Paper Citation Record · LEDGER

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents

As of 18 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 1 inbound Pith citation observation for arXiv:2605.20061.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2605.20061 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T05:35:45.084011Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-31T22:51:52.859785Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

45 of 45 outbound references displayed

verified exact27
verified fuzzy16
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 012ea2ec-3a8e-4547-aaf9-aac28ec6acaf · outbound

This paper cites Back to basics: Revisiting reinforce-style optimization for learning from human feedback in llms.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Back to basics: Revisiting reinforce-style optimization for learning from human feedback in llms

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.623982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dd1f9a8d-ad26-4961-a91f-ad0d90bc6ffc · outbound

This paper cites Digirl: Training in-the-wild device-control agents with autonomous reinforcement learning.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Digirl: Training in-the-wild device-control agents with autonomous reinforcement learning

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.595551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8312bc98-f50d-4c52-9068-4cd3ade9f260 · outbound

This paper cites Exploration by Random Network Distillation.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Exploration by Random Network Distillation

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.576948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 96854874-9cc5-4dd8-8337-aaa084eb7e79 · outbound

This paper cites arXiv preprint arXiv:2511.16108(2025).

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents arXiv preprint arXiv:2511.16108(2025)

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:38:05.629513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7f9a707d-2739-4f66-a25d-cfedcc0afaa5 · outbound

This paper cites Sparse2dense: A keypoint-driven generative framework for human video compression and vertex prediction.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Sparse2dense: A keypoint-driven generative framework for human video compression and vertex prediction

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:38:05.637540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fe5798ea-0ed8-40ee-bd67-1950eebb2d83 · outbound

This paper cites Reinforcement Learning for Long-Horizon Interactive LLM Agents.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Reinforcement Learning for Long-Horizon Interactive LLM Agents

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:38:05.569721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fea07252-93ec-4980-b5e9-f72545c22899 · outbound

This paper cites In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-29T02:04:56.900644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3c5d387c-8159-4439-8748-2ae3e97f5b7b · outbound

This paper cites Process Reinforcement through Implicit Rewards.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Process Reinforcement through Implicit Rewards

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.597087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 31fa0f1d-f338-4d9d-99d8-9a2c52ff711a · outbound

This paper cites Causal-Guided Active Learning for Debiasing Large Language Models.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Causal-Guided Active Learning for Debiasing Large Language Models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:38:05.609691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d6ee478c-0d33-46d2-b74f-66c82d0dfd3a · outbound

This paper cites UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:38:05.556220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 37cda70b-f966-4fed-82e0-ff2e5503d418 · outbound

This paper cites Group-in-Group Policy Optimization for LLM Agent Training.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Group-in-Group Policy Optimization for LLM Agent Training

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.561954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9b88eeb2-e5d9-444f-82b7-04f9cc4a0ca4 · outbound

This paper cites Reward shaping to mitigate reward hacking in rlhf.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Reward shaping to mitigate reward hacking in rlhf

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.615287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation eb0fd076-7e1f-4a4f-b105-2640a98e096c · outbound

This paper cites A survey on llm-as-a-judge.The Innovation.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents A survey on llm-as-a-judge.The Innovation

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.592049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ccad7092-8913-47ea-95d8-154beb4e1c4b · outbound

This paper cites Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633–638.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633–638

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.580201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 536ea10e-a0fe-474f-afa9-d6eb8a971c87 · outbound

This paper cites Retrieval augmented language model pre-training.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Retrieval augmented language model pre-training

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.588522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2eef5082-7dca-4653-9404-39ef37fe7458 · outbound

This paper cites Reason- ing with language model is planning with world model.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Reason- ing with language model is planning with world model

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.556080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c5a900b7-0a5f-4dde-b407-57e7a7d7707e · outbound

This paper cites Sample-Efficient Multi-Round Generative Data Augmentation for Long-Tail Instance Segmentation.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Sample-Efficient Multi-Round Generative Data Augmentation for Long-Tail Instance Segmentation

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.574964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5dc5fd74-4f94-469e-99f6-62e8a1d63375 · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T05:38:05.656716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 72c95792-12f3-42aa-ac25-33d7645719b5 · outbound

This paper cites ABBEL: Learning Natural-Language Belief States for Memory-Efficient Interaction.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents ABBEL: Learning Natural-Language Belief States for Memory-Efficient Interaction

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-06-05T02:15:32.426400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c57c37ad-9882-4127-b0e7-4c4e70b8d627 · outbound

This paper cites Let’s verify step by step.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Let’s verify step by step

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.559369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dbdc0305-8223-4178-8ff1-cade817a5fc2 · outbound

This paper cites Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.476364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1d16f286-4699-4d31-9965-58a52a70115c · outbound

