alternative regulatory approach that ensures AI safety while actively promoting innovation: mandating that large AI laboratories release small, openly accessible analog models (scale… ▽ More Recent proposals for regulating frontier AI models have sparked concerns about the cost of safety regulation, and most such regulations have been shelved due to the safety-innovation tradeoff. This paper argues for an alternative regulatory approach that ensures AI safety while actively promoting innovation: mandating that large AI laboratories release small, openly accessible analog models (scaled-down versions) trained similarly to and distilled from their largest proprietary models. Analog models serve as public proxies, allowing broad participation in safety verification, interpretability research, and algorithmic transparency without forcing labs to disclose their full-scale models. Recent research demonstrates that safety and interpretability methods developed using these smaller models generalize effectively to frontier-scale systems. By enabling the wider research community to directly investigate and innovate upon accessible analogs, our policy substantially reduces the regulatory burden and accelerates safety advancements. This mandate promises minimal additional costs, leveraging reusable resources like data and infrastructure, while significantly contributing to the public good. Our hope is not only that this policy be adopted, but that it illustrates a broader principle supporting fundamental research in machine learning: deeper understanding of models relaxes the safety-innovation tradeoff and lets us have more of both. △ Less

Submitted 15 October, 2025; originally announced October 2025.

Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Language Models

Authors: Philip Quirke, Narmeen Oozeer, Chaithanya Bandi, Amir Abdullah, Jason Hoelscher-Obermaier, Jeff M. Phillips, Joshua Greaves, Clement Neo, Michael Lan, Fazl Barez, Shriyash Upadhyay

Abstract: This position paper argues that the prevailing trajectory toward ever larger, more expensive generalist foundation models controlled by a handful of companies limits innovation and constrains progress. We challenge this approach by advocating for an "Expert Orchestration" (EO) framework as a superior alternative that democratizes LLM advancement. Our proposed framework intelligently selects from m… ▽ More This position paper argues that the prevailing trajectory toward ever larger, more expensive generalist foundation models controlled by a handful of companies limits innovation and constrains progress. We challenge this approach by advocating for an "Expert Orchestration" (EO) framework as a superior alternative that democratizes LLM advancement. Our proposed framework intelligently selects from many existing models based on query requirements and decomposition, focusing on identifying what models do well rather than how they work internally. Independent "judge" models assess various models' capabilities across dimensions that matter to users, while "router" systems direct queries to the most appropriate specialists within an approved set. This approach delivers superior performance by leveraging targeted expertise rather than forcing costly generalist models to address all user requirements. EO enhances transparency, control, alignment, performance, safety and democratic participation through intelligent model selection. △ Less

Submitted 7 October, 2025; v1 submitted 28 May, 2025; originally announced June 2025.

REL: Working out is all you need

Authors: Toby Simonds, Jey Han Lau, Chaithanya Bandi

Abstract: Recent developments, particularly OpenAI's O1 model, have demonstrated the remarkable potential of Large Language Models (LLMs) for complex reasoning tasks. Through analysis of O1's outputs and provided sample Chain-of-Thought (CoT) demonstrations, we observe that it approaches problem-solving in a distinctly human-like manner, systematically brainstorming ideas, testing hypotheses, verifying resu… ▽ More Recent developments, particularly OpenAI's O1 model, have demonstrated the remarkable potential of Large Language Models (LLMs) for complex reasoning tasks. Through analysis of O1's outputs and provided sample Chain-of-Thought (CoT) demonstrations, we observe that it approaches problem-solving in a distinctly human-like manner, systematically brainstorming ideas, testing hypotheses, verifying results, and planning comprehensive solutions. These sophisticated reasoning capabilities remain notably absent in other state-of-the-art language models. In this paper, we hypothesize that this performance gap stems from the limited availability of high-quality reasoning process data in current training sets. We demonstrate that by constructing a specialized dataset focused on explicit problem-solving workflows ("worked solutions"), we can elicit substantially improved planning capabilities from existing models. Additionally, we propose the Reasoning Enhancement Loop (REL), a method for generating synthetic worked solutions. △ Less

Submitted 5 December, 2024; originally announced December 2024.

Debate, Deliberate, Decide (D3): A Cost-Aware Adversarial Framework for Reliable and Interpretable LLM Evaluation

Authors: Abir Harrasse, Chaithanya Bandi, Hari Bandi

Abstract: The evaluation of Large Language Models (LLMs) remains challenging due to inconsistency, bias, and the absence of transparent decision criteria in automated judging. We present Debate, Deliberate, Decide (D3), a cost-aware, adversarial multi-agent framework that orchestrates structured debate among role-specialized agents (advocates, a judge, and an optional jury) to produce reliable and interpret… ▽ More The evaluation of Large Language Models (LLMs) remains challenging due to inconsistency, bias, and the absence of transparent decision criteria in automated judging. We present Debate, Deliberate, Decide (D3), a cost-aware, adversarial multi-agent framework that orchestrates structured debate among role-specialized agents (advocates, a judge, and an optional jury) to produce reliable and interpretable evaluations. D3 instantiates two complementary protocols: (1) Multi-Advocate One-Round Evaluation (MORE), which elicits k parallel defenses per answer to amplify signal via diverse advocacy, and (2) Single-Advocate Multi-Round Evaluation (SAMRE) with budgeted stopping, which iteratively refines arguments under an explicit token budget and convergence checks. We develop a probabilistic model of score gaps that (i) characterizes reliability and convergence under iterative debate and (ii) explains the separation gains from parallel advocacy. Under mild assumptions, the posterior distribution of the round-r gap concentrates around the true difference and the probability of mis-ranking vanishes; moreover, aggregating across k advocates provably increases expected score separation. We complement theory with a rigorous experimental suite across MT-Bench, AlignBench, and AUTO-J, showing state-of-the-art agreement with human judgments (accuracy and Cohen's kappa), reduced positional and verbosity biases via anonymization and role diversification, and a favorable cost-accuracy frontier enabled by budgeted stopping. Ablations and qualitative analyses isolate the contributions of debate, aggregation, and anonymity. Together, these results establish D3 as a principled, practical recipe for reliable, interpretable, and cost-aware LLM evaluation. △ Less

Submitted 23 January, 2026; v1 submitted 6 October, 2024; originally announced October 2024.

An Application of Newsboy Problem in Supply Chain Optimisation of Online Fashion E-Commerce

Authors: Chandramouli Kamanchi, Gopinath Ashok Kumar, Nachiappan Sundaram, Ravindra Babu T, Chaithanya Bandi

Abstract: We describe a supply chain optimization model deployed in an online fashion e-commerce company in India called Myntra. Our model is simple, elegant and easy to put into service. The model utilizes historic data and predicts the quantity of Stock Keeping Units (SKUs) to hold so that the metrics "Fulfilment Index" and "Utilization Index" are optimized. We present the mathematics central to our model… ▽ More We describe a supply chain optimization model deployed in an online fashion e-commerce company in India called Myntra. Our model is simple, elegant and easy to put into service. The model utilizes historic data and predicts the quantity of Stock Keeping Units (SKUs) to hold so that the metrics "Fulfilment Index" and "Utilization Index" are optimized. We present the mathematics central to our model as well as compare the performance of our model with baseline regression based solutions. △ Less

Submitted 5 July, 2020; originally announced July 2020.