26 / papers
How models hold context, carry state, and compose steps beyond next-token prediction. 26 open-access papers by Pranay Mahendrakar, each with a permanent DOI.
Teams of language-model agents increasingly read and write a common memory: a message pool, a blackboard, a bank of distilled experience, a knowledge base served to several frameworks at once. The case for pooling is efficiency, since no…
Two bodies of work quantify uncertainty in multi-step language-model reasoning, and both rest on an independence assumption placed at some unit. Step-level error models multiply per-step reliabilities, which, at an illustrative 95%…
Multi-agent debate, multi-persona prompting and related schemes are usually justified by diversity of viewpoint: several perspectives err differently, so their combination is more reliable than any one of them. That justification is a…
Some proposals to quantify machine self-awareness combine several sub-scores - persistent identity, goal stability, cross-session memory continuity, contradiction detection, uncertainty awareness, self-prediction and introspective access…
Language-model agents that remember across sessions compress what they store: they summarise dialogue, extract facts, or evict cache entries, and then answer later questions from what is left. The compression ratios used to justify these…
Curriculum learning entered large-scale reasoning training through reinforcement learning with verifiable rewards (RLVR): difficulty-ordered or difficulty-filtered problem schedules are now routine in systems built on GRPO and DAPO, and…
A chain-of-thought (CoT) trace is called "faithful" when it accurately represents the computation that produced the model's answer, as opposed to a plausible-sounding story invented after the fact (Jacovi and Goldberg, 2020). Whether…
The dominant frame for large reasoning models borrows a label from dual-process psychology: a fast, intuitive System 1 and a slower, deliberate System 2, with longer chains of thought read as more of the latter and therefore, on average…
A language model that declines to answer is scored the same way whether the reason is that the question has several readings and it picked the wrong one, or that the question has one reading and the model does not know the fact it names…
Two 2024-2026 literatures make claims about resource use in language-model agents that look incompatible. One reports that allocating test-time compute according to problem difficulty beats spending it uniformly, by margins up to a factor…
An agent that stores what happens to it must decide what is worth storing and, later, what is worth reading back. The most-copied mechanism for the first decision is a scalar written at storage time: a language model is shown a record and…
An agent that fails a task and writes down what it should have done instead has produced a specific kind of object: a sentence asserting that a named step caused the failure and that a named alternative would not have. This paper takes…
Memory systems for language-model agents almost all contain a step called consolidation, and almost all of them cite, or gesture at, the complementary learning systems account of hippocampus and neocortex when they name it. In that account…
Persistent memory has become a standard component of language-model agents, and with it a standard assumption: that where a fact lives in a retrievable store rather than in weights, erasing it is a solved problem, because a store supports…
Reinforcement learning with verifiable rewards is the standard route to reasoning-tuned language models, and the field has split over whether its gains leave the training domain. One body of work reports that most models succeeding at…
Two lines of work on language-model agents have converged on the same component from opposite directions. One proposes that an agent keep a persistent safety memory, so that an attack seen once, a request refused once or a source found…
The literature on how language models behave when retrieved context contradicts parametric memory contains a flat contradiction, and neither of its two surveys resolves it. One body of results reports over-reliance on memorised…
An agent with persistent memory writes its own records, and two of them can disagree. Across the published systems examined here the resolution runs in one direction: the newer record supersedes the older. This paper argues that the…
Process reward models are introduced, almost without exception, as models that score whether an individual reasoning step is correct. This paper argues that the phrase "process supervision" is currently attached to three different target…
Out-of-distribution detection was formalised for a setting in which the training distribution is known, the label space is closed, and a designated test set stands in for everything outside it. Foundation models satisfy none of those…
Persistent agent memory has acquired a security literature that models contamination as adversarial injection, and detectors are trained and evaluated on attacker-generated distributions. A separate empirical literature reports the same…
A model trained with reinforcement learning from verifiable rewards beats its base model at one sample and loses to it at many. The field has read that crossover as a measurement of the reasoning boundary and has spent two years arguing…
State-space models did not merely "open a door" beyond attention; they walked through it. Mamba, Mamba-2, Samba, Jamba, Granite 4, Hymba, and a growing family of hybrid attention-SSM architectures are now in production language models…
Causal representation learning (CRL) — the recovery of latent causal variables and their causal graph from high-dimensional observations — has produced a substantial body of theoretical results in the past five years. CITRIS, CauCA, CRID…
Modern reasoning systems are dominated by autoregressive models trained with reinforcement learning on reasoning trajectories — the o1, R1, and Claude 3.7 family of "thinking" models. Energy-based models (EBMs) offer a theoretically…
In-context learning (ICL) — the ability of a transformer language model to acquire a new input-output mapping from a handful of demonstrations in its prompt, with no weight updates — remains the most striking and least understood…
Pranay Mahendrakar has published 26 open-access papers on Reasoning & Memory: "Pooling Experience Spends Independence Twice", "Errors That Should Compound, and When They Do", "Perspectives Without Independence", "Self-Model or Self-Simulation? A Machine Self-Awareness Index Averages Sub-Scores With No Common Referent and No Fixed Sign, Why Persistent Identity, Goal Stability and Memory Continuity Are Not Evidence of Self-Access, and the Validity Tests Any Composite Would Have to Pass", "Compressed Once, Read Many Times", "Curriculum Is Three Claims, Not One", "Faithful to What? Four Instruments for Chain-of-Thought Faithfulness Disagree With Each Other, and the One Ground-Truth Check Run So Far Found Most of Them Near Chance", "When Deliberation Hurts", "Two Kinds of Missing", "Three Things Called Budget Awareness", "Scored Before the Question Exists", "A Lesson Is an Untested Counterfactual", "Consolidation Without Weights", "Delete Names Five Operations", "Transfer Is a Directed Relation", "A Safety Memory Is a Declassification Channel", "A Conflict Is Constructed Before It Is Measured", "Newer Is Not Truer", "A Step Score Is Not a Step Verdict", "Out-of-Distribution With Respect to What? Four Referents Behind One Predicate, and Why OOD Detection Results Do Not Transfer to Foundation-Model Reasoning", "Intent Is Not a Property of the Record", "The Crossover Does Not Carry the Claim", "Memory Architectures Beyond Attention", "Causal Representation Learning from Observational Video", "Energy-Based Models for Reasoning" and "Mechanistic Interpretability of In-Context Learning". Each is deposited on Zenodo with a permanent DOI and is free to read.
