Pith. sign in

REVIEW 7 cited by

A Survey of In-Context Reinforcement Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.07978 v1 pith:CVIQCQIY submitted 2025-02-11 cs.LG

Amir Moeini , Jiuqi Wang , Jacob Beck , Ethan Blaser , Shimon Whiteson , Rohan Chandra , Shangtong Zhang This is my paper
classification cs.LG
keywords learningreinforcementagentsin-contextparametersaction-observationadditionalbackward
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new tasks without updating any parameters by simply conditioning on additional context such as their action-observation histories. This paper surveys work on such behavior, known as in-context reinforcement learning.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. LiteOdyssey: A Lightweight Reasoning AI Agent for Interpretable Rare-Disease Diagnosis

    cs.AI 2026-06 conditional novelty 6.0 of 10

    A clinician-audited diagnostic policy plus public tools lets a single unmodified LLM reach high phenotype-first rare-disease Recall@1 and modestly beat baselines on real UDN patients.

  2. How Does the Pretraining Distribution Shape In-Context Learning? A Fundamental Trade-Off

    cs.LG 2025-10 conditional novelty 6.0 of 10

    Heavy-tailed pretraining distributions improve in-context task selection under distribution shift but worsen ICL generalization, especially in low-data regimes.

  3. Discovering New Theorems via LLMs with In-Context Proof Learning in Lean

    cs.LG 2025-09 unverdicted novelty 6.0 of 10

    LLMs in a conjecturing-proving loop that conditions on their own prior verified Lean proofs discover more hard-to-prove theorems than baselines that generate statements and proofs together.

  4. In-Context Reinforcement Learning via Communicative World Models

    cs.LG 2025-08 unverdicted novelty 6.0 of 10

    CORAL trains an information agent as a world model that sends concise messages to a control agent, improving in-context reinforcement learning and zero-shot adaptation.

  5. LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra

    cs.MA 2025-07 reject novelty 6.0 of 10

    The LLM Economist framework couples persona-conditioned worker agents with an in-context RL planner to search US-bracket tax schedules, yet its Saez benchmark is derived from the planner's own solution and its headlin...

  6. Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Adversarially training a Decision-Pretrained Transformer against learned reward-poisoning attackers makes it robust to test-time reward corruption, outperforming robust bandit baselines in experiments.

  7. ReBRAC-v2: The Return of the King

    cs.LG 2026-08 conditional novelty 5.0 of 10

    A fixed-recipe offline RL method combining normalizing-flow actors, categorical critics, staged training, and test-time refinement beats recent flow-based baselines by 22.5 points averaged over ten OGBench categories.

Pith tools