This paper cites Agentic reinforcement learning with implicit step rewards.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Agentic reinforcement learning with implicit step rewards

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:38:05.616554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dde12716-7245-4f66-8666-2fff40799569 · outbound

This paper cites Symbolic and subsymbolic geoai: Geospatial knowledge graphs and spatially explicit machine learning.Trans.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Symbolic and subsymbolic geoai: Geospatial knowledge graphs and spatially explicit machine learning.Trans

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.584526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 66ff8920-b637-422e-9234-891c994c2a83 · outbound

This paper cites Augmented Language Models: a Survey.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Augmented Language Models: a Survey

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.663138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 607163d8-842d-4eca-8978-8dd92539bc64 · outbound

This paper cites Uncertainty quantification in llm agents: Foundations, emerging challenges, and opportunities.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Uncertainty quantification in llm agents: Foundations, emerging challenges, and opportunities

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.619793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dead8b95-81ca-4233-9490-4607066f35e9 · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.628346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0f1eefb2-5760-4d62-8312-4efae2694fa6 · outbound

This paper cites Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-20T09:42:06.579174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b069b3c8-cb86-418f-94b9-e3117a4981e0 · outbound

This paper cites WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:38:05.549697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 74f3a646-af73-4093-9624-7a67d59c5b8a · outbound

This paper cites ToolRL: Reward is All Tool Learning Needs.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents ToolRL: Reward is All Tool Learning Needs

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.643313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cad7fdda-c1b9-451c-b078-33c44222fcaf · outbound

This paper cites A possibility for implementing curiosity and boredom in model-building neural controllers.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents A possibility for implementing curiosity and boredom in model-building neural controllers

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.611174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 30ef472a-92d5-4cc3-97a4-902a8226c098 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.589891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7a71902c-632d-4363-9a7e-e9bd2d163928 · outbound

This paper cites ALFWorld: Aligning Text and Embodied Environments for Interactive Learning.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.543201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c2ca204c-6241-40e0-afc0-1f11f80191cb · outbound

This paper cites Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:38:05.525894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d180fe40-4558-4732-a493-9eefd30a594c · outbound

This paper cites Monte carlo tree search: A review of recent modifications and applications.Artificial Intelligence Review, 56(3):2497–2562.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Monte carlo tree search: A review of recent modifications and applications.Artificial Intelligence Review, 56(3):2497–2562

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.607710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e890ac0e-3c93-4f75-a7f8-2a656467d5f8 · outbound

This paper cites Solving math word problems with process- and outcome-based feedback.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Solving math word problems with process- and outcome-based feedback

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.649948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 71b714c2-ce8d-4902-b461-f6355dafef08 · outbound

This paper cites Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.583384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8f6170ba-ec94-4679-9880-94e7e6a78c23 · outbound

This paper cites RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.463079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b59c1e80-b311-4087-a119-9dbbe090a57a · outbound

This paper cites AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:38:05.470067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 17c7d3ff-d50a-45d5-868b-bfe81a49f6fa · outbound

This paper cites Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:38:05.519281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 62165ce6-d375-4406-99a3-6bcd1478482b · outbound

This paper cites Qwen2.5 Technical Report.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Qwen2.5 Technical Report

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.603208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fc52fa50-7a6d-4d03-9159-74fa85313a7b · outbound

This paper cites Webshop: Towards scalable real-world web interaction with grounded language agents.Advances in Neural Information Processing Systems, 35:20744–20757.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Webshop: Towards scalable real-world web interaction with grounded language agents.Advances in Neural Information Processing Systems, 35:20744–20757

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.603719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 87b15eba-f30b-4a0f-aa93-ef773b398c8e · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in neural information processing systems, 36:46595–46623.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in neural information processing systems, 36:46595–46623

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:43:24.599605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d1c10b34-de1c-4fc3-874a-c8745195a556 · outbound

This paper cites WebArena: A Realistic Web Environment for Building Autonomous Agents.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:05.537641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4ac2a3c3-7399-4a83-aacd-b7eedd783c24 · outbound

This paper cites ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:38:05.483436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation efe056c7-d2ce-416f-b3d3-3d9bc68915a3 · outbound

This paper cites Enhancing agentic rl with progressive reward shaping and value-based sampling policy optimization.

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents Enhancing agentic rl with progressive reward shaping and value-based sampling policy optimization

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T05:38:05.496454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation be776092-685d-4b9a-8c28-90ea9b07680a · inbound

From Scoring to Acting: Outcome-Verified Comparative Self-Distillation for LLM Agents cites this paper.

From Scoring to Acting: Outcome-Verified Comparative Self-Distillation for LLM Agents Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-31T22:51:52.859785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